SYSTEMS AND METHODS FOR THE DETECTION OF SEPSIS AND TREATMENT OF PATIENTS

Abstract

Systems and methods for the detection of sepsis and treatment of patients. A sepsis detection system includes a first subsystem configured to detect the presence of an infection in a patient, a second subsystem configured to detect the presence of a dysregulated immune response in the patient, a third subsystem configured to detect organ dysfunction in the patient, a fourth subsystem configured to detect antibiotic resistance (ARB) of a pathogen in the patient, and a processing device. The first, second, third, and fourth subsystems and the processing device are communicatively coupled to each other via a network. The processing device is configured to determine the presence of sepsis in the patient based on the presence of infection, the presence of the dysregulated host response, and clinical data indicative of organ dysfunction in the patient.The subsystems utilize at least one polymerase chain reaction (PCR) procedure, Raman spectroscopy, clinical data, electronic health record (EHR) data, and antibiotic susceptibility testing (antibiogram).

Description

Systems and methods for the detection of sepsis and treatment of patients Field of invention This description refers to systems, methods, and devices for the early recognition, detection, and treatment of sepsis using one or more techniques, including, for example, Raman spectroscopy, polymerase chain reaction (PCR), single-cell microscopy, and artificial intelligence (AI). Background of the invention Sepsis is defined as life-threatening organ dysfunction caused by a dysregulated host response to infection. A patient exhibiting or experiencing sepsis may begin with a local infection, such as pneumonia, which leads to systemic inflammation caused by an overactive immune response. This inflammation can ultimately lead to organ failure and death if left untreated. Sepsis causes 11 million deaths annually, and many of these cases are preventable with early diagnosis and appropriate clinical management. Early detection of sepsis, when it can still be effectively treated, is essential for improving patient outcomes and reducing mortality. In some cases, sepsis can be difficult to identify because there is no single, specific biomarker for detecting it. Several sepsis biomarkers exist for different stages of the disease, such as procalcitonin (PCT) or C-reactive protein. However, these biomarkers for the early recognition and diagnosis of sepsis may not be sensitive or specific enough to detect it before symptoms appear. Their positive predictive value can be a limiting factor in many cases. Therefore, establishing a single, concrete criterion for detecting sepsis is challenging due to the complexities and rapid progression of patients' responses to sepsis. Sepsis can be diagnosed through laboratory tests in which blood samples are cultured to identify the infection. Currently, laboratory tests can take several days to produce results due to the time required to obtain and process blood cultures of the bacteria causing the sepsis and ultimately determine their sensitivity to effective antibiotics. However, detecting sepsis can be urgent for hospitalized patients, as it can lead to septic shock and death within hours if not identified and treated promptly. Furthermore, blood culture tests are slow and do not always provide reliable results for detecting bacteria or fungi in patients clinically suspected of having sepsis, especially those who have already undergone antibiotic treatment.Often the yield of positive blood cultures is low, and patients may suffer from sepsis even without a positive blood culture. Brief summary of the invention The embodiments of the present invention provide an economical solution of improved diagnostic methods, systems, and devices for detecting sepsis earlier in the disease cascade, identifying pathogens and antibiotic susceptibility, and managing appropriate treatments in patients to improve patient prognosis. This dissertation describes systems, methods, and devices for the early recognition, detection, and treatment of sepsis using machine learning algorithms, Raman spectroscopy, clinical data, electronic health record (EHR) data, and polymerase chain reaction (PCR). This dissertation also discloses systems, methods, and devices for the rapid detection (or characterization) of the immune response (of the host / patient), identification of pathogens, and antibiotic susceptibility testing (antibiograms) directly from blood samples or other samples such as urine, sterile body fluids, or similar materials.Some implementations provide early warning functionality to monitor patients' EHR data, along with a Raman spectroscopy device that scans blood samples to identify patients with a high probability of having an infection or developing sepsis or septic shock. Some implementations also identify pathogens without a culture step by using a multiplex PCR strategy, significantly reducing analysis time. In some implementations, PCR techniques can also be used to detect genotypic information about a pathogen's resistance. Single-cell microscopy can be used to identify the pathogen's phenotypic susceptibility, leading to a diagnostic pathway for rapid and effective antimicrobial treatments. The systems and methods include predicting sepsis-related health problems and their severity based on an analysis of various available information, including clinical data, immune response data, and infection data. This data can also be used to stratify patients based on the totality of available information. An example system