Systems and methods for dynamic monitoring of drug and antimicrobial resistance trends

Abstract

It provides a system for selecting treatment regimens for specific patients. [Solution] A first data store contains first patient records for first patients, and a second data store contains efficacy rates for multiple treatment regimens against multiple infections and causative pathogens. A first infection for a specific patient and a first treatment regimen to be prescribed are identified. Second patient records are generated by identifying patient records associated with the diagnosis or treatment of the first infection in the first patient records of the first data store. Efficacy rates for the first infection from the second data store are appended to the second patient records. The appended records can be used to generate a dynamic model for determining the likelihood estimate that the first treatment regimen is an appropriate treatment regimen for treating the first infection.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims priority to U.S. Provisional Patent Application No. 62 / 981,439, filed on February 25, 2020, which is hereby incorporated by reference in its entirety.

[0002] Embodiments of the present disclosure relate to systems and methods for providing dynamic situational awareness of the resistance rates of specific pathogens, the success rates of specific antibiotic regimens for treating drug - resistant pathogens, and the susceptibility rates of related pathogens to new antibiotic regimens, on a patient - specific, facility - specific, and region - specific basis. The systems and methods of the present disclosure include data processing including databases and file management, and optimize treatment protocols and include a database system for improving patient prognosis based on real - time data regarding resistance rates, treatment success rates, and susceptibility rates, and treatment prognosis analysis.

Background Art

[0003] The rate of increase and spread of antibiotic - resistant infections continues to rise at an alarming pace. In the United States, approximately 2.8 million antibiotic - resistant infections occur each year, resulting in 35,000 deaths. Although there has been progress in understanding and curbing the spread of antibiotic - resistant infections (or so - called "superbugs" (multidrug - resistant bacteria)), the threat of untreatable infectious diseases caused by bacteria and microorganisms that can spread rapidly continues to grow. Drug resistance is generally associated with the misuse and overuse of antibiotics and other microbial treatments that evolve bacteria into treatment - resistant strains. Addressing antibiotic resistance is extremely important to ensure that life - saving medications are administered effectively and in a timely manner, thereby improving patient prognosis.

Summary of the Invention

[0004] The systems, methods, and devices described herein each have several embodiments, and none of them alone contribute to their desired attributes. Some non-limiting features are briefly described below without limiting the scope of this disclosure.

[0005] Embodiments of this disclosure relate to a database system (also referred to herein as the “System”) for merging and analyzing data from separate, changing datasets, and dynamically generating and applying customized models based on the merged data. The electronic databases of this disclosure enable the storage and retrieval of digital data records. Data records in such databases are electronically and automatically updated and processed in real time without human intervention.

[0006] In one embodiment, a system is provided for selecting a treatment regimen for a particular patient. The system includes a first data store containing a first plurality of patient records for a first plurality of patients, a second data store containing efficacy rates for a plurality of treatment regimens against a plurality of infections and causative pathogens, and a hardware processor. The hardware processor is configured to execute computer-executable instructions that receive from a user a marker indicating a first infection for a particular patient and a first treatment regimen prescribed to treat the first infection, generate a first database containing a second plurality of patient records by identifying patient records associated with the diagnosis or treatment of the first infection in the first plurality of patient records in the first data store, generate a second database containing a second plurality of patient records with efficacy rates for the first infection added from the second data store, and generate a dynamic model configured to determine a likelihood estimate that the first treatment regimen is an appropriate treatment regimen for treating the first infection. The dynamic model is configured to identify a first efficacy rate for a first treatment regimen to treat a first infection, based on a second database, and to identify a second efficacy rate for a second treatment regimen to treat a first infection, based on the second database. The hardware processor is further configured to execute a computer executable instruction that generates a first alert to the user if the identified first efficacy rate is below a first threshold level or the identified second efficacy rate is above a second threshold level. The first datastore can sequentially store additional patient records. The hardware processor can further be configured to dynamically and automatically execute computer executable instructions that update the first and second databases based on patient records associated with the first infection among the additional patient records, thereby updating the first and second efficacy rates.

[0007] The computer executable instruction can be further configured to receive an identifier from the user indicating a medical facility, and the second set of patient records identified by the computer executable instruction are patient records associated with a first infectious disease and the indicated medical facility.

[0008] The computer executable instruction can be further configured to receive an indicator from the user indicating a geographical area, and the second set of patient records identified by the computer executable program instruction are patient records associated with the first infection and the indicated geographical area.

[0009] The computer executable instruction can be further configured to receive an indicator from the user indicating a period, and the second set of patient records identified by the computer executable instruction are patient records associated with the diagnosis or treatment of a first infection within the indicated period.

[0010] The computer-executable instructions can be configured to filter a second set of patient records, each with an effectiveness rate appended, so as to include patient records associated with a specific treatment regimen among several treatment regimens, infections related to the first infection, geographical area, and healthcare facility.

[0011] The computer executable instructions can be further configured to generate a second alert to the user if, after the first and second effectiveness rates have been updated, the first effectiveness rate falls below a first threshold or the second effectiveness rate exceeds a second threshold.

[0012] In another embodiment, a computer implementation method is provided. The computer implementation method selects a treatment regimen for a particular patient using a first data store containing first patient records for a first plurality of patients and a second data store containing efficacy rates for a plurality of treatment regimens against a plurality of infections and causative pathogens. The computer implementation method includes, under the control of one or more processors, receiving a marker indicating a first infection for a particular patient and a first treatment regimen prescribed to treat the first infection; generating a first database containing a second plurality of patient records by identifying patient records associated with the diagnosis or treatment of the first infection in the first plurality of patient records of the first data store; generating a second database containing a second plurality of patient records with efficacy rates for the first infection added from the second data store; and generating a dynamic model configured to determine a likelihood estimate that the first treatment regimen is an appropriate treatment regimen for treating the first infection. The dynamic model is further configured to identify a first efficacy rate for a first treatment regimen to treat a first infection, based on a second database, and to identify a second efficacy rate for a second treatment regimen to treat a first infection, based on the second database. The computer implementation method further includes generating a first alert, under the control of one or more processors, if the identified first efficacy rate is below a first threshold level or the identified second efficacy rate is above a second threshold level.

[0013] The first data store can sequentially store additional patient records, and the computer implementation method may further include updating the first and second databases based on patient records associated with the first infection among the additional patient records, and updating the first and second efficacy rates.

[0014] The computer implementation method may further include receiving a label indicating a medical facility, and the second set of patient records are patient records associated with the first infectious disease and the indicated medical facility.

[0015] The computer implementation method may further include receiving a marker indicating a geographical area, where the second set of patient records are patient records associated with the first infection and the indicated geographical area.

[0016] The computer implementation method may further include receiving an indicator of a period, where the second set of patient records are patient records associated with the diagnosis or treatment of a first infection within the indicated period.

[0017] The computer implementation method may further include filtering a second set of patient records, to which an effectiveness rate has been added, so as to include patient records associated with a specific treatment regimen among a set of treatment regimens, an infection related to the first infection, a geographical area, and a healthcare facility.

[0018] The computer implementation method may further include generating a second alert if, after updating the first and second effectiveness rates, the first effectiveness rate falls below the first threshold or the second effectiveness rate exceeds the second threshold.

[0019] Other embodiments of this disclosure are described below in relation to the appended claims, which may serve as a further summary of this disclosure.

[0020] In various embodiments, a computer system is disclosed which includes one or more hardware computer processors communicating with one or more non-transient computer-readable storage devices, wherein one or more hardware computer processors are configured to execute a plurality of computer executable instructions to cause the computer system to perform operations including one or more embodiments of the above embodiments (including one or more embodiments of the appended claims).

[0021] In various embodiments, computer implementation methods are disclosed in which one or more embodiments of the above-described embodiments (including one or more aspects of the appended claims) are implemented and / or carried out under the control of one or more hardware computing devices configured with specific computer executable instructions.

[0022] In various embodiments, a computer-readable storage medium for storing software instructions is disclosed, wherein, in response to execution by a computing system having one or more hardware processors, the computing system is configured such that the software instructions perform operations including one or more aspects of the embodiments described above (including one or more aspects of the appended claims).

[0023] Specific embodiments and examples are described below, but the subject matter of the present invention extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses, and their modifications and equivalents. Therefore, the scope of this application is not limited by any of the specific embodiments described below. For example, in any method or process disclosed herein, the actions or operations of the method or process may be performed in any suitable order and are not necessarily limited to any specific order disclosed. While various operations may be described sequentially as multiple separate operations for the sake of understanding a particular embodiment, the order of description should not be interpreted as implying that those operations are order-dependent. Furthermore, the structures, systems and / or devices described herein can be realized as integrated components or as separate components. For the purpose of comparing various embodiments, specific aspects and advantages of these embodiments are described. Not all such aspects or advantages are necessarily realized by any particular embodiment. Therefore, for example, various embodiments may be implemented to realize or optimize one advantage or group of advantages taught herein without necessarily realizing other aspects or advantages that may also be taught or suggested herein.

[0024] The above embodiments, as well as other features, embodiments, and advantages of this technology, will be described below with reference to the attached drawings in relation to various embodiments. However, the embodiments shown are merely examples and are not intended to be limiting.

[0025] The diagrams and corresponding descriptions in this specification may include examples of patients, physicians, other caregivers such as nurses, pharmacists, and microbiologists, medicines, diseases and illnesses, and corresponding entities and records. However, these entities and records may be replaced with other entities and records. [Brief explanation of the drawing]

[0026] [Figure 1A] A block diagram or data flow diagram showing a drug therapy database system for providing electronic notifications regarding database records, according to one embodiment. [Figure 1B] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1C] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1D] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1E] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1F] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1G] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1H] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 1I] Exemplary tables and figures that can be implemented in the data flow diagram of the drug therapy database system of FIG. 1A, according to one embodiment. [Figure 2] A diagram showing an example of a block diagram or data flow diagram of a treatment regimen database system referred to as a dynamic system, according to one embodiment of the present disclosure. [Figure 3] An embodiment of a communication flow diagram showing communications exchanged between various components of the system of FIG. 2 to provide electronic notifications regarding database records, according to one embodiment. [Figure 4]This figure shows the overlapping levels of insights available from the system in Figure 2, according to one embodiment. [Figure 5] The block diagram shows one possible configuration of the system in Figure 2, which, according to one embodiment, can dynamically generate and apply models for tracking drug efficacy and track situations to identify potential drug resistance conditions based on information from one or more databases. [Figure 6] Figure 2 is a block diagram corresponding to one embodiment of the hardware and / or software components of the dynamic system and / or an exemplary embodiment of the system. [Modes for carrying out the invention]

[0027] The systems and methods of this disclosure favorably implement appropriate antimicrobial use and antimicrobial resistance (AMR) objectives at various levels, including patient-specific, facility-specific, and region-specific levels. The systems and methods of this disclosure provide healthcare staff with dynamic, real-time insights and contextual awareness regarding drug and antimicrobial resistance trends at three core levels: regional insights and contextual awareness, facility-specific insights and contextual awareness, and patient-specific insights and contextual awareness.

[0028] Physicians, nurses, pharmacists, medical staff, healthcare administrators, medical researchers, and other entities involved in the diagnosis and treatment of infectious diseases (hereinafter referred to as "healthcare professionals") understand the public health threat posed by drug-resistant infections and the potential for misuse and abuse of certain medications to exacerbate such resistance. While healthcare professionals can receive updated drug efficacy information, it is at very infrequent intervals (e.g., every 5-7 years) and is based on aggregate data across broad timeframes and geographical areas. Furthermore, when diagnosing patients and prescribing medications, clinicians such as physicians may not be aware of which available treatment regimens are appropriate or inappropriate, including the type and dosage of medication (e.g., which treatment regimens have been empirically and clinically demonstrated to resolve infections, and which have not).

[0029] Furthermore, physicians may evaluate treatment regimens based on the symptoms a patient is presenting before an infection is diagnosed. In some cases, physicians may not have sufficient information about the patient's previous infections and treatments. For example, a patient diagnosed by a physician may have traveled from a different geographical area to the physician's medical facility, or may have been infected during travel or visits to a different geographical area. Therefore, physicians may have insufficient or inaccurate information about the origin and type of pathogen causing the infection (and, in particular, which treatment regimens the pathogen is resistant to or susceptible to). As a result, physicians may diagnose an infection and prescribe a treatment regimen based on the geographical area of ​​their facility and the information they can obtain from the patient at that time. Therefore, physicians may rely on diagnostic test results (e.g., blood tests, cultures, bacterial identification, and susceptibility testing), which can be time-consuming and may delay the information the physician needs to accurately diagnose the infection and prescribe an appropriate treatment regimen. Therefore, physicians may not know whether the pathogen causing an infection originates from a geographical area where it is more or less resistant to the treatment regimen than in other areas, whether a particular patient has a history of infection caused by the same pathogen, whether a particular patient has a history of resistance to treatment for that pathogen (for reasons related to or unrelated to the pathogen), and / or whether the physician's previous diagnosis and prescription for the same or similar infection was successfully resolved. All of this can be useful in determining what treatment regimen a physician should prescribe for a patient.