is described in one embodiment. The system includes a first subsystem configured to detect the presence of an infection in a patient, a second subsystem configured to detect the presence of a dysregulated immune response in the patient, a third subsystem configured to detect organ dysfunction in the patient, and a processing device. The first subsystem, the second subsystem, the third subsystem, and the processing device are communicatively coupled to each other via a network. The processing device is configured to determine the presence of sepsis in the patient based on the presence of the infection, the presence of a dysregulated immune response in the patient, and clinical data indicative of organ dysfunction in the patient. In another embodiment, an example system is described. The system includes a first subsystem configured to detect the presence of an infection in a patient, a second subsystem configured to detect the presence of a dysregulated immune response in the patient, a third subsystem configured to detect organ dysfunction in the patient, a fourth subsystem configured to detect antibiotic resistance (ARB), such as the susceptibility of a pathogen in the patient from a sample, and a processing device. The first subsystem, the second subsystem, the third subsystem, the fourth subsystem, and the processing device are communicatively coupled to each other via a network.The processing device is configured to determine the presence of sepsis in the patient based on the presence of infection, the presence of the patient's dysregulated immune response, and clinical data indicative of organ dysfunction in the patient. In yet another embodiment, an example system is described. The system includes a first subsystem configured to receive a first sample from the patient, a second subsystem configured to obtain Raman spectrum data from the patient based on the first sample, and a processing device. The processing device is configured to acquire one or more patient variables from the patient's electronic health record (EHR) data, receive the patient's Raman spectrum data from the second subsystem, and classify the patient into an immune profile group by applying a machine learning algorithm trained on at least one of the EHR data and the Raman spectrum data. Other features and advantages, as well as the structure and operation of different embodiments, are described in detail below with reference to the accompanying figures. It should be noted that the specific embodiments described herein are not intended to be exhaustive. Such embodiments are presented herein for illustrative purposes only. Other embodiments will become evident to those skilled in the relevant technique or techniques based on the information contained herein. Brief description of the drawings / figures The accompanying drawings, which are incorporated in this document and form part of the specification, illustrate the embodiments of the present description and, together with the information, also serve to explain the principles of the invention and enable a person skilled in the relevant art to materialize and use the invention. Figure 1A illustrates an example diagram of the process for sepsis detection, according to the realizations described herein. Figure 1B illustrates an example diagram of a sepsis detection system, according to realizations of the present description. Figure 2 illustrates an example diagram of a Raman spectroscopy device in the sepsis detection system, according to the realizations described herein. Figure 3 illustrates an example diagram of a processing device in the sepsis detection system, according to the embodiments described herein. Figure 4 illustrates an example diagram of an analyzer in the sepsis detection system, according to the realizations described herein. Figure 5 illustrates an example flowchart of a method for training a learning algorithm to identify sepsis in patients, according to realizations of the present description. Figure 6 illustrates an example flowchart of a method for determining the probability of sepsis in a patient, according to realizations of the present description. Figure 7 illustrates a block diagram of the example components of a computer system, according to the realizations of the present description. The realizations described herein will be described with reference to the accompanying drawings. Detailed description of the invention Although certain configurations and arrangements are explained, it should be understood that this is done for illustrative purposes only. A person skilled in the relevant art will recognize that other configurations and arrangements may be used without departing from the spirit or scope of this description. It will be evident to a person skilled in the relevant art that this description can also be used in many other applications. It is important to note that references in the specification to "an embodiment," "an example embodiment," etc., indicate that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Likewise, such phrases do not necessarily refer to the same embodiment. Furthermore, when a specific feature, structure, or characteristic is described in relation to an embodiment, a person skilled in the art should be able to implement that feature, structure, or characteristic in relation to other embodiments, whether or not it has been explicitly described. Introduction: Sepsis is defined as life-threatening organ dysfunction caused by a dysregulated immune response to infection. Sepsis is typically caused by a bacterial infection, but it can also be caused by fungi and viruses. The septic cascade may begin with an infection, followed by an uncontrolled or dysregulated immune response to the infection, which ultimately leads to organ dysfunction, organ failure, and / or death. In some realizations, a patient with sepsis may exhibit symptoms of systemic inflammatory response syndrome (SIRS), which can progress to sepsis, septic shock, multiple organ dysfunction (MOD), and ultimately death. As sepsis worsens, it can lead to abnormal blood clotting, resulting in small clots or the rupture of blood vessels that damage or destroy tissue.This disrupts blood flow to vital organs, such as the brain, heart, and kidneys, leading to organ damage and dysfunction. In a hospital setting, there is an urgent need to identify patients at risk of sepsis and to manage their care appropriately. Without accurate diagnosis and appropriate treatment, the likelihood of patient morbidity and mortality increases significantly with each passing hour. Rapid sepsis detection methods are currently scarce. The gold standard for sepsis detection relies on blood cultures, for which the average turnaround time is approximately 13 hours. Blood culture assays yield one organism, without pathogen identification (ID), followed by plating positive samples onto Petri dishes. In a standard blood culture procedure, two sets of blood culture bottles are collected per adult patient, each set consisting of one aerobic and one anaerobic culture bottle to ensure that the full spectrum of sepsis-causing bacteria is captured during culturing. Typically, each culture is obtained from a separate venipuncture (e.g., the patient's left and right arms).This is done to ensure that the bacterial dispersal event is captured in the culture, so that the bacteria can be recovered for subsequent testing (e.g., ID and antibiogram). After culturing, the aerobic and anaerobic flasks are incubated in a blood culture instrument where their growth is monitored live. The aerobic and anaerobic flasks are incubated and shaken until some bacteria undergo a transition from the latent phase to exponential growth that can be detected electronically. A laboratory worker can then be alerted that a positive culture exists for the patient. Typically, a blood culture will be positive after approximately 13 hours on average for most bacteria, while some yeasts and fungi may take much longer (e.g., up to 5 days).However, many cultures are negative due to an error in collection, insufficient blood volume taken during collection, delays in transport to the laboratory, insufficient sensitivity, or similar reasons. Due to the urgent nature of sepsis, after a positive test result, a laboratory can immediately begin diagnostic testing to identify whether the bacteria are Gram-positive or Gram-negative, determine if the organism is contaminant or significant, whether the infection is caused by a single microorganism or multiple microorganisms, and report this interim information to the physician. In addition, the laboratory can immediately take steps to identify the bacteria using rapid methods, such as molecular diagnostic systems, which can provide results in as little as 1.5 hours. These systems may offer limited molecular information regarding the genetic resistance to drugs of certain bacteria exhibiting these profiles.Alternatively, the laboratory can process the positive blood culture (BSC) aliquot using an array-assisted laser desorption / ionization time-of-flight (MALDI-TOF) mass spectrometry system to identify the bacteria in approximately one hour. This identification allows the physician to confirm or potentially adjust the antibiotics administered prophylactically to the patient. However, by the time the bacteria is identified, 20–24 hours (at best) may have passed since the initial culture was taken from the patient. In parallel with obtaining and describing the identified pathogen, an antibiotic susceptibility test (antibiogram) can also be performed to determine the pathogen's antibiotic susceptibility profile. In some cases, the antibiogram can be performed in vitro on an isolated bacterial pathogen using manual methods, including broth microdilution methods or culture-based assays (e.g., disk diffusion assays or plating on Petri dishes). In other cases, the antibiogram can be performed using automated devices with antibiotic resistance panels to analyze the minimum inhibitory concentration (MIC) of antibiotics or drug resistance. However, these systems may require the isolation of bacterial colonies. For example, current antibiogram methods may require a significant biomass of isolated bacteria to function properly. The positive blood culture must first be subcultured on a medium plated in Petri dishes. This procedure can take 6–12 hours for a laboratory operating around the clock, but can sometimes take up to 24 hours when the laboratory closes overnight. The culture may then need to be adjusted to make it uniform (e.g., starting with 10,000 cells) before loading it into the antibiogram system. After loading, the antibiogram analysis can take 8–16 hours to provide antibiotic susceptibility or resistance information for all classes of organisms. Furthermore, the antibiogram may not begin until the second day of the patient's hospital stay.In other words, the results of the antibiogram analysis (e.g., including whether the bacteria are sensitive, intermediate, or resistant (SIR) to certain antibiotics, MIC, or resistance information) can be reported to the physician approximately 2.5 to 3 days after an initial collection of the original blood culture sample from the patient. The overall procedure can take several days to