[0030] To accurately diagnose infectious diseases and prescribe effective treatment regimens, healthcare professionals need to receive accurate, dynamic, and real-time information. Information received after a patient has been diagnosed and a treatment regimen has been prescribed is less useful than information received at the time of diagnosis and before the regimen is prescribed. Furthermore, providing information on how often physicians prescribe effective treatment regimens could be useful in enabling physicians to adapt their practice to improve patient care by identifying antibiotic misuse or abuse, and in identifying ways in which they can adapt to improve patient care.

[0031] Physicians prescribing inappropriate treatment regimens may not know how to correct or improve their own standard practice. Physicians may not be aware that there are different options for medications whose efficacy rates have changed since the last time they surveyed or received updates on efficacy rates. Furthermore, when treating a particular current patient, a physician may not know whether the chosen treatment regimen successfully resolved a previous patient's infection (for example, whether the type and dosage of medication prescribed caused the physician's previous patient to recover from the infection). For example, a physician may remember that a previous patient presented with infection X and that they prescribed treatment regimen A, but they may not have been informed whether the prescribed treatment regimen resolved infection X in that previous patient. Therefore, physicians may prescribe treatment regimen A to a current patient exhibiting symptoms of infection X without knowing whether treatment regimen A is effective against infection X, or whether there are other factors to consider (e.g., the patient has a history of resistance to treatment with drug A, or the patient has had infection X in a geographical area known to carry strains of infection X resistant to drug A). Furthermore, there is inevitably overlap in the process of diagnosing (or rediagnosing) an infection and where it lies on the clinical spectrum—i.e., whether it is partially treated, nearly completed, or a treatment failure. Reducing this overlap increases the overall economic value proposition and contributes to patient safety and faster treatment.

[0032] Embodiments of the systems and methods of this disclosure provide healthcare professionals with dynamically updated information at the diagnostic and / or prescribing stages of patient care, thereby enabling physicians to adjust and adapt prescribed treatments to improve treatment according to the current situation of a particular patient, while taking into account recent past treatments. The systems and methods of this disclosure utilize real-time or near-real-time data inputs from various data stores, using these data inputs to focus particularly on the current patient and the specific needs and circumstances of the current patient. The data inputs relate to site-specific and region-specific insights in addition to patient-specific insights. As a non-limiting example, if a patient was infected with a pathogen while traveling abroad, the systems and methods could analyze records of similar infections caused by the same pathogen in that foreign country to take into account outcome-dependent variables (e.g., drug resistance, different strains of the pathogen, etc.) when prescribing a treatment regimen.

[0033] Furthermore, in many cases, physicians may not know which tests to order to identify the causative pathogen of a particular patient's infection. For example, testing whether a particular causative pathogen is resistant to a specific treatment regimen may be more useful if the patient has a history of resistance to conventional treatments for that pathogen or a similar pathogen. However, if a physician is aware that the first patient may be infected with a drug-resistant strain of pathogen A, and the second patient is infected with a non-drug-resistant strain of pathogen A, the physician can treat the first patient using a different treatment regimen than the one prescribed for the second patient, for example, by ordering additional blood culture tests from the first patient to test for drug resistance to other antibiotics, without using valuable, limited blood testing resources to test for drug resistance in the second patient. In addition, a physician may prescribe different treatment regimens for the first and second patients based on identified or suspected drug resistance. Overview of Dynamically Updated Parameters

[0034] The implementation of this disclosure addresses the aforementioned deficiencies in the flow of information and contextual awareness in the treatment of infectious diseases. The systems and methods described herein provide dynamically updated region, facility, and patient-specific insights and analyses across five parameters directly related to the appropriate use of antimicrobial agents and diagnostic resources. While the terms “physician” or “specific physician” are used throughout this disclosure, it should be understood that embodiments of the systems and methods described herein provide dynamic insights and contextual awareness to any healthcare professional involved in patient care. Parameter 1: Resistance rate of a specific pathogen or infection

[0035] In the first step, the systems and methods of the present disclosure use dynamically updated data to notify healthcare professionals if resistance rates to a particular pathogen or infection are high within a defined timeframe in their facility and their geographical area. Insights into this parameter may be based on data collected over a timeframe of the physician's choice or a timeframe set by the physician's facility, supervisory authority, or any other entity. In one non-limiting embodiment, the timeframe is a quarter or three-month period ending on the date the physician requested or received the dynamically updated data. Other examples of timeframes include the previous day, previous week, previous two weeks, previous month, previous two months, previous six months, and previous year. It should be understood that any suitable timeframe can be implemented in embodiments of the present disclosure. This data can be provided to the physician in various forms. In one non-limiting embodiment, where the timeframe is the previous quarter, the physician identifies an antibiotic treatment regimen that the physician is considering prescribing to a particular patient.

[0036] In response to the receipt of an identified antibiotic, the system and method of the present disclosure can display to a physician a quarterly heatmap of associated or highly active multidrug-resistant (MDR) pathogens treatable with the selected antibiotic. Examples of MDR pathogens include, but are not limited to, carbapenem-resistant Enterobacteriaceae (CRE) and Acinetobacter baumannii (ACB). The system and method of the present disclosure can display quarterly heatmaps of urine, skin / wound, or respiratory cultures that are positive for associated or highly active MDR pathogens. Upon receiving one or both of these types of quarterly heatmaps, a physician is dynamically informed of how a particular antibiotic candidate is more common than other antibiotic candidates for the treatment of a particular infection caused by a resistant pathogen, compared to resistance records at the physician's facility, such as a hospital or outpatient clinic. Parameter 2: Use of relevant antibiotics (e.g., prescribed, filled, and / or administered) within a specific physician's geographical area and facility.

[0037] The systems and methods of this disclosure use dynamically updated data to inform healthcare professionals of the quantities of relevant antibiotics being used in their specific geographical area and specific facilities to treat specific pathogens identified in Parameter 1 above. It should be understood that the information regarding relevant antibiotic use may include information regarding antibiotics prescribed, filled, and / or administered in the geographical area or facilities of the physician. In a non-limiting embodiment, embodiments of this disclosure inform physicians of research papers that have evaluated the correlation of antibiotics used to treat a specifically identified resistance type. For example, in the case of Carb NS / CRE, the systems and methods described herein display research papers that have evaluated the correlation of the latest antibiotics for treating Carb NS / CRE, such as Xerava, Vabomere, Avycaz, Zemdri, Zerbaxa, and colistin. The systems and methods of this disclosure may evaluate and display other relevant information, such as, but not limited to, likely or common complications associated with the use of relevant antibiotics in a particular physician's geographical area and facilities. For example, the percentage of patients prescribed colistin-based treatment regimens who developed renal impairment can be provided to physicians as an insight. In another non-limiting example, insights regarding antibiotic combination regimens can be provided to physicians based on the antibiotics selected in item Parameter 1 above.

[0038] Finally, the intent of treatment influences a physician's prescribing patterns, which may also vary by geographical area and local cultural practices. Furthermore, hyperspecialists often “overturn” the instructions of hospital physicians or general practitioners. Consequently, the prescribed medication and the administered medication may differ in quantity, strength, and volume. Systems and methods that use the analysis of either or both the prescribed medication and the administered medication (or medication filled in an outpatient setting) may be preferred in embodiments of this disclosure, depending on the type and purpose of the analysis.

[0039] Insights into this parameter may be based on data collected over timeframes selected by the physician or set by the physician's facility, supervisory body, or any other entity. In one non-limiting embodiment, the timeframe is a quarter ending on the date the physician requested or received the dynamically updated data. Other examples of timeframes include the previous day, previous week, previous two weeks, previous month, previous two months, previous six months, and previous year. It should be understood that any suitable timeframe can be implemented in embodiments of this disclosure. Parameter 3: Frequency of inappropriate use of antibiotics in a particular physician's geographical area and facility.

[0040] The systems and methods of this disclosure use dynamically updated data to inform healthcare professionals of the frequency with which the antibiotic selected in the Parameter 1 section is being inappropriately selected for the treatment of resistant pathogens in the healthcare professional's geographical area and the healthcare professional's facilities. In one non-limiting embodiment, an embodiment of this disclosure dynamically informs a physician of the overall or local (e.g., in the physician's geographical area and the physician's facilities) ineffective empirical treatment (IET) rate of the antibiotic selected in the Parameter 1 section above in the recent quarter. In another non-limiting embodiment, an embodiment of this disclosure dynamically informs a physician of the overall or local (e.g., in the physician's geographical area and the physician's facilities) ineffective empirical treatment (IET) rate of common infections in the recent quarter. Examples of common infections include, but are not limited to, SSSI, bacteremia, CAP, HCAP, HAP / VAP, and urinary tract infections (UTI).

[0041] Insights into this parameter may be based on data collected over timeframes selected by the physician or set by the physician's facility, supervisory body, or any other entity. In one non-limiting embodiment, the timeframe is a quarter ending on the date the physician requested or received the dynamically updated data. Other examples of timeframes include the previous day, previous week, previous two weeks, previous month, previous two months, previous six months, and previous year. It should be understood that any suitable timeframe can be implemented in embodiments of this disclosure. Parameter 4: Testing of the latest antibiotics for relevant pathogens and their susceptibility in the geographical area and facilities of a specific physician.

[0042] The systems and methods of this disclosure use dynamically updated data to inform healthcare professionals how often the latest commercially available antibiotic treatment regimens are being tested for the relevant pathogens identified in parameters 2 and 3 above. The dynamically updated data may include information regarding the susceptibility of the latest antibiotics in the specific geographical area of ​​the professionals and in the specific facilities of the professionals. Embodiments of this disclosure are advantageous because they can determine susceptibility rates using real-world data, what types of patient testing are being performed using real-world data, and whether such testing is being performed on hospitalized patients who may require such testing.

[0043] In one non-limiting embodiment, the system and method of the present disclosure evaluates the susceptibility and minimum inhibitory concentration (MIC) distribution of test pathogens to specific antibiotics identified in the parameter 1 section above, both globally and by source. Examples of modern antibiotics not included in conventional periodic testing microbiology panels include Xerava, Vabomere, Avycaz, Zemdri, and / or Zerbaxa. In another non-limiting embodiment, the system and method of the present disclosure evaluates quarterly trends in testing of modern antibiotics. In yet another embodiment, the system and method of the present disclosure evaluates national and local resistance rates of testing for these selected antibiotics against global and source-specific resistance rates associated with specific resistance types. This information may include, for example, resistance rate heatmaps for specific resistance types. Embodiments of the present disclosure can evaluate these insights to assist in the selection of candidate antibiotics identified in the parameter 1 section above.

[0044] Insights into this parameter may be based on data collected over timeframes selected by the physician or set by the physician's facility, supervisory body, or any other entity. In one non-limiting embodiment, the timeframe is a quarter ending on the date the physician requested or received the dynamically updated data. Other examples of timeframes include the previous day, previous week, previous two weeks, previous month, previous two months, previous six months, and previous year. It should be understood that any suitable timeframe can be implemented in embodiments of this disclosure. Parameter 5: Identification of patient-specific risk factors for specific infections and resistance types.

[0045] The systems and methods of this disclosure use dynamically updated data to inform healthcare professionals of patient risk factors for specific infections and resistance types identified in parameters 1-4 above. Implementations of this disclosure can create risk scores for patient populations, enabling healthcare professionals to distinguish specific pathogen types for each infection (e.g., SSI, CAP, HCAP). For example, the risk score may take into account risk factors associated with specific resistance or pathogen types. In another embodiment, the risk score may take into account mixed resistance or pathogen types associated with these risk factors. Implementations of this disclosure can create stepwise models to guide the need to cover specific mixed resistance or pathogen types. The dynamically updated data may include information on the susceptibility of current antibiotics in the specific geographical area of ​​the stakeholders and in the specific facilities of the stakeholders. Embodiments of this disclosure are advantageous because they can determine susceptibility rates using real-world data, what types of patient testing are being performed using real-world data, and whether such testing is being performed on hospitalized patients who may require such testing.

[0046] Insights into this parameter may be based on data collected over timeframes selected by the physician or set by the physician's facility, supervisory body, or any other entity. In one non-limiting embodiment, the timeframe is a quarter ending on the date the physician requested or received the dynamically updated data. Other examples of timeframes include the previous day, previous week, previous two weeks, previous month, previous two months, previous six months, and previous year. It should be understood that any suitable timeframe can be implemented in embodiments of this disclosure.

[0047] Figure 1A is a block diagram or data flow diagram illustrating an exemplary method, according to embodiments of the present disclosure, for providing dynamically updated region-specific, site-specific, and patient-specific insights and analyses of the parameters described above. The flowchart of Method 10 may be performed by any device described herein, for example, the computing system 102 or dynamic system 103 of System 100, which is detailed below. Depending on the embodiment, one or more steps / blocks of Method 10 may be omitted or combined with other steps / blocks, or additional steps / blocks may be added to Method 10.

[0048] In Block 12, the method includes receiving input from a user (such as, but not limited to, a physician, hospital administrator, or other healthcare professional). For example, the user is a physician evaluating a patient suffering from a disease caused by a pathogen. Input from the physician may include a selection of specific antibiotics the physician is considering prescribing, and / or a selection of pathogens the physician suspects or has confirmed to be causing the disease, such as a bacterial infection. In some embodiments, the user provides input that includes both pathogens and antibiotics (for example, if the physician is treating or planning to treat a selected pathogen with a selected antibiotic). In some embodiments, the input includes only the selected pathogens (for example, if the physician is unsure which antibiotic to use to treat a selected pathogen). In some embodiments, the input includes only the selected antibiotics (for example, if the physician is unsure which particular pathogen is causing the infection, but knows which antibiotic to use to treat the patient's symptoms overall).

[0049] Based on the selected antibiotic and / or pathogen, Method 10 proceeds to Block 14, where the resistance rate associated with the selected antibiotic and / or pathogen is identified. For example, Method 10 identifies, retrieves, or retrieves information (e.g., one or more of the following: research papers, reports, culture information, heatmaps, resistance records, etc.) from one or more databases (e.g., a second data store 108 detailed below). An example of a research paper is shown in Figure 1B. In one non-limiting embodiment, a physician may evaluate this research paper and other appropriate research papers to determine whether the resistance rate to the selected antibiotic and / or pathogen is high in the most recent quarter in the physician's geographical area, such as Region 2, or in the physician's facility, such as an acute disease patient treatment facility in Region 2. In the example research paper, the physician can confirm that Carb-NS Pseudomonas aeruginosa has a significantly higher non-susceptibility rate (17.1%) in Region 2, which is the physician's geographical area, than in Regions 1, 3, and 4. Method 10 may retrieve this information and store it locally, for example, in a database in System 100.

[0050] For example, based on the selected antibiotic, Method 10 obtains a relevant heatmap. An example of a heatmap is shown in Figure 1C. The heatmap in this example shows the geographical incidence (per 1000 hospitalized patients) of urine isolates of pathogen X, a specific pathogen, in hospitalized patients. An example of a pathogen is ESBL-ENT (broad-spectrum β-lactamase enterobacteriaceae). Using this heatmap, a physician can determine that the incidence of pathogen X in urine isolates is higher in Southern California, a specific geographical area of ​​the physician, compared to other geographical areas. Further details are provided in the description related to parameter 1 above. Alternatively, Method 10 may obtain heatmaps related to the selected pathogen and / or the selected antibiotic. In another embodiment, if the physician provides both the selected antibiotic and the selected pathogen, Method 10 identifies heatmaps for the selected pathogen and / or the selected antibiotic, or for only one or the other. The heatmaps may show drug resistance information for the selected antibiotic and / or the selected pathogen. For example, a heatmap specific to a selected antibiotic might show drug resistance of the selected antibiotic to pathogens commonly treated by the selected antibiotic over a specific period or over a specific time period in a particular geographical area or facility. A heatmap relating to both the selected antibiotic and the selected pathogens might show drug resistance (determined, e.g., by urine, skin / wound, or respiratory culture) of the selected pathogens to the selected antibiotic over a specific period or over a specific time period in a particular geographical area or facility. In some embodiments, the user also selects a specific geographical area or facility and / or a specific time period as input to the system 100. In some embodiments, the specific geographical area or facility and / or the specific time period are predetermined. The predetermined may be a fixed predetermined based on, for example, the user's location, facility, or parameters detectable by the system. The predetermined may be a dynamic predetermined based on one or more parameters detectable by the system.For example, if the user is a mobile clinic user, the system may identify a geographical area within a threshold distance (e.g., 50 miles (80 km) or 100 miles (160 km)) from the current location of the mobile device used by the mobile clinic user. Based on the information obtained, method 10 may determine how common a selected antibiotic candidate is for treating a selected pathogen, taking into account any drug resistance characteristics of the selected pathogen. In some embodiments, in block 14, method 10 also identifies a specific resistance type based on the selected antibiotic and / or pathogen.

[0051] After various data have been obtained in Block 14, Method 10 may identify the use of appropriate antibiotics for treating drug-resistant pathogens in Block 16. In some embodiments, if the user selects a pathogen and the selected pathogen is not drug-resistant, this step / block of Method 10 may be omitted or skipped (by System 100 or by user selection). In some embodiments, the selected pathogen is drug-resistant, and System 100 identifies the use of appropriate antibiotics to treat the selected pathogen. The identified antibiotics may include the selected antibiotic or antibiotics commonly used to treat selected drug-resistant pathogens. Block 16 may include obtaining specialized research papers on information, such as the selected antibiotic or antibiotics commonly used to treat selected pathogens that are drug-resistant. In some embodiments, the information obtained may further include information on complications or side effects of a particular antibiotic, treatment regimens involving multiple antibiotics, etc. Further details regarding Block 16 are described in the description related to Parameter 2 above. The information obtained may relate to a specific geographical area or facility and may pertain to a selected pathogen (e.g., determined by urine, skin / wound, or respiratory culture) against a selected antibiotic over a specific period or duration. In some embodiments, the user also selects a specific geographical area or facility and / or a specific period as input to Method 10. In some embodiments, the specific geographical area or facility and / or a specific period is predetermined. The predetermined may be a fixed predetermined based on, for example, the user's location, facility, or parameters detectable by the system. The predetermined may be a dynamic predetermined based on one or more parameters detectable by the system. For example, if the user is a mobile clinic user, the system may identify a geographical area within a threshold distance (e.g., 50 miles (80 km) or 100 miles (160 km)) from the current location of the mobile device used by the mobile clinic user.

[0052] An example of a research paper is shown in Figure 1D. In one non-limiting embodiment, a physician may evaluate this research paper to determine how much relevant antibiotics are being used in the physician's geographical area and / or in the physician's facility to treat specific resistant pathogens identified in Block 12. Using the research paper shown in Figure 1D, for example, a physician may determine cumulative high-risk antibiotic use (sorted by total high-risk antibiotic use rate) for four classes of antibiotics, namely Class A, Class B, Class C, and Class D. Examples of antibiotic classes may include cephalosporins, fluoroquinolones, carbapenems, and lincosamides. A physician may determine, for example, that cumulative antibiotic use of Class D antibiotics is particularly high in the physician's hospital.

[0053] In block 18, method 10 determines details of relevant inappropriate antibiotic use for the treatment of drug-resistant pathogens, and this information can be used to inform the user how often a selected antibiotic (or another antibiotic) is inappropriately selected for the treatment of a selected pathogen. For example, method 10 obtains information on effective treatment rates (e.g., from one or more databases). For example, method 10 identifies and / or receives the effective treatment rate of a selected antibiotic against a selected drug-resistant pathogen (in a specific geographical area or facility over a specific period of time). Alternatively, or in addition to this, method 10 identifies and / or receives the effective treatment rate of a selected antibiotic against common drug-resistant pathogens to which that antibiotic is commonly applied. Alternatively, or in addition to this, method 10 identifies and / or receives the effective treatment rate of one or more antibiotics commonly used against a selected drug-resistant pathogen. Details of block 18 are described in the description related to parameter 3 above. The information obtained may relate to a specific geographical area or facility and may be for a selected pathogen against a selected antibiotic over a specific period of time or over a specific period of time. In some embodiments, the user also selects a specific geographical area or facility and / or a specific period as input to the system 100. In some embodiments, the specific geographical area or facility and / or a specific period is predetermined. The predetermined may be a fixed predetermined based on, for example, the user's location, facility, or parameters detectable by the system. The predetermined may be a dynamic predetermined based on one or more parameters detectable by the system. For example, if the user is a mobile clinic user, the system may identify a geographical area within a threshold distance (e.g., 50 miles (80 km) or 100 miles (160 km)) from the current location of the mobile device used by the mobile clinic user.

[0054] Examples of research papers are shown in Figures 1E, 1F, and 1G. In a non-limiting embodiment, a physician may determine the frequency of inappropriate antibiotic use for a particular infection / resistance type in their geographical area and / or facility. For example, a physician may evaluate appropriate and inappropriate antibiotic use as shown in Figure 1E (initial empirical antibiotic therapy for complicated urinary tract infections (cUTIs) caused by pathogen Y) and Figure 1F (clinical characteristics of patients with cUTIs caused by pathogen Y). Examples of pathogens include enterobacteria. In another non-limiting embodiment shown in Figure 1G, a physician may evaluate inappropriate empirical treatment (IET) for antibiotics A-S by pathogen category. Examples of antibiotics include vancomycin-IV, piperacillin / tazobactam-IV, clindamycin-IV, cefepime-IV, ceftriaxone-IV, meropenem-IV, levofloxacin-IV, cefazolin-IV, ampicillin / sulbactam-IV, daptomycin-IV, linezolid-IV, ciprofloxacin-IV, cephthalolin-IV, sulfamethoxazole / trimethoprim-oral, ertapenem-IV, doxycycline-oral, ciprofloxacin-oral, metronidazole-IV, and levofloxacin-oral.

[0055] In block 20, method 10 may identify one or more antibiotics available for treating a selected pathogen, or for replacing a selected antibiotic, or both. Depending on the embodiment, such identification may include receiving and / or analyzing information related to the available antibiotics. For example, method 10 may receive and evaluate susceptibility rates between a pathogen (such as a selected pathogen or associated drug-resistant pathogen) and an antibiotic (such as a selected antibiotic, or an antibiotic commonly used to treat a selected pathogen or associated drug-resistant pathogen). Depending on the embodiment, the information may relate to testing of a new antibiotic or the trend and / or rate of testing (e.g., a new treatment regimen being tested). Details of block 20 are described in the description related to parameter 4 above. The information obtained may relate to a specific geographical area or facility and to a specific period or duration of a selected pathogen against a selected antibiotic. Depending on the embodiment, the user also selects a specific geographical area or facility and / or a specific period as input to system 100. Depending on the embodiment, the specific geographical area or facility and / or a specific period are predetermined. The predeterminant may be a fixed predeterminant based on, for example, the user's location, facility, or parameters detectable by the system. The predeterminant may also be a dynamic predeterminant based on one or more parameters detectable by the system. For example, if the user is a mobile clinic user, the system may identify a geographic area within a threshold distance (e.g., 50 miles (80 km) or 100 miles (160 km)) from the current location of the mobile device used by the mobile clinic user.

[0056] An example of a research paper is shown in Figure 1H. In one non-limiting embodiment, a physician could evaluate this study to determine how often the latest commercially available antibiotics are tested against the pathogens selected in block 12. Using the research paper shown in Figure 1H, for example, a physician could evaluate the source distribution of non-overlapping PSA (Pseudomonas aeruginosa) isolates tested against a new antibiotic, in this case C / T (ceftolozane / tazobactam).

[0057] In block 22, method 10 may identify patient risk factors relating to selected pathogens and / or antibiotics or specific infection types determined. Depending on the embodiment, patient risk factors may include, for example, a risk score for a population of patients. Risk factors may enable identification or analysis by pathogen type or resistance type, or identification of pathogen types or resistance types based on risk factors. For example, method 10 may use risk factors to identify specific resistance or pathogen types (or mixed resistance or pathogen types) with specific (e.g., user-selected or pre-determined) risk factors. Furthermore, method 10 may generate one or more models (e.g., dynamic models) to identify specific mixed resistance or pathogen types and / or specific antibiotics to use against selected pathogens. Details of block 22 are described above in relation to parameter 5. The information obtained may relate to a specific geographical area or facility and to a specific period or duration for selected pathogens against selected antibiotics. Depending on the embodiment, the user also selects a specific geographical area or facility and / or a specific period as input to system 100. Depending on the embodiment, a specific geographical area or facility and / or a specific period is predetermined. The predetermined may be a fixed predetermined based on, for example, the user's location, facility, or parameters detectable by the system. The predetermined may be a dynamic predetermined based on one or more parameters detectable by the system. For example, if the user is a mobile clinic user, the system may identify a geographical area within a threshold distance (e.g., 50 miles (80 km) or 100 miles (160 km)) from the current location of the mobile device used by the mobile clinic user.

[0058] An example of a research paper is shown in Figure 1I. In one non-limiting embodiment, a physician may evaluate this research paper and related research papers to identify patient risk factors for specific infection types of the pathogen selected in block 12 (e.g., skin and skin tissue infections (SSSI), urinary tract infections (UTI), pneumonic bacteremia, CAP, HCAP, HAP / VAP). Using the research paper shown in Figure 1I, for example, a physician may evaluate anti-Pseudomonas β-lactams prescribed as empirical treatment in hospitalized patients with Pseudomonas aeruginosa (PSA) after indexing, based on the indexed PSA infection non-susceptible (NS) status. Examples of antibiotics include anti-Pseudomonas β-lactams, carbapenems (Carb), broad-spectrum cephalosporins (ESC2), and piperacillin / tazobactam (TZP).

[0059] In some embodiments, Method 10 generates customizable output for the user in block 24. In some embodiments, the output for the user is an interactive report or notification to provide the user with various information obtained by Method 10, as described, for example, in relation to Figure 1A and the parameters described above. The report generated by Method 10 may include, for example, a selected antibiotic (or an alternative antibiotic if Method 10 identifies a more effective alternative for use against a selected pathogen). In some embodiments, the report includes the obtained heatmap, report, and other relevant information. Thus, block 24 may generate output based on the output of various blocks and parameters related to the processing of Method 10 and described above.