provide crucial antibiotic information for patients with sepsis. For example, if an infection is suspected, a blood, urine, sputum, or similar sample is collected from the patient and sent to a clinical laboratory to first determine the presence of an infectious agent. This can take 18 to 24 hours (e.g., day 1) for most pathogenic bacterial species to grow sufficiently. If a bacterium is isolated, it takes another 18–24 hours (e.g., day 2) to culture the isolate and a further 2–48 hours (e.g., day 3) to identify the bacterial isolate and perform the antibiogram. Traditional and automated antibiogram methods require a pure culture of the bacterial isolate, along with a long incubation period (e.g., 6–24 hours) for the microorganism to grow.Conventional systems may be inadequate because they are growth-based, slow, expensive, require manual handling, and are not integrated. Without better solutions for detecting sepsis, patients may continue to suffer and often worsen when clinicians treat them with empirically chosen antibiotics while waiting for laboratories to send more useful information about the causative agents of the infection (e.g., pathogens) for treatment. Current technologies do not provide a comprehensive, integrated solution for the entire process of detecting the patient's response, identifying the pathogen, and performing antimicrobial or antibiotic susceptibility testing (antibiogram). In some cases, some systems focus solely on identifying a single aspect of the sepsis cascade, such as detecting the host response or a pathogen. For example, a system might detect the host response for early sepsis by identifying white blood cell RNA molecular markers (using reverse transcription (RT) and PCR to detect gene expression), but it would not provide answers for pathogen identification or susceptibility testing.The outcome of the immune response can alert healthcare professionals that a patient is entering or has entered the septic cascade and urgently requires treatment or intervention to prevent irreversible morbidity. Healthcare professionals can react immediately by searching for the source of the infection and the infectious agent using traditional methods, such as obtaining blood cultures from the site of infection, to identify the infectious agent. Regarding pathogen detection, current technologies can offer a direct identification and detection method from blood, thanks to the use of PCR on blood samples followed by detection by nuclear magnetic resonance (NMR) spectroscopy. However, such systems can be expensive, have limited menu options, and be difficult to implement, without providing a solution for rapid antibiogram results, and instead offer a limited panel of molecular genetic resistance. Other systems can use RT-PCR of pathogen RNA directly from blood for pathogen identification, but these too may be constrained by a very limited menu (e.g., 15 targets or fewer).Finally, current technologies do not offer an automated, rapid antibiogram solution directly from blood. Instead, they rely on positive blood cultures, which can take 13 to 20 hours to yield a useful result. For example, some systems can obtain aliquots from positive blood culture bottles (BCBs), saving the time required for bacterial isolate growth from the BCB bottle (e.g., 6–24 hours). However, these systems are limited by the number of drugs and organisms they can report on and are therefore of little use to clinicians.To greatly reduce mortality, new diagnostic methods and systems for sepsis are needed to rapidly determine the antibiotic sensitivity and antibiotic resistance of an infectious bacterium causing sepsis from a small copy number or a single cell, which is detected directly from a blood sample without the significant time delay required for the multiple culture stages (e.g., biological amplification) currently required by reference treatment methods. Because septic conditions often go undetected in patients and rapidly progress to life-threatening pathological processes, there is a clear need and demand for new and comprehensive systems, devices, and methods to acquire rapid and relevant information about the host immune response, identify causative pathogens, and provide guidance on appropriate antibiotics to save lives and reduce antibiotic resistance (ARR). The systems, devices, and methods described herein present a systematic and holistic strategy for identifying and managing sepsis and its severity in patients, determining the antibiotic susceptibility and resistance of identified pathogens, and recommending treatments that are effective and appropriate for patients. Overview of sepsis detection: Figure 1A illustrates an example flowchart of a sepsis detection workflow 100 according to the embodiments described herein. As shown in workflow 100, sepsis can be detected by identifying the three stages that occur in a patient: organ dysfunction, dysregulation of the host response, and infection. In this document, the terms patient and host are used interchangeably to refer to the living being (e.g., human) that, as a result of an infection, experiences a dysregulated immune response. Organ dysfunction can represent a pathological process in a patient where one or more organs are unable to perform their expected functions. In some cases, organ dysfunction can lead to organ failure, in which organs in different body systems or apparatuses can fail as a consequence of sepsis and septic shock (e.g., multiple organ dysfunction syndrome (MODS)). In some cases, a patient's caregiver might not identify the presence of sepsis until the patient exhibits signs of organ dysfunction