[0060] Depending on the embodiment, the user may interact with Method 10 through a user interface. Thus, the user may have the option to select which steps of Method 10 to perform based on the input provided to the system 100 implementing Method 10. For example, if the user has determined that a particular antibiotic will be used in a treatment regimen, the user may choose to skip the identification of the new antibiotic. Example of a database system that provides dynamically updated parameters

[0061] Embodiments of the present disclosure may include a database system (also referred to herein as the “System”) for dynamically generating electronic notifications (also referred herein as “Notifications” or “Alerts”) for various healthcare professionals, for example, using one or more customized models, to incorporate data from remote, and possibly heterogeneous, database systems and to provide dynamically updated data related to any one or a combination of the parameters 1 to 5 above. A subset of data from heterogeneous database systems may be processed, merged, and further filtered to meet requirements and criteria selected by healthcare professionals. Furthermore, various filters, including geographical filters, facility type filters, treatment regimen filters, pathogen filters, resistance type filters, and / or infection type filters, may be applied to aggregate and / or analyze the merged subset of data into a dataset that can be used to dynamically generate electronic notifications without burdening the available processing capacity or memory storage, which may occur when datasets that are too fine-grained are used. Aggregating the merged subset of data may also help improve the level of accuracy, which may decrease when a large number of datasets are merged.

[0062] Embodiments of this disclosure may also enable systems and / or methods to perform the above-described processing, merging, filtering, aggregating and / or alert generation in a time-efficient manner, even when data is added to the database and / or individual stakeholder requirements (such as filters to be selected) may differ.

[0063] The system and methods may rely on data supply from multiple databases, where one or more of the databases contain data in different formats and / or data relating to different information and / or geographical areas. Dynamically generated and customized alerts may be generated based on various customized models and rules for processing the data and generating outputs based on that data. Data processing may include, for example, aggregating, filtering, merging, comparing, and / or refining data within the databases, and automatically generating new data files and / or databases. term

[0064] To facilitate understanding of the systems and methods described herein, some terms are defined below. The terms described below, and other terms used herein, should be interpreted broadly to include the information provided, their ordinary and customary meanings, and / or any other implied meanings of each term. Therefore, the following explanations are not limiting and are merely illustrative.

[0065] Datastore: Includes any computer-readable storage medium and / or device (or collection of data storage mediums and / or devices). Examples of datastores include, but are not limited to, optical discs (e.g., CD-ROMs and DVD-ROMs), magnetic discs (e.g., hard disks, floppy disks, etc.), and memory circuits (e.g., solid-state drives and random-access memory ("RAM")). Another example of a datastore is a hosted storage environment (commonly referred to as "cloud" storage) which includes a collection of physical data storage devices that are remotely accessible and can be quickly provisioned as needed.

[0066] Databases include, but are not limited to, any data structures (and / or combinations of data structures) for storing and / or organizing data, including, but not limited to, relational databases (e.g., Oracle databases and MySQL databases), non-relational databases (e.g., NoSQL databases), in-memory databases, spreadsheets, comma-separated value ("CSV") files, Extended Markup Language ("XML") files, TeXT ("TXT") files, flat files, spreadsheet files, and / or any other formats widely used for data storage, or proprietary formats. Databases are typically stored in one or more data stores. Therefore, each database referred to herein (e.g., in this description and / or in the drawings of this application) should be understood to be stored in one or more data stores.

[0067] Database record and / or record: Contains one or more related data items stored in the database. The one or more related database items that make up a record may be related within the database, for example, by common key values ​​and / or common index values.

[0068] Electronic notifications, notices, and / or alerts: including electronic notifications of the results of calculations, analyses, and / or other processing of records. Notifications may show the results of calculations, analyses, and / or other processing of records to users (e.g., healthcare professionals). Notifications may be electronically transmitted and may trigger the activation of one or more processes as described herein.

[0069] Users and / or healthcare professionals: This includes entities that provide input (e.g., requests) to the system and / or entities that use devices to receive event notifications, notices, or alerts (e.g., users who are interested in receiving notifications). Non-exclusive examples of users include physicians, nurses, pharmacists, medical staff, healthcare administrators, healthcare researchers, and regulatory bodies. Examples of operation of the dynamic system as described in this disclosure

[0070] Figure 2 shows an example of a block diagram or data flow diagram of a treatment regimen database system referred to as dynamic system 103 or system 103, according to one embodiment of the present disclosure. System 103 uses data records in various databases to dynamically generate electronic notifications, for example, treatment regimen effectiveness rates, antibiotic use and infection rates by geographical area and facility, resistance heatmaps, and other information related to parameters 1-5 described above. Depending on the implementation, one or more of the blocks in Figure 1A may be arbitrary, additional blocks may be added, and / or the blocks may be rearranged. As shown in the figure, system 103 is part of system 100, which is detailed with respect to Figure 5.

[0071] System 103 includes a first filter 112, filtered records 114, merged internal database records 116, a filter 118, a dynamic model 120, and generated notifications. The first filter 112 is configured to filter records in the first data store 104. Depending on the embodiment, the first data store 104 stores information about a patient population. The first filter 112 may include user-selected content (e.g., selected antibiotics and / or selected pathogens). The dynamic system 103 can identify several records in the first data store 104 that fit, match, or are based on the filter content, and can use the first filter 112 to filter calculations for a specific subset of the patient population. Database records in the first data store 104 may represent a patient and may include the patient's name, address (including city, county, state, country, and zip code), past medical history, past treatment regimens (including information on the effectiveness of past treatment regimens), current medical conditions including suspected or confirmed infections, known health problems or medical conditions, and currently prescribed treatment regimens. Depending on the embodiment, the first filter 112 includes instructions for applying or performing one or more specific filtering functions or calculations to database records stored in the first data store 104 by the system. The system 103 may query the first data store 104 for a specific set of data and perform calculations on that data (based on the first filter 112) to automatically generate a set of filtered records 114. Non-exclusive examples of such instructions and / or filters and / or calculations are described below. The system may determine that the first filter 112 includes an instruction to count the number of people who reside within a specific geographic area and have records in the first data store 104, such as a specified geographic area, a zip code, a zip code + 4 areas, a city, a county, a state, a set of five specific zip codes, or any other appropriate geographic area.

[0072] For example, the first filter 112 may be applied to records in the first data store 104 to generate or identify records in the first data store 104 that are related to the first filter 112 or remain after the application of the first filter 112. In one non-limiting embodiment, the first data store 104 contains medical records of patients who were hospitalized or treated at a particular medical facility (such as a particular hospital or outpatient facility), or patients who reside in a particular geographical area, such as a county or state. Continuing the description of this non-limiting embodiment, the first filter 112 may include one or more of the following: a particular infectious disease, a particular infectious pathogen, a particular strain of an infectious pathogen, a treatment regimen prescribed to one or more patients (including information on the type and dosage of medications, such as antibiotics), or a particular city within a state. By applying the first filter 112 to the records in the first data store 104, the dynamic system 103 generates a first set of filtered records 114 that include only the records from the first data store 104 that match the user selection parameters of the first filter 112. Thus, if the first data store 104 includes all patient records for a particular state and the first filter 112 includes a filter for methicillin-resistant Staphylococcus aureus (MRSA) infections, the resulting filtered records 114 will include only the records in the data store 104 for patients who are infected with or have been infected with MRSA in that particular state.

[0073] In some embodiments, the second data store 108 may include records relating to the effectiveness rate of treatment regimens against specific infectious diseases or causative pathogens. In some embodiments, the records may include details such as specific geographical regions, different infectious disease strains, different patient categories, and different treatment regimens.

[0074] The filtered record 114 described above includes records from the first data store 104 that satisfy the criteria of the first filter 112. In some embodiments, the dynamic system 103 combines the treatment regimen effectiveness data from the second data store 108 with the filtered record 114 to generate a combined or merged internal database record 116. Such a combination of records may include the filtered record 114 with further effectiveness information from the second data store 108. Thus, the records in the merged internal database record 116 may include details for each patient, including the patient's current infection and the current treatment regimen with added effectiveness information from the second data store 108 (and other information). The details for each patient may also include information about the patient's past infections and past treatment regimens used to treat those past infections. In a non-limiting embodiment, the established efficacy rate of TMP-SMX against MRSA is added to the patient record of a patient infected with MRSA who has been treated with trimethoprim sulfamethoxazole (TMP-SMX), using dynamically updated information based on real-world data aggregated over the most recent quarter. In embodiments of the present disclosure, this added information is specific to the geographical area in which the patient resides or was infected, and / or specific to the facility where the patient is receiving treatment.

[0075] In some embodiments, the merged internal database record 116 includes one or more (or all) of the items contained in the corresponding database record in the first data store 104, along with additional information from the second data store 108. The dynamic system 103 may dynamically add information from the second data store 108 to the filtered record 114 (for example, when new data or records are received in the first data store 104 or the second data store 108, or periodically, for example, daily, weekly, monthly, bimonthly, semi-annually, annually, every 28 days, or any other appropriate schedule). In some embodiments, the dynamic system 103 may filter and merge records from the first data store 104 and the second data store 108 when information is requested by a user of the dynamic system 103.

[0076] Storing such filtered records and merging them with efficacy information is advantageous because it speeds up subsequent processing by the dynamic system 103, such as dynamic generation of custom models and / or additional filtering or merging operations. For example, as will be discussed later, storing a subset of patient records associated with a treatment regimen or infection, such as patients infected with MRSA and treated with vancomycin intravenously, in real time or periodically, allows the system to analyze those records more quickly when a user request is received and merge them with other datasets organized at one or more levels. Indexing is one way to access data more quickly. Factors influencing the indexing process and the resources required for indexing include the number of records being indexed, the number of fields included in the index, and the size of the data stored in the fields included in the index. To expedite future record retrieval and analysis while using resource-efficient indexes, subsets of information can be indexed in detail.

[0077] Depending on the embodiment, one or more of the first data store 104 and the second data store 108 may be updated on a schedule of any kind, for example, daily, weekly, monthly, bimonthly, semi-annually, annually, every 28 days, or any other type. Depending on the embodiment, the first data store and / or the second data store 108 may be updated on demand or when a certain threshold of change is detected (for example, 2% of records have been updated, or 0.8% of a particular field of a record has been updated).

[0078] In some embodiments, the merged internal database records 116 are stored in a separate file from the first data store 104 and / or the second data store 108, while in other embodiments, the merged internal database records 116 are stored in either the first data store 104 or the second data store 108. In some embodiments, storing the merged internal database records 116 separately may have several advantages, such as when the accessed set of data is a smaller dataset compared to the complete set of records in the first data store 104 and / or the second data store 108, or, as another example, when the merged internal database records 116 are stored as a file or in a system that is more easily readable and accessible than the first data store 104 and / or the second data store 108. In some embodiments, the merged internal database records 116 are stored locally within the dynamic system 103, while in other embodiments, the merged internal database records 116 are stored remotely from the dynamic system 103, such as in an external database or a second data store. If it is separate from the second data store 108, the merged internal database record 116 can be processed by the dynamic system 103 without the need to communicate further with the first data store 104 or the second data store 108 to process the merged internal database record 116.

[0079] In the next step of this illustrative process, the dynamic system 103 may then apply a filter 118 to the merged internal database records 116. This may be done in real time or periodically, as described above. Depending on the embodiment, the filter 118 includes one or more criteria that are stored in or accessed by the dynamic system 103. The filter 118 can be used to focus insights on a particular treatment regimen, infection, geographical area, etc. Depending on the embodiment, a subset of the data generated by applying the filter 118 is stored in a separate database from the merged internal database records 116, while in other embodiments, the filtered subset of the data is stored in a temporary storage location such as RAM or buffer memory that is accessed for use in the dynamic model 120 detailed below.

[0080] In some embodiments, if filter 118 is applied, one or more criteria of filter 118 are based on user input. For example, a user may use a computing device to interface with the dynamic system 103 and request information on the effectiveness of a particular treatment regimen against a particular infectious disease or pathogen within a specific geographical area. It should be understood that in some cases, the particular infectious disease or pathogen may not yet be definitively identified, and insights may be provided to the user based on the patient's symptoms. In some embodiments, additional information, such as a date of interest, is provided by the user as a data parameter. For example, a user may give instructions to filter results outside of a six-month period prior to the current date to ensure that the information used for analysis and processing is timely and relevant.

[0081] In some embodiments, the dynamic system 103 may dynamically generate and apply a dynamic model 120 (e.g., as a custom model or custom modeling algorithm) that groups the filtered subset after applying a filter 118 to determine a predictive or likelihood estimate of an appropriate treatment regimen for treating the current infection. The dynamic system 103 may use the various forms of data described above to generate the dynamic model 120. Using the examples described above, the dynamic system 103 may obtain a filtered set of patient records for a specific infection or pathogen, a specific treatment regimen, and a specific geographical area in order to dynamically generate a dynamic model 120 that determines the treatment regimen with the best efficacy (higher efficacy than other candidate treatment regimens) for treating the current infection by optimizing the likelihood that the selected treatment regimen has the best (or sufficiently high) efficacy against the target infection over a given period, a given geographical area, etc. In some embodiments, the dynamic model 120 considers the different parameters 1-5 described above and generates a report that includes risk factors and / or risk scores to be output to the user. The dynamic model 120 can be dynamic in that the model itself is constantly updated by additional information that may affect the output generated by the dynamic model 120.