and / or organ failure. For example, signs of organ dysfunction or failure may include fever, irregular or rapid heartbeat (tachycardia), abnormally rapid breathing (tachypnea), decreased urine output, and the like.Due to the rapid progression of the septic cascade in a patient, identifying sepsis at this stage may be too late to prevent the patient's deterioration. It can be difficult for the caregiver to quickly provide the patient with appropriate care and treatment to prevent morbidity and mortality. Organ dysfunction may ultimately result from a dysregulated host response. In some realizations, a dysregulated host response may be referred to herein as a dysregulated immune response. A dysregulated host response can be the body's unregulated response to infection or injury, in which the body does not follow the process of a normal immune response. This dysregulated host response may include inflammation, immunosuppression, as well as neuroendocrine, coagulation, and metabolic responses. Disseminated inflammatory conditions can result from an interaction between a pathogenic microorganism and the host's defense system, triggering an excessive and dysregulated response in the host. Identifying a dysregulated host response in a patient can lead to the detection of an infection. Specifically, a dysregulated host response may be caused by an infection. In some embodiments, the infection may be caused by a pathogen. In some embodiments, a pathogen may be referred to herein as a bacterium or bacteria, organism, microorganism, single-celled or loosely cellular microorganism, microbe, virus, or similar. An infection can begin anywhere in the body and can spread throughout if not treated appropriately. For example, an infection in a patient may lead to a dysregulated host response and may ultimately cause organ dysfunction. In some implementations, the presence of sepsis in a patient can be determined by detecting at least one of the following: organ dysfunction, dysregulated host response, and infection. In some implementations, all three stages or aspects of sepsis can be detected in any order and using different technologies, as further described in this document. In some implementations, organ dysfunction in a patient can be determined based on at least one of the following: clinical data, EHR data, SOFA scores, and Raman spectroscopy data from a patient sample, along with trained learning algorithms. In some implementations, a dysregulated host response in a patient can be detected using at least one of the following: Raman spectroscopy data from a patient sample and EHR data, along with trained learning algorithms. In some implementations, the presence of an infection in a patient can be determined using at least one of the following: PCR testing of a patient sample and analysis of data related to the patient's immune response.In some embodiments, the presence of an infection in a patient can be determined by performing a PCR on a patient sample, and a dysregulated host response can be detected by Raman spectroscopy data from a patient sample. In some implementations, organ dysfunction, dysregulated host response, and infection can be represented by a clinical score, immune score, and infection score, respectively. In some implementations, these three different scores can be used to calculate a sepsis score for sepsis detection. In some embodiments, organ dysfunction, dysregulated host response, and infection can be detected by different subsystems and systems that include different modules, computer devices, or systems and / or technologies, as described later in this document. System overview: Figure 1B illustrates an example diagram of a sepsis detection system 101, according to embodiments of the present description. In some embodiments, the sepsis detection system 101 may be referred to as system 101 in this specification. System 101 may comprise a Raman spectroscopy device 102, an electronic health record (EHR) system 104, a processing device 106, an analyzer 108, and multiple databases 110 connected communicatively via a network 112. In some embodiments, different combinations of one or more of the components of system 101 can be used together and / or separately to detect sepsis and identify the progression of sepsis, including detecting organ dysfunction, dysregulated host response, and infection in a patient, as described in this dissertation. System 101 may comprise a Raman spectroscopy device 102 configured to scan patient samples. In some embodiments, the Raman spectroscopy device 102 may be referred to herein as a Raman reader or Raman scanner. The Raman spectroscopy device 102 may be used to acquire Raman spectrum data for immune response screening or triage of samples from patients suspected of having sepsis upon admission to a hospital through the emergency department or who are already hospitalized. In some embodiments, the Raman spectroscopy device 102 may scan patient plasma samples preserved in ethylenediaminetetraacetic acid (EDTA).In some embodiments, the Raman 102 spectroscopy device may reside inside or outside a hospital laboratory and may use a sample collection tube to read plasma samples from patients. In some implementations, Raman spectra data acquired from patient samples using the Raman 102 spectroscopy device can be used to provide a rapid indication of a patient's sepsis probability or a probability score for a "septic state." This information informs clinicians to escalate sepsis treatment and follow a comprehensive diagnostic protocol based on the probability value. Specifically, the Raman 102 spectroscopy device can perform