[0082] In some embodiments, the dynamic system 103 may generate and / or specify efficacy thresholds used in generating recommendations. For example, if a treatment regimen has an efficacy rate below a first threshold, that particular treatment regimen may not be recommended by the system 100. In one non-limiting embodiment, if the efficacy rate of a treatment regimen is below a first threshold of 90%, that particular treatment regimen may not be recommended by the system 100. Alternatively, or in addition to the above, if the efficacy rate is above a second threshold, a second (e.g., newer) treatment regimen may be recommended over the first (older or previously selected) treatment regimen, even if the first treatment regimen has an acceptable efficacy rate (e.g., above the first threshold). In one non-limiting embodiment, if the efficacy rate is greater than a second threshold of 80%, a second (e.g., newer) treatment regimen is recommended over the first (older or previously selected) treatment regimen, even if the efficacy rate of the first treatment regimen exceeds the first threshold of 90%. It should be understood that these first and second threshold examples are not limiting, and that embodiments of this disclosure can be adequately implemented using other acceptable first and second thresholds.

[0083] For example, a user might seek insights and contextual awareness regarding the optimal (most appropriate) treatment regimen for treating MRSA in a particular geographical area. The user may filter patient records in the first data store 104 (e.g., via a first filter 112 containing infectious MRSA) to generate filtered records 114 that include only patient records of patients exposed to MRSA (in the user's specific geographical area, the specific geographical area where the patient resides, the specific geographical area where the patient contracted the infection, the user's specific facility, or any combination thereof) and the corresponding treatment regimens used to treat MRSA in those cases. The dynamic system 103 generates merged internal database records 116 by applying effectiveness rates from the second data store 108 to the filtered records 114. The dynamic system 103 may then further filter the merged internal database records 116 (e.g., based on one or more of the following: geographical area, period of interest, etc.). Next, a subset of the resulting records may be used to generate a custom model used to identify the optimal (most appropriate) treatment regimen for treating the MRSA infection, based on the current patient's medical information, the records in the subset of records, and merged internal database records 116 or filtered records 114. As described above, embodiments of the present disclosure include a dynamic model 120 that takes into account patient-specific information, such as, but not limited to, past exposure to the same pathogen causing the particular patient's current infection, past infections of the particular patient that have been confirmed or are likely to have been caused by the same pathogen, and past resistance to treatment for the same infection of the particular patient (using the same or different treatment regimen that the user is currently considering for treating the current infection).

[0084] The dynamic modeling described herein (performed by dynamic model 120) can enable the updating of efficacy information for various treatment regimens, taking diagnosed infections into account, and the provision of alerts or notifications for recommended treatment regimens, without placing an excessive burden on the healthcare facility's computing system. For example, embodiments of the disclosure can avoid placing an excessive burden on the healthcare facility's computing system by focusing on parameters identified by the system (or users of the system) rather than irrelevant parameters and providing insights related to those parameters. For example, insights for a specific geographical area or a specific time frame can be generated without having to process data for other irrelevant geographical areas or time frames. As another example, embodiments of the disclosure can avoid placing an excessive burden on the healthcare facility's computing system by dynamically generating patient and efficacy information based on data that is updated in real time or near real time, thereby reducing the amount of memory required by the computing system. As described above, one or more of the first data store 104 and the second data store 108 can be updated frequently, such as daily, weekly, or monthly, or on any other appropriate schedule.

[0085] The dynamic system 103 can also dynamically or periodically (e.g., daily, weekly, monthly, bimonthly, quarterly, semi-annually, etc.) generate output files or notifications 122 and send notification alerts or notification packages. The generated notification packages or alerts may include digital and / or electronic messages. The notification package may include indicators that show the user's preferred treatment regimen for treating a patient's current infection. The notification package may include indicators that the user needs to access the dynamic system 103 to review records from various data stores and databases associated with the dynamic system 103. The notification may be sent to the user who provided the filter criteria and / or to any other recipients indicated by the user or notification package. The notification package may also be delivered by any appropriate mode. Using the above example, the dynamic system 103 may send a notification package containing information on the optimal treatment regimen for treating an infection in a given geographical area, based on effectiveness data acquired over a defined period.

[0086] In some embodiments, such notification alerts (also referred to herein as notification 122) may include notifications recommending against prescribing a particular treatment regimen, along with recommendations to prescribe alternative treatment regimens. The dynamic modeling described herein may enable the dynamic system 103 to generate updated efficacy rates by monitoring, aggregating, and analyzing patient records to identify factors that improve or decrease efficacy rates. The dynamic modeling may take into account various geographical factors, time periods, etc., to determine the updated efficacy rates.

[0087] In some embodiments, alerts and / or notifications are automatically sent to a device operated by the user associated with the corresponding notification. Alerts and / or notifications can be sent to a computing device 106, as described later with reference to Figures 3 and 5, for example, at the time the alert and / or notification is generated, or at some predetermined time after the generation of the alert and / or notification. Upon receipt by the computing device 106, the alert and / or notification can be displayed on the computing device 106 by launching an application on the computing device 106 (e.g., a browser, a mobile application, etc.). For example, upon receipt of an alert and / or notification, an application on the computing device 106, such as a messaging application (including, but not limited to, an SMS or MMS messaging application), a standalone application (e.g., the user's messaging application), or a browser, may be automatically launched to display the information contained in the alert and / or notification. If the computing device 106 is offline when the alert and / or notification is sent, the application may be automatically launched when the computing device 106 is online so that the alert and / or notification can be displayed. In another embodiment, the receipt of an alert and / or notification may redirect the user to a login page generated by system 100, which opens a browser and allows the user to log in to system 100 and view the alert and / or notification. Alternatively, the alert and / or notification may include a URL to a webpage (or other online information) associated with the alert and / or notification, such that when computing device 106 receives the alert, a browser (or other application) is automatically launched and the URL contained in the alert and / or notification is accessed over the internet.

[0088] In some embodiments, alerts and / or notifications may be automatically routed directly to an interactive user interface, where they may be viewed and / or evaluated by a user, such as a physician or administrator. In another embodiment, alerts and / or notifications may be automatically routed directly to a printer device, where they may be printed as reports for user viewing. In yet another embodiment, alerts and / or notifications may be automatically routed directly to an electronic work queue device so that the information from the notification can be automatically displayed to a user, and optionally the information from the notification can be used to automatically contact (e.g., dial a phone number) the relevant party indicated in the notification (e.g., a supervisor or hospital administrator). In yet another embodiment, alerts and / or notifications may be automatically routed as input to an external system (e.g., supplied to a pharmacy prescription management system, a hospital patient management system, or a health insurance customer relationship management system).

[0089] Depending on the embodiment, if the infection to which a treatment regimen is prescribed has a higher resistance than a given threshold (for example, if there is more than 50% resistance in a geographical area, thereby reducing the effectiveness rate of the treatment regimen to less than 50%), Notice 122 may indicate or recommend to a physician not to prescribe the treatment regimen initially selected by the physician. Alternatively, or in addition to this, if a different treatment regimen is more effective (i.e., has lower drug resistance) than the selected treatment regimen, Notice 122 may recommend to a physician that the more effective treatment regimen be prescribed. For example, if a different treatment regimen has a higher effectiveness rate than a second threshold (for example, if the effectiveness rate against the infection in that area or facility exceeds 70%), Notice 122 may recommend a different treatment regimen than the initially selected treatment regimen.

[0090] In various implementations, the first data store 104, the second data store 108, the filtered records 114, the merged internal database records 116, and / or any combination of these databases or other databases and / or data storage devices of the system may be combined and / or separated into additional databases, and / or a subset of records generated after the application of the filter 118 may be merged into one or more common databases or separated into different databases.

[0091] Figure 3 is an illustrative communication flow diagram 300 illustrating communication between various components of the system 100 in Figure 2 for providing electronic notifications regarding database records according to one embodiment of the present disclosure. The communication flow diagram 300 shows several components of the system 100. The communication flow of this non-limiting embodiment involves a computing device 106, data stores 104 and 108, and a dynamic system 103. Although not shown, each of the computing device 106, data stores 104 and 108, and dynamic system 103 can be connected via a network, such as the network 110 in Figure 5, which is detailed below. Thus, each of the illustrated components can be configured to communicate, for example, via a network connection.

[0092] In one embodiment, computing device 106 is configured to receive user input 302. The computing device 106 that receives user input 302 may be computing device 102 described later with reference to Figure 5. Depending on the embodiment, user input 302 may be one or more of selected antibiotics and selected pathogens. Furthermore, user input 302 may include geographical constraints and / or periods or durations of interest. All user input 302 may be provided at once or at different times or intervals. Similarly, data stores 104 and 108 may be configured to receive or retrieve various types of information, including patient information and / or health records, pathogen information (including resistance information, susceptibility information, etc.), antibiotic information (including resistance information, susceptibility information, test information, etc.), heatmaps, and drug resistance research papers. Depending on the embodiment, patient information and health records are stored in the first data store 104, and the remaining information is stored in the second data store 108.

[0093] Based on the received user input 302, the dynamic system 103 may generate a user request 304 to the dynamic system 103. The user request 304 to the dynamic system 103 may include one or more of the following: a selected antibiotic, a selected pathogen, a specific geographical area, and a specific period or time frame. When the computing device 102 receives the user input 302, the computing device 102 may generate a user request 304 based on the received user input 302.

[0094] The dynamic system 103 receives a user request 304 and generates one or more requests seeking relevant insights based on the user request 304. For example, a request for relevant insights may include requests for insights on a specific patient, a specific facility, and / or a specific geographic. In addition to or instead of this, the insight request 306 may include requests for insights on selected antibiotics and / or selected pathogens over a specific period or time frame.

[0095] Based on the received insight request 306, data stores 104 and 108 may retrieve and / or access data. For example, the first and second data stores 104 and 108 may retrieve or access patient records, pathogen information, antibiotic information, heatmaps, drug resistance research papers, information, and evidence, etc. In 308, data stores 104 and 108 may provide the retrieved or accessed data to the dynamic system 103. Depending on the embodiment, the relevant information provided from data stores 104 and 108 to the dynamic system 103 may include patient records or information from patient records, pathogen information (e.g., drug resistance of pathogens, and similar information), details about selected antibiotics, heatmaps (e.g., heatmaps pre-generated by the dynamic system 103 or system 100), and other relevant information. The dynamic system 103 may use the information from user request 304 and the relevant information 308 to generate and / or update the dynamic model 310. The dynamic model 310 uses the user request 304 and related information 308 to generate an analysis or additional information regarding the best antibiotic and / or treatment regimen for the treatment of the selected pathogen. Depending on the embodiment, the best antibiotic may be the selected antibiotic or another antibiotic. The dynamic model 310 may analyze the received request and related information 308 to identify information regarding the effectiveness of the selected antibiotic against the selected pathogen, which may include drug resistance information.

[0096] After the dynamic model is generated or updated in 310, the dynamic system 103 may provide a report to the user in 312. Depending on the embodiment, the report may include one or more pieces of information used by the dynamic system 103 to generate the recommended antibiotic and / or treatment regimen, and relevant risk factors (as detailed herein). Report 312 may also include heatmaps, pathogen information, patient information, and other information from data stores 104 and / or 108 and analyses generated by the dynamic system 103 related to the recommended antibiotic and / or treatment regimen and corresponding selections. Report 312 may include all of this information so that the user can view any information related to the recommendation.

[0097] Figure 4 shows a figure 400 of overlapping levels of insights available to a user of the system 100 of Figure 2, according to one embodiment of the present disclosure. For example, figure 400 shows multiple levels of insights that the system 100 may provide. The first level, patient-specific insight level 402, may include insights specific to a particular patient. Thus, based on various inputs (as shown, for example, in Figure 4), the system 100 may identify one or more specific patient insights based on the inputs and deliver those insights to the user. In one non-limiting embodiment, the system 100 may identify whether a particular patient under examination or consideration is currently infected with or has previously been infected with a particular pathogen. In another non-limiting embodiment, the system 100 may identify whether a particular patient under examination or consideration has health risks associated with a particular treatment regimen. In yet another non-limiting embodiment, the system 100 may identify whether a particular patient has previously been treated with or is currently being treated with a particular treatment regimen. As detailed above, System 100 has the advantage of being able to communicate these and other insights to the user within the optimal time frame within the patient care timeline.

[0098] The second level, corresponding to the next largest circle in Figure 400, represents facility-specific insights 404, which represent insights for a specific facility. Facility-specific insights may include insights for patients being treated at that particular facility. For example, system 100 can identify patients being tested, treated, or having exposure determined for a specific pathogen. Thus, facility-specific insights 404 for that particular facility essentially include patient-specific insights 402 for patients being treated at that particular facility.

[0099] The third level, corresponding to the next largest circle in Figure 400, represents geo-specific insights 406, which represent insights for a specific geographical area. Geographic-specific insights may include facility-specific insights for facilities located within that specific geographical area. For example, system 100 can identify all patients being tested, treated, or having exposure determined for a particular pathogen, which would include any particular patient at any particular facility within that specific geographical area. Thus, geo-specific insights 406 for that specific geographical area essentially include facility-specific insights 404 for any facility within that specific geographical area and patient-specific insights 402 for patients being treated at facilities within that specific geographical area. As described above, these insights may be based on real-time or real-time data aggregated over a specific period, including a period ending on the date of the user's insight request. Thus, embodiments of the systems and methods of this disclosure can provide dynamic real-time insights and contextual awareness to healthcare staff at three core levels: geographical area-specific insights and contextual awareness, facility-specific insights and contextual awareness, and patient-specific insights and contextual awareness. Other implementation examples of dynamic systems as disclosed herein

[0100] Figures 5 and 6 show other non-limiting embodiments of a dynamic system 103 configured to communicate with a data store in system 100, according to the implementation of the present disclosure. System Overview

[0101] Figure 5 shows a block diagram of one possible configuration of the system of Figure 2, according to one embodiment of the present disclosure, which can dynamically generate and apply models for tracking pharmacovigilance and track situations to identify possible drug resistance conditions based on information from one or more databases. The system 100 can enable a user to dynamically generate models for processing records and data obtained from various databases, and the models can generate outputs (e.g., reports and notifications) from the data based on dynamically changing requirements from the user.

[0102] The system 100 in Figure 5 includes a dynamic system 103 that interfaces with a computing device 102, a first data store 104, a second data store 108, other computing devices 106, and a network 110. Furthermore, a communication link is shown enabling communication between components of the system 100 via the network 110. The computing device 102 is shown as being communicably coupled to the dynamic system 103 in a local manner (for example, via a local communication link), but the dynamic system 103 may be incorporated into the computing device 102, or vice versa, or may be accessible via the network 110. Also, in some embodiments, one or more of the data stores described herein may be combined into a single data store that is either locally with the computing device 102 or remotely from the computing device 102. In some embodiments, two or more of the above components may be integrated. In some embodiments, one or more of the components may be excluded from the communication system 100, or one or more components not shown in Figure 5 may be included in the communication system 100. The communication system 100 can be used to implement the systems and methods described herein.

[0103] In some embodiments, network 110 may include any wired or wireless communication network capable of communicating data and / or information between multiple electronic devices and / or computing devices. The wireless or wired communication network may employ widely used networking protocols to interconnect nearby devices or systems. The various embodiments described herein are applicable to any communication standard, such as the wireless 802.11 protocol. Computing device 102 may include any computing device configured to send and receive data and information over network 110 for healthcare personnel. Healthcare personnel may be individuals (e.g., individual doctors or nurses) or organizations such as, but not limited to, corporations, non-profit organizations, educational institutions, or medical facilities. In some embodiments, computing device 102 may include or have access to one or more databases (e.g., a first data store 104 and a second data store 108) containing various records and information that can be used to generate customized output. In some embodiments, computing device 102 may be accessible locally and remotely over network 110. The computing device 102 may generate customized outputs based on events associated with the patient (e.g., past infections, previously prescribed treatment regimens, health events, and health risks). These events (and corresponding information) may be used to dynamically generate models of which treatment regimens should be prescribed to ensure maximum efficacy against a particular infection, a particular pathogen, or a particular drug-resistant strain of the pathogen.

[0104] The first data store 104 may include one or more databases or data stores and may store data relating to either historical or current events. Using an exemplary use case, the first data store 104 may include patient records, including patient name, contact information, address information, medical information, current and past infections, past treatment regimens prescribed, geographical areas where the patient was infected (or potentially infected based on residence or travel information), and the dates on which the patient was ill. Depending on the embodiment, the first data store 104 may provide patient data within a specific geographical area defined by the user via one or more computing devices 106 or computing device 102. For example, the first data store 104 may provide details about patients within a geographical area defined by state, county, zip code, or other geographical identifier.

[0105] Computing devices 102, 106 may include any computing devices configured to send and receive data and information over the network 110. In some embodiments, computing device 106 may be configured to analyze the transmitted and received data and information and / or to perform one or more actions based on the analysis performed and / or the transmitted and received data and information. In some embodiments, one or more computing devices 102, 106 may include, but are not limited to, personal computers, server computers, handheld or laptop devices, multiprocessor systems, microprocessor-based systems, microcontrollers or microcontroller-based systems, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and smartphones, as well as mobile or stationary computing devices. Thus, users described herein (e.g., physicians, hospital administrators, etc.) may use any of these types of devices to access reports generated based on their respective requests or inquiries. In some embodiments, computing devices 102, 106 may be integrated into a single terminal or device. In some embodiments, computing device 102 may be remote from the patient, user, physician, hospital, etc. Computing device 106 may be used by a user to access network 110 and remotely access computing device 102. For example, computing device 102 may be located in a medical facility and accessible by computing device 106.

[0106] The second data store 108 may include one or more databases or data stores, for example, that store data on the effectiveness rates of treatment regimens against specific infectious diseases or pathogens in different geographical regions and different predefined timeframes. In the exemplary use case, as described above, the second data store 108 includes a database of effectiveness rates for infectious diseases treated with treatment regimens corresponding to infectious diseases and / or treatment regimens of patients for whom records exist in the first data store 104.

[0107] The dynamic system 103 may process data from the first data store 104 and the second data store 108, and may generate one or more models based on requests or inputs provided by users via computing devices 106 and 102. The dynamic system 103 may dynamically generate one or more models that are applied to data obtained from the first data store 104, the second data store 108, or from one or more users (via one or more computing devices 106). In some embodiments, the models may be dynamically generated by the dynamic system 103 as the inputs and data change or according to a predetermined schedule. For example, the dynamic system 103 may generate a model that changes in real time based on inputs received from a user (e.g., the type of infection to be diagnosed, the type of treatment regimen to be prescribed, the area affected by the infection, and the relevant time frame). In some embodiments, the generated model itself may be dynamically applied to the inputs and data. For example, the model generated by the dynamic system 103 may create various metrics and data points based on data obtained from the first and second data stores 104 and 108, respectively, and data obtained from the user themselves (e.g., user-selected filters and geographical areas). In some cases, the model may dynamically apply one or more rules to ensure that the generated output does not violate any predetermined requirements or standards such as data mining, storage, etc. (e.g., to ensure that medical information compliance elements are met). In some embodiments, model creation may include creating a set of heuristic rules, filters, and / or electronic data screens to determine and / or identify and / or predict which pharmaceuticals will be considered more likely to meet certain criteria based on current and / or historical data. In some embodiments, the dynamic system 103 may automatically adjust the model to fit a pre-selected level of accuracy and / or efficiency.

[0108] Depending on the embodiment, the dynamic system 103 may be adaptable to constantly changing data from the first data store 104, the second data store 108, or from users. For example, input received from users (e.g., via the user interface module 214 or I / O interface and device 204 detailed below) may differ from user to user. Using the exemplary use cases, one user (e.g., a first physician) may be interested in the efficacy rate of MRSA-infected patients treated with TMP-SMX in a first set of zip codes, another user (e.g., a second physician) may be interested in the efficacy rate of Streptococcus pneumoniae-infected patients treated with penicillin in a first set of zip codes, and a third user (e.g., a third physician) may be interested in the efficacy rate of a third infection treated with a third drug. Thus, the data retrieved from the first and second data stores 104 and 108 using filter criteria from these users is likely to be constantly changing. Therefore, processing and / or model generation will vary per user and / or per combination of data of interest. Furthermore, the data retrieved from the first and second data stores 104 and 108 is likely to change over time as records in the data stores are updated, replaced, and / or deleted. In the exemplary use case, different users may request different time periods, different patient parameters, different infections, different treatment regimens, etc., so that patient and medical records are constantly being updated. Therefore, the dynamic system 103 may dynamically generate models to deal with constantly changing data and requests.

[0109] As detailed herein, based on user requests, the data retrieved from the first and second data stores 104 and 108, respectively, may be filtered to exclude unwanted records. For example, in the exemplary use case, records may be filtered to exclude infections, dates, and / or treatment regimens that are not of interest.

[0110] In various embodiments, large amounts of data are automatically and dynamically calculated interactively in response to user input, and the calculated data is efficiently and concisely presented to the user by the system. Therefore, depending on the embodiment, the data processing and generation of the user interface described herein is more efficient than conventional data processing and user interface generation in which data and models are not dynamically updated in response to interactive input and are not presented to the user concisely and efficiently.

[0111] Furthermore, as described herein, the system can be configured and / or designed to generate output data and / or information that can be used to render various interactive user interfaces or reports as described herein. The output data can be used by system 100 and / or another computer system, device and / or software program (e.g., a browser program) to render the interactive user interface or report. The interactive user interface or report can be displayed, for example, on an electronic display (including, for example, a touch-enabled display).

[0112] The various embodiments of interactive dynamic data processing and output generation described herein are the result of extensive research, development, improvement, iteration, and testing. The result of this significant development is the modeling and output generation described herein, which can deliver greater efficiency and advantages over conventional systems. Interactive dynamic modeling, user interfaces, and output generation include improved human-computer and computer-computer interaction, which can lead to reduced workload and / or improved predictive analytics for the user. For example, output generation via the interactive user interface described herein can provide an optimized display of time-varying report-related information, enabling users to access, navigate, evaluate, and process such information more quickly than with conventional systems.

[0113] Depending on the embodiment, the output data or report may be presented in a graphical representation, such as visual representations like charts, spreadsheets, and graphs, where appropriate, to enable the user to efficiently review large amounts of data and leverage the particularly high human pattern recognition abilities related to visual stimuli. Depending on the embodiment, the system may present total quantities such as sums, totals, and averages. The system may also use this information to interpolate or extrapolate, for example, predict future developments.

[0114] Furthermore, the models, data processing, and interactive dynamic user interfaces described herein are made possible by efficient data processing, modeling, interaction between user interfaces, and innovations in the underlying systems and components. For example, this specification discloses improved methods for receiving user inputs, transforming those inputs and distributing them to various system components, automatically and dynamically executing complex processes in response to input distribution, automatic data acquisition, automatic interaction between various components and processes of the system, and automatic and dynamic report generation and user interface updates.

[0115] The various embodiments of this disclosure bring improvements to various technologies and technical fields. For example, as mentioned above, existing data storage and processing technologies (including, for example, memory databases) have limitations in various respects (e.g., manual data review is slow, costly, lacks detail, and the data volume is too large), and the various embodiments of this disclosure bring significant improvements to such technologies. Furthermore, the various embodiments of this disclosure are closely tied to computer technology. Specifically, the various embodiments rely on detecting user input via a graphical user interface, acquiring data based on that input, modeling data for generating dynamic output based on that user input, automatically processing related electronic data, and presenting output information via an interactive graphical user interface or report. Such and other features (e.g., processing and analyzing large amounts of electronic data) are closely tied to computer technology, enabled by computer technology, and would not exist without it. For example, the interaction with data sources and display data, described later with reference to the various embodiments, cannot be reasonably performed by humans alone without the computer technology on which their implementations are based. Furthermore, computer technology implementations of various embodiments of this disclosure enable many of the advantages described herein, including more efficient interaction with and presentation of various types of electronic data. Examples of dynamic systems

[0116] Figure 6 is a block diagram corresponding to one aspect of the hardware and / or software components of an exemplary embodiment of the dynamic system 103 and / or system 100 of Figure 5. As will be described below with reference to block diagram 200, the hardware and / or software components can be included in any of the devices of system 100 (e.g., computing device 102, computing device 106, or dynamic system 103). These various components shown can be used to implement the systems and methods described herein.

[0117] Depending on the embodiment, certain modules described below, such as the modeling module 215, the user interface module 214, or the reporting module 216 included in the dynamic system 103, may be included in, run on, or distributed across different and / or multiple devices of the system 100. For example, certain user interface functions described herein may be run by the user interface module 214 on various devices, such as the computing device 102 and / or one or more computing devices 106.

[0118] Depending on the embodiment, the various modules described herein can be implemented either in hardware or software. In one embodiment, the various software modules included in the dynamic system 103 can be stored in components of the dynamic system 103 itself (e.g., local memory 206 or mass storage device 210) or in a computer-readable storage medium or other component separate from the dynamic system 103, communicating with the dynamic system 103 via a network 110 or other suitable means.

[0119] The dynamic system 103 may include, for example, an IBM, Macintosh, or Linux / Unix-compatible computer, or a server, workstation, or mobile computing device running on any corresponding operating system. Depending on the embodiment, the dynamic system 103 interfaces with a smartphone, personal digital assistant, kiosk, tablet, smartwatch, car console, electronic assistant, media player, or similar electronic computing device. Depending on the embodiment, the dynamic system 103 may include a plurality of these devices. Depending on the embodiment, the dynamic system 103 includes one or more central processing units ("CPU" or processors) 202, I / O interfaces and devices 204, memory 206, modeling module 215, mass storage device 210, multimedia device 212, user interface module 214, reporting module 216, and bus 218.

[0120] The CPU 202 can control the operation of the dynamic system 103. The CPU 202 may also be referred to as a processor. The processor 202 may include or be a component of a processing system implemented using one or more processors. One or more processors may be implemented using any combination of general-purpose microprocessors, microcontrollers, digital signal processors ("DSPs"), field-programmable gate arrays ("FPGAs"), programmable logic devices ("PLDs"), controllers, state machines, gate logic, individual hardware components, dedicated hardware finite state machines, or any other suitable entities capable of performing computations or other operations on information.