Raman spectroscopy on a small portion of a plasma sample to obtain a Raman spectrum comprising one or more peaks that represent a signature of the host response in the sample.In some embodiments, the Raman spectroscopy device 102 can communicate with the processing device 106 in the sepsis detection system 101 to use the acquired Raman spectrum data, along with machine learning algorithms and / or other decision tool parameters, to rapidly detect sepsis and / or provide a sepsis probability value or score. In some embodiments, the Raman spectroscopy device 102 can transmit the Raman spectrum data to the processing device 106, and the processing device 106 can train a deep learning algorithm to identify a probability of infection, or sepsis, in future patients using the Raman spectrum data. Finally, the Raman spectrum data can be used to distinguish patients with sepsis from patients without sepsis based on their host response Raman signature. In addition to the Raman spectroscopy device 102, system 101 also comprises an EHR system 104. The EHR system 104 can include any number of servers, computers, and / or devices configured to electronically store patient health information. In some embodiments, the EHR system 104 can aggregate data from different healthcare services and providers, such as hospitals, clinical care facilities, laboratories, radiology providers, and pharmacies. Although only one EHR system 104 is illustrated in Figure 1B for reference, there can be any number of EHR systems 104, where each EHR system 104 is associated with one or more hospitals or other healthcare delivery facilities. In some embodiments, the EHR 104 system may comprise one or more EHR databases (not shown) that store patient data and medical history data pertaining to patient health and treatment. In some embodiments, the data stored in the EHR 104 system may be referred to herein as EHR data. In some embodiments, one or more EHR databases within the EHR 104 system may store records for each patient, including demographics, medical history, medications and allergies, immunization status, laboratory test results, radiological images, vital signs, personal statistics such as age and weight, and billing information for each patient. Records in the EHR 104 system may include observational data records, patient consultations, laboratory results, prescriptions, and messages (e.g.,messages that healthcare staff transmit to their patients) and also biographical information about a patient, such as name, address, date of birth, and the like. In some implementations, the EHR 104 system can also store data regarding previous illnesses, long-term comorbidities, medications, interventions, and the like for each patient. In some embodiments, one or more of the multiple databases 110 in system 101 may be integrated within the EHR system 104. For example, the multiple databases 110 may include one or more EHR databases, which can be accessed by the processing device 106 to retrieve, acquire, and / or monitor patient information. In other embodiments, the multiple databases 110 may be separate from the EHR system 104. In some embodiments, the multiple databases 110 may represent any number of databases and may include different databases that store clinical parameter data, epidemiological information, antibiotic resistance information for multiple pathogens, organ dysfunction data, Raman spectrum data, and the like.In some embodiments, the multiple 110 databases may store organ dysfunction data for multiple patients, where the organ dysfunction data includes one or more scores associated with at least one of the following: Sequential Organ Failure Assessment (SOFA) scale, Rapid SOFA, Logistic Organ Dysfunction System (SDOL), Emergency Department Severity Prognostic Scale (NEWS), and / or Modified Severity Prognostic Scale (MEWS). In some embodiments, the multiple 110 databases may include a clinical database that stores Raman spectra data from validated sepsis samples. For example, the clinical database may include Raman spectra data from sepsis patients showing peaks that represent septic host response signatures from the multiple samples corresponding to septic patients.In some embodiments, data in the clinical database or a Raman spectrum database can be collected and compiled from the Raman spectroscopy device 102 and / or the EHR system 104 using the processing device 106, and updated with one or more machine learning algorithms as described herein. In some embodiments, the clinical database can store a Raman spectral collection of Raman spectrum data from known samples of septic patients. The processing device 106 can coordinate the communication, computerization, and processing of data obtained from the Raman spectroscopy device 102, the EHR system 104, the analyzer 108, and the multiple databases 110. In some embodiments, the processing device 106 can acquire EHR data and data associated with laboratory information system (LIS) parameters from the EHR system 104 and / or the databases 110. In some embodiments, the processing device 106 can monitor EHR data and acquire patient data for one or more patient variables from the EHR data for multiple patients.In some embodiments, patient variables may include at least one of the following: temperature, heart rate, systolic blood pressure, respiratory rate, white blood cell count, platelet count, partial pressure of arterial oxygen to fractional inspired oxygen (PaO2 / FiO2) ratio, bilirubin concentration, Glasgow Coma Scale score, mean cardiovascular arterial pressure, creatinine concentration, urine output, lactate concentration, C-reactive protein