[0121] The I / O interface 204 may include a keypad, microphone, touchpad, speaker, and / or display, or any other commonly available input / output ("I / O") devices and interfaces. The I / O interface 204 may include any elements or components that communicate information to and / or receive input from a user of the dynamic system 103 (e.g., a requesting physician, nurse, hospital administrator, researcher, or other entity). In one embodiment, the I / O interface 204 includes one or more display devices, such as monitors, that enable the visual presentation of data to a consumer. More specifically, the display devices may provide, for example, a GUI, application software data, a website, a web application, and a multimedia presentation.

[0122] Depending on the embodiment, the I / O interface 204 may provide a communication interface with various external devices. For example, the dynamic system 103 is electronically coupled to a network 110 (Figure 5), which includes one or more of a LAN, WAN, and / or the Internet. Therefore, the I / O interface 204 includes an interface that enables communication with the network 110, for example, via a wired communication port, a wireless communication port, or a combination thereof. The network 110 may enable various computing devices and / or other electronic devices to communicate with each other via wired or wireless communication links.

[0123] Memory 206, which includes either or both read-only memory (ROM) and / or random access memory ("RAM"), can provide instructions and data to the processor 202. For example, data received via inputs received by one or more components of the dynamic system 103 may be stored in memory 206. Part of memory 206 may also include non-volatile random access memory ("NVRAM"). Typically, the processor 202 performs logical and arithmetic operations based on program instructions stored in memory 206. Instructions in memory 206 may be executable to perform the methods described herein. Depending on the embodiment, memory 206 may be configured as a database and may store information received via the user interface module 214 or I / O interface and device 204.

[0124] The dynamic system 103 may also include a mass storage device 210 for storing software or information (e.g., a generated model or acquired data on which a model is applied). Software should be broadly interpreted to mean any kind of instruction, whether it is called software, firmware, middleware, microcode, hardware description language or any other name. Instructions may include code (e.g., source code format, binary code format, executable code format or any other suitable code format). When executed by one or more processors, instructions cause the processing system to perform various functions described herein. Thus, the dynamic system 103 may include, for example, hardware, firmware and software, or any combination thereof. The mass storage device 210 may include a hard drive, diskette, solid-state drive, or optical media storage device. Depending on the embodiment, the mass storage device 210 may be structured so that the stored data is easily manipulated and parsed.

[0125] As shown in Figure 6, the dynamic system 103 includes a modeling module 215. As described herein, the modeling module 215 dynamically generates one or more models for processing data obtained from a data store or user. In some embodiments, the modeling module 215 may apply the generated models to the data. In some embodiments, one or more models may be stored in a mass storage device 210 or memory 206. In some embodiments, the modeling module 215 may be stored in the mass storage device 210 or memory 206 as executable software code executed by the processor 202. This module or other modules in the dynamic system 103 may include components such as hardware components and / or software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. In the embodiment shown in Figure 6, the dynamic system 103 is configured to execute the modeling module 215 to perform various methods and / or processes described herein.

[0126] In some embodiments, the reporting module 216 may be configured to generate reports, notifications, or outputs as referred to and detailed herein. In some embodiments, the reporting module 216 may use information received from the dynamic system 103, the data store and / or computing device 102 in Figure 5, or data obtained from users of computing device 106 or computing device 102 to generate reports, notifications, or outputs for a particular physician, nurse, medical administrator, medical researcher, or other healthcare professional. For example, the dynamic system 103 may receive information provided by a physician, nurse, medical administrator, medical researcher, or other healthcare professional via the network 110 that the dynamic system 103 uses to retrieve information from the data store, and generate a model for processing that information. In some embodiments, the generated reports, notifications, or outputs may include a data file containing patient medical information related to a recommended treatment regimen to be used to treat an entered infection in a particular patient. In some embodiments, the reporting module 216 may include information received from a user in the generated reports, notifications, or outputs. Depending on the embodiment, the reporting module 216 or processor 202 may generate the notification 122 shown in Figure 2.

[0127] The dynamic system 103 also includes a user interface module 214. Depending on the embodiment, the user interface module 214 may be stored in a mass storage device 210 as executable software code executed by the processor 202. In the embodiment shown in Figure 6, the dynamic system 103 may be configured to execute the user interface module 214 to perform various methods and / or processes as described herein.

[0128] The user interface module 214 may be configured to generate and / or operate various types of user interfaces. In some embodiments, the user interface module 214 creates pages, applications, or displays to be shown in a web browser or computer / mobile application. In some embodiments, the user interface module 214 may provide applications or similar modules to be downloaded and operated on computing devices 102 and / or computing devices 106, through which the user can interface with the dynamic system 103 to obtain desired reports or outputs. In some embodiments, the pages or displays may be device type specific, such as a mobile device or a desktop web browser, to maximize usability for a particular device. In some embodiments, the user interface module 214 may also interact with customer-side applications such as a mobile phone application, a standalone desktop application, or a user communication account (e.g., email or SMS messaging) to provide data necessary to display medical or infectious disease notifications.

[0129] For example, as described herein, the dynamic system 103 may be accessible via a website to specific physicians, nurses, healthcare administrators, medical researchers, or other healthcare professionals. Depending on the embodiment, users may choose to receive or not receive any reports or outputs.

[0130] After the dynamic system 103 receives user input (e.g., identified infection, data time frame of interest, geographical area, treatment regimen of interest), the user may view the received information via the I / O interface and device 204 and / or the user interface module 214. After the dynamic system 103 receives information from the data store (e.g., via the I / O interface and device 204 or via the user interface module 214), the processor 202 or the modeling module 215 may store the received input and information in the memory 206 and / or the mass storage device 210. Depending on the embodiment, the information received from the data store may be analyzed and / or manipulated (e.g., filtered or similar processing) by the processor 202 of the dynamic system 103.

[0131] Depending on the embodiment, the processor 202 or the modeling module 215 may generate the dynamic model 120 described above with reference to Figure 2.

[0132] Various components of the dynamic system 103 can be coupled to one another by the bus system 218. The bus system 218 may include a data bus and, in addition to the data bus, a power bus, a control signal bus, a status signal bus, etc. In different embodiments, the bus can be implemented using, for example, a Peripheral Component Interconnect ("PCI"), Microchannel, Small Computer System Interface ("SCSI"), Industry Standard Architecture ("ISA"), and Extended ISA ("EISA") architecture. Furthermore, the functions provided by the components and modules of the dynamic system 103 may be combined as fewer components and modules than those shown in Figure 6, or they may be further separated as additional components and modules. Use Cases - Systems and Methods Using Dynamically Updated Infectious Disease Data

[0133] As briefly described above, System 100 is usable in various environments to perform database updates and dynamically generate custom models. In one non-limiting embodiment as described above and herein, System 100 can be used to process infectious disease and treatment regimen data. Healthcare professionals involved in patient care (e.g., physicians, pharmacists, nurses, healthcare administrators, and medical researchers) are constantly working to maintain the latest and best practices. In some cases, this includes maintaining awareness of drug efficacy against infectious diseases and diseases, and tracking infectious diseases and diseases within geographical areas of interest. Medicines are used to treat various causes of infectious diseases, illnesses, and diseases, and these causes may develop resistance to those medicines. For example, as antibiotics are used to treat many bacterial infections, drug-resistant bacteria are becoming more common worldwide. In some embodiments, such drug resistance may be geographically specific. For example, different geographical areas may be exposed to different pathogens or prescribe different medicines for the treatment of infectious diseases and other illnesses. Therefore, pathogens with varying levels of drug resistance may exist in different geographical areas. Differences in resistance affect the effectiveness or efficacy of treatment regimens prescribed to treat infectious diseases. Each medication may have region-specific, facility-specific, and patient-specific efficacy rates for each infection in which it is prescribed. For example, penicillin may have a higher efficacy rate against some diseases than against other bacterial infections. Therefore, medications may have different efficacy rates against different diseases or illnesses (whether the disease or illness is viral, bacterial, or fungal, for example). Similarly, different strains of penicillin may have different efficacy rates against different penicillin-resistant bacterial infections.

[0134] In some cases, a patient in a healthcare facility for diagnosis and / or treatment may have been exposed to an infectious pathogen in a different geographical area than the healthcare facility treating the patient, or in a different healthcare facility within the same geographical area as the current healthcare facility. For example, a patient may be infected while traveling, but only begin to show symptoms or develop the illness after returning from their trip. Another example is a patient who moves from their home area where they were first infected to a healthcare facility in a more populated area where they are diagnosed with and / or treated for the illness. Embodiments of this disclosure enable healthcare professionals currently treating such patients (or those interested in disease tendencies associated with such patients) to consider infectious disease, pharmaceutical, and efficacy information for a different geographical area than the geographical area in which their healthcare facility is located or is generally exposed. In some embodiments, different patients with the same infectious disease may visit different healthcare facilities for treatment, and therefore no single healthcare facility will have all the data associated with any of the infectious diseases and / or corresponding treatments in a given geographical area. In some embodiments of this disclosure, a healthcare facility may store in a patient record details of an infection associated with a patient, the treatment regimen used to treat that infection, the corresponding outcome of that treatment, and the relative date of the infection. Thus, a patient's healthcare record, for example, a healthcare record stored in the first data store 104, may contain details useful for updating information on the effectiveness of a drug for a particular disease in the same healthcare facility and other healthcare facilities.

[0135] In some embodiments, physicians, pharmacists, nurses, healthcare administrators, and medical researchers associated with a healthcare facility can conduct efficacy rate surveys to maintain quality control and improve contextual awareness of prescribing trends. However, such attempts can be time-consuming and generally difficult to perform manually, as constraints and system incompatibilities can make accessing patient records from different healthcare facilities cumbersome, time-consuming, inefficient, and costly. Such constraints and system incompatibilities make it virtually impossible to analyze resistance and antibiotic use trends using real-time data. Furthermore, aggregating enough information to accurately update drug efficacy rates against infectious diseases can require a considerable amount of data points, time, and resources (e.g., time-consuming data processing and computation). Moreover, the results of such attempts may be unreliable with respect to accurate drug efficacy updates and / or uniform aggregation of information from multiple healthcare facilities. Embodiments of this disclosure address these shortcomings of conventional systems and methods by dynamically responding to customized user inputs with real-time insights and contextual awareness gathered from large datasets of real-world data collected over a timeframe based on user requests.

[0136] In some embodiments, even if patient records containing details of a specific patient, disease, and / or medication are available, this information is stored in isolated, access-restricted medical records where it is not possible to aggregate and analyze some useful information from it along with other details to generate up-to-date information (e.g., due to regulatory and system incompatibilities). Some patient records may not contain information on whether the patient has fully recovered from an infection based on the prescribed treatment regimen, or may not contain appropriate details about the diagnosed infection or the prescribed treatment regimen. Consequently, healthcare professionals of general interest in such records may not be able to use information from patient records and / or determine and / or update such effectiveness rates. Furthermore, such parties may not be able to identify the optimal treatment regimen for treating an infection based on a particular patient's record, or such parties may not be aware that they have selected a treatment regimen that is less optimal than alternative treatment regimens.

[0137] Embodiments of this disclosure address these shortcomings by using dynamically updated data records and user-specific filters to generate insights based on aggregated information across geographical areas or facilities, where this information is aggregated over the most recent period, such as several quarters, months, weeks, or days prior to the user's information request. Use Cases - Systems and Methods Using Risk Scores

[0138] Embodiments of System 100 as disclosed herein generate a risk score for a specific patient and generate heatmaps (and similar data displays) and timely insights regarding changes in infectious diseases, drug efficacy rates, geographical distribution of infectious diseases, drug efficacy rates, and other variables.

[0139] The dynamic system 103 uses current patient information or records (hereinafter, current patient records) in combination with patient records from a first data store 104 and efficacy rate information from a second data store 108 to generate a risk score. The risk score may indicate the risk that the patient will be diagnosed with a particular infection, the risk that the diagnosed infection will be caused by a drug-resistant pathogen, the risk that the current patient will be resistant to treatment for a particular pathogen using a particular medicine, and / or the risk that the diagnosed infection will respond to or not respond to a particular medicine. For example, the current patient information or records may indicate specific symptoms (and test results, if available). The dynamic system 103 of this disclosure may determine the likelihood that the current patient has a particular infection based on a comparison of the current patient's symptoms and test results with known symptoms and test results of the infection, and with infections present in the same geographical area as the current patient. The dynamic system 103 may also determine a risk score representing the likelihood that the current patient's infection is resistant to a particular medicine or class of medicines. For example, the dynamic system 103 may use a dynamic model to determine the risk score of a current patient being infected with a drug-resistant strain of the infection. A higher risk score may indicate a higher likelihood that the current patient is infected with a drug-resistant strain. In some embodiments, a higher risk score may, in addition to or instead of this, indicate the likelihood that a particular treatment regimen will be successful in treating the infection based on a record of similar successful treatment regimens in or near the same geographic area of ​​interest.

[0140] Depending on the embodiment, System 100 identifies risk scores for individual patients, specific demographic segments of patients, specific geographical regions, and other populations of patients. Depending on the embodiment, System 100 may incorporate past diagnoses of patients (or corresponding patient populations), details of healthcare facilities or groups associated with those diagnoses, etc. Based on an analysis of the current patient's past diagnoses, response to medications, and current symptoms and diagnoses, System 100 may determine a risk score representing the likelihood that the current patient will be resistant to treatment with a particular drug.

[0141] Depending on the embodiment, System 100 may use a scoring system or determined risk scores to identify the risk of failure of a treatment regimen or drug therapy. For example, if a drug prescribed to treat a specific infection has a high risk score for drug resistance (meaning the infection is likely to be resistant to treatment using the prescribed drug), System 100 may identify a higher risk of failure. For example, a scoring system may aggregate risk scores from infections resistant to treatment, risk scores for whether the current patient is resistant to treatment or has a poor response to a particular drug, and the risk that the current patient is infected with a drug-resistant pathogen. Embodiments of this disclosure can generate and notify healthcare professionals of these risk scores at critical points in patient care, i.e., when healthcare professionals first evaluate and consider treatment regimens based on the symptoms the patient is exhibiting, and possibly even before a specific infection is diagnosed.

[0142] Embodiments of this disclosure also provide useful insights and contextual awareness that can lead to improved appropriate use of diagnostic testing resources. Some infections are difficult, time-consuming, and / or expensive to test for. Furthermore, drug resistance testing may not cover all relevant, available, or appropriate pharmacovigilants, and therefore some drug-resistant infections may not be addressed by a general test panel. Moreover, even when some degree of drug resistance is known or expected for a particular infection, it may not be possible to test various dosages of a pharmacovigilant in relation to drug-resistant infections. For example, even if a particular strain of MRSA is known to be resistant to a particular dosage level of a particular pharmacovigilant, users may not know other dosages of that pharmacovigilant that are effective against that strain of MRSA, or dosages that are ineffective or inappropriate for treating that strain of MRSA. Based on all the records in the first data store 104 and the second data store 108, the dynamic system 103 and / or system 100 of the present disclosure can determine and recommend specific medications and / or dosages to be prescribed based on patient information in the first data store 104 and efficacy information in the second data store 108, eliminating the need for healthcare professionals to order diagnostic tests to determine the specific pathogens causing the patient's infection. In this way, embodiments of the present disclosure improve the appropriate use of diagnostic testing resources, which are often inadequate and costly.

[0143] Embodiments of the dynamic systems 103 and 100 of this disclosure can identify when a physician is prescribing an inappropriate or inadequate treatment regimen to treat a patient's current infection. Inadequate treatment regimens may include inappropriate, suboptimal, or ineffective medications (e.g., medications to which the infection is known to be drug-resistant), insufficient dosages to overcome drug resistance in the infection, and so on. Thus, the dynamic system 103 can identify how successful individual physicians are in prescribing appropriate medications for the infections they are diagnosing, how effective a particular healthcare facility is in prescribing appropriate medications for the infections it is diagnosing and / or treating, and the amount of new / existing medications prescribed for treatment. Depending on the embodiment, the dynamic system 103 or system 100 dynamically compares numerical values ​​as additional patient records are added or updated in the first data store 104 and / or efficacy information is added or updated in the second data store 108, across physicians in healthcare facilities, physicians in geographical areas, physicians in specific specialties, or any other appropriate population. Depending on the embodiment, the dynamic system 103 or system 100 generates reports for individual physicians to indicate how often an individual physician has inappropriately prescribed medication and to identify situations in which the physician can adapt or modify their routine prescribing strategy to improve the selection of appropriate treatment regimens at an earlier stage of patient care (for example, sending prompts to the physician to inform them of an inappropriate selection of a treatment regimen, sending recommendations for a more optimal treatment regimen, or sending recommendations to pharmacists or laboratory clinicians to encourage early intervention in the treatment regimen chosen by the physician by directing diagnostic testing of patient samples). Other embodiments

[0144] The above description details specific embodiments of the systems, devices, and methods described herein. However, regardless of how detailed the above text may seem, it should be understood that the systems, devices, and methods can be implemented in many ways. Again, as stated above, the use of specific terms when describing particular features or aspects of the invention should not be construed as implying that the terms are redefined herein to include any particular characteristic of any of the features or aspects of the technology to which they relate.

[0145] While the above detailed description has shown, explained, and pointed out novel features of the present development applicable to various embodiments, those skilled in the art will see that various omissions, substitutions, and modifications may be made to the exemplary device or process forms and details without departing from the spirit of the present development. Naturally, since some features may be used or implemented separately from others, the present development may be embodied in forms that do not provide all of the features and advantages described herein. All modifications that fall within the meaning and scope of the claims should be incorporated into the claims.

[0146] Generally, the term “module” as used herein refers to a set of logic or software instructions, possibly having entry and exit points, written in any programming language described herein, and embodied in hardware or firmware. Software modules may be compiled into an executable program, linked, installed in a dynamic link library, or written in any interpreted programming language. It should be understood that software modules may be callable from other modules or by themselves, and / or may be invoked in response to detected events or interrupts. Software modules configured to run on a computing device may be provided on a computer-readable medium such as a compact disk, digital video disk, flash drive, or any other tangible medium. Such software code may be partially or entirely stored in a memory device of the executing computing device, such as dynamic system 103, for execution by the computing device. Software instructions may be embedded in firmware such as an EPROM. It should also be understood that hardware modules may consist of connected logic units such as gates and flip-flops, and / or programmable units such as a programmable gate array or a processor. Modules described herein are preferably implemented as software modules. These may be represented by hardware or firmware. Generally, the modules described herein refer to logical modules, which, despite their physical organization or storage, may be combined with other modules or divided into submodules. Modules can be stored in any kind of non-transient computer-readable medium or computer storage device, such as hard drives, solid-state memory and / or optical discs.The systems and modules may be transmitted as generated data signals (e.g., as part of a carrier wave or other analog or digitally propagated signals) on various computer-readable transmission media, including wireless and wired / cable media, and may take various forms (e.g., as part of a single or multiplexed analog signal, or as multiple individual digital packets or frames). The processes and algorithms may be implemented in part or in whole in application-specific circuits. The processes and process steps of this disclosure may be stored permanently or otherwise in any type of non-transient computer storage, such as volatile or non-volatile storage. Those skilled in the art can implement the described functions in various ways for their respective specific applications, but the determination of such implementation forms should not be construed as resulting in a departure from the scope of the invention.

[0147] A model is a general term for a machine learning construct that can be used to automatically generate results or outcomes. A model may be trained. Model training is a general term for an automated machine learning process to generate a model that accepts inputs and provides results or outcomes as outputs. A model may be represented as a data structure that identifies one or more correlated values ​​for a given value. For example, the data structure may contain data that represents one or more categories. In such an implementation, the model may be indexed to allow for efficient referencing and retrieval of categorical values. In other embodiments, a model may be constructed based on statistical or mathematical properties and / or definitions that are implemented in executable code without necessarily employing machine learning.

[0148] Machine learning is a general term for automated processes in which incoming data is analyzed to generate and / or update one or more models. Machine learning may include artificial intelligence such as neural networks, genetic algorithms, and clustering. Machine learning may be performed using a training set of data. The training data can be used to generate a model that best characterizes the features of interest. Depending on the implementation, the classes of the features may be identified before training. In such cases, the model can be trained to provide an output that is most similar to the desired class of features. Depending on the implementation, there may not be any available prior knowledge to train the data. In such cases, the model may discover new relationships for the provided training data. Such relationships may include similarities between proteins, such as protein functions.

[0149] The microprocessor may be any conventional general-purpose single or multi-chip microprocessor, such as a Pentium(R) processor, Pentium(R) Pro processor, 8051 processor, MIPS(R) processor, PowerPC(R) processor, or Alpha(R) processor. Alternatively, the microprocessor may be any conventional dedicated microprocessor, such as a digital signal processor or graphics processor. The microprocessor typically has conventional address lines, conventional data lines, and one or more conventional control lines.

[0150] The system can be used with various operating systems such as Linux(R), UNIX(R), MacOS(R), or Microsoft Windows(R).

[0151] System control can be written in any traditional programming language such as C, C++, BASIC, Pascal, .NET (e.g., C#), or Java, and can run under traditional operating systems. C, C++, BASIC, Pascal, Java, and FORTRAN are industry-standard programming languages ​​that can use many commercial compilers to create executable code. System control can also be written using interpreted languages ​​such as Perl, Python, or Ruby. Other languages ​​such as PHP and JavaScript are also usable.

[0152] In substantially any use of plural and / or singular terms herein, a person skilled in the art can appropriately convert from plural to singular and / or singular to plural depending on the context and / or use. For clarity, various singular / plural substitutions may be specified herein.

Claims

1. A system for selecting a treatment regimen for a specific patient, A first data store containing first patient records of first multiple patients, A second data store containing efficacy rates of multiple treatment regimens for multiple infectious diseases and pathogens that cause infectious diseases, Including a hardware processor, The aforementioned hardware processor is The system receives from the user a label indicating a first infection in the specific patient, and a first treatment regimen prescribed to treat the first infection. A first database containing a second plurality of patient records is generated by identifying patient records associated with the diagnosis or treatment of a first infectious disease in the first plurality of patient records in the first data store. A second database is generated from the second data store, which includes a second set of patient records to which the efficacy rate of the first infectious disease has been added. The system is configured to execute computer-executable instructions that generate a dynamic model configured to determine a likelihood estimate that the first treatment regimen is an appropriate treatment regimen for treating the first infection. The aforementioned dynamic model is Based on the second database, a first efficacy rate of the first treatment regimen for treating the first infection is identified. From the second database, a second efficacy rate of the second treatment regimen for treating the first infection is identified. The system is further configured to generate a first alert to the user if the identified first effectiveness rate is below a first threshold level or the identified second effectiveness rate is greater than a second threshold level. The first data store sequentially stores additional patient records. The aforementioned hardware processor is The first database and the second database are updated based on the patient records among the additional patient records associated with the first infection. A system further configured to dynamically and automatically execute computer-executable instructions that update the first and second efficiency rates.

2. The system according to claim 1, wherein the computer executable instruction is further configured to receive a label from a user indicating a medical facility, and the second plurality of patient records identified by the computer executable instruction are patient records associated with the first infectious disease and the indicated medical facility.

3. The system according to claim 1 or 2, wherein the computer executable instruction is further configured to receive a geographical area indicator from a user, and the second plurality of patient records identified by the computer executable instruction are patient records associated with the first infection and the indicated geographical area.

4. The system according to any one of claims 1 to 3, wherein the computer executable instruction is further configured to receive a time period indicator from a user, and the second plurality of patient records identified by the computer executable instruction are patient records associated with the diagnosis or treatment of the first infection within the indicated time period.

5. The system according to any one of claims 1 to 4, wherein the computer executable instruction is configured to filter the second plurality of patient records to which an effectiveness rate has been added, such that the second plurality of patient records include patient records associated with a specific treatment regimen among a plurality of treatment regimens, an infection related to the first infection, a geographical area, and a medical facility.

6. The system according to any one of claims 1 to 5, wherein the computer executable instruction is further configured to generate a second alert to the user if, after updating the first and second effectiveness rates, the first effectiveness rate falls below a first threshold or the second effectiveness rate exceeds a second threshold.

7. A computer implementation method for selecting a treatment regimen for a particular patient, using a first data store containing first patient records of first multiple patients and a second data store containing the effectiveness rates of multiple treatment regimens against multiple infections and infectious pathogens, Under the control of one or more processors, Receiving a marker indicating a first infection in the aforementioned specific patient, and a first treatment regimen prescribed to treat the first infection, To generate a first database containing a second plurality of patient records by identifying patient records associated with the diagnosis or treatment of the first infectious disease in the first plurality of patient records of the first data store, To generate a second database containing a second set of patient records, each of which has the efficacy rate of the first infection added from the second data store, A dynamic model configured to determine the likelihood estimate that the first treatment regimen is an appropriate treatment regimen for treating the first infection, Based on the second database, a first efficacy rate of the first treatment regimen for treating the first infection is identified. Further configured to identify a second efficacy rate of a second treatment regimen for treating the first infection from the second database, To generate the aforementioned dynamic model, A computer implementation method comprising generating a first alert if the identified first effectiveness rate is less than a first threshold level or the identified second effectiveness rate is greater than a second threshold level.

8. Additional patient records are sequentially stored in the first data store. The aforementioned computer implementation method Updating the first database and the second database based on the patient records among the additional patient records associated with the first infection, The computer implementation method according to claim 7, further comprising updating the first effectiveness rate and the second effectiveness rate.

9. The computer implementation method according to claim 7 or 8, further comprising receiving a sign indicating a medical facility, wherein the second plurality of patient records are patient records associated with the first infectious disease and the indicated medical facility.

10. A computer implementation method according to any one of claims 7 to 9, further comprising receiving a marker indicating a geographical area, wherein the second plurality of patient records are patient records associated with the first infection and the indicated geographical area.

11. A computer implementation method according to any one of claims 7 to 10, further comprising receiving a label indicating a period, wherein the second plurality of patient records are patient records associated with the diagnosis or treatment of the first infection within the indicated period.

12. A computer implementation method according to any one of claims 7 to 11, further comprising filtering the second plurality of patient records, to which an effectiveness rate has been added, so as to include patient records associated with a specific treatment regimen among a plurality of treatment regimens, an infection related to the first infection, a geographical area, and a healthcare facility.

13. A computer implementation method according to any one of claims 7 to 12, further comprising generating a second alert if, after updating the first and second effectiveness rates, the first effectiveness rate falls below a first threshold or the second effectiveness rate exceeds a second threshold.

Images