concentration, and procalcitonin concentration. The 106 processing device can monitor EHR data and identify one or more patient variables that are indicative of a change in a patient's condition based on this monitoring. In some embodiments, the processing device 106 can also collect and / or receive Raman spectrum data from multiple patients from the Raman spectroscopy device 102. In some embodiments, the processing device 106 can use either Raman spectrum data or EHR data separately to determine the presence of sepsis in patients by training a learning algorithm and applying the trained learning algorithm to the Raman or EHR data. In alternative or additional embodiments, the processing device 106 can integrate the acquired EHR data with the Raman spectrum data acquired from the Raman spectroscopy device 102 to improve the prediction of whether a patient is likely to have sepsis. In some embodiments, integrating EHR data with Raman spectrum data can help strengthen the certainty of the sepsis prediction model (e.g.,, the learning algorithm) of whether a patient who has been tested has a high probability or possibility of suffering from sepsis. In some embodiments, the processing device 106 may further generate one or more notifications indicating the results of the sepsis prediction or identification probability, and the processing device 106 may transmit one or more notifications to at least one of a healthcare provider-associated computing device or to the analyzer 108. In some embodiments, the sepsis prediction or identification results may indicate a low probability of infection and / or sepsis in the patient, where a probability value may be less than a predetermined threshold value. In other embodiments, the sepsis prediction or identification results may indicate a high probability of infection and / or sepsis in the patient, where a probability value may be greater than or equal to a predetermined threshold value. In some embodiments, the processing device 106 can employ a deterministic model to reduce false positives and unnecessary "noise" arising from systemic inflammatory response syndrome (SIRS) in patients or from non-sepsis patients who may be ill with other conditions for which the learning algorithm might not be trained. Furthermore, the processing device 106 can incorporate decision models for prognostic screening of patient severity using Raman spectrum data (e.g., Raman scattering data) from plasma samples and Raman spectrum data from clinical databases, which could be regularly updated with validated sepsis samples. In some embodiments, the Raman spectroscopy device 102, the EHR system 104, and / or the processing device 106 can be used together to provide early warning of sepsis in patients.The 106 processing device can screen patients based on Raman spectrum data and / or EHR data, and help pinpoint which patients show early signs of sepsis. In some embodiments, the processing device 106 can monitor the EHR data of multiple patients in the EHR system 104 and determine whether one or more patient variables indicate a change in patient status for each patient among the multiple patients, based on this monitoring. If the values ​​of one or more patient variables are above a predetermined threshold value for a patient, then the processing device 106 can transmit a command to the Raman spectroscopy device 102 to acquire Raman spectrum data for the identified patient. The processing device 106 can then use the Raman spectrum data and / or the EHR data to identify the probability of infection and / or sepsis in the patient, such as by applying a trained algorithm to the collected Raman spectrum data and / or EHR data. In some embodiments, this preventive screening implemented in the processing device 106 can identify patients at risk of sepsis, transmit alerts to the clinicians of the identified patients, and transmit notifications to computer devices in a laboratory (e.g., within or outside a hospital) to obtain further samples from the patients for diagnosis using the analyzer 108. The processing device 106 can also provide clinicians with rapid results on a patient's immune status, pathogen identification, and antimicrobial susceptibility testing (antibiogram) results as information is received from one or more of the following: Raman spectroscopy device 102, EHR system 104, analyzer 108, and multiple databases 110 in the sepsis screening system 101.In addition, because many sepsis patients are often readmitted months after leaving the hospital, the 106 processing device can be configured to collect, process, and / or compare previous values ​​for a sepsis patient to identify the best treatment plans to address recurrent infection or other complications resulting from a previous sepsis event. After detecting the probability of sepsis in a patient sample using the Raman spectroscopy device 102, the EHR system 104 and / or the processing device 106, the patient sample (or other sample collected from the patient) can subsequently be subjected to direct analysis by the analyzer 108 for rapid identification directly from the blood and the antibiogram. The 108 analyzer may include one or more modules for sample collection, pathogen identification, and sensitivity testing. In some embodiments, the 108 analyzer may employ polymerase chain reaction (PCR) technology for rapid pathogen identification in blood samples to achieve highly competitive sensitivity (compared to blood culture detection concentrations) while ensuring specificity. In some embodiments, the 108 analyzer may use PCR technology to test for a set of viral targets or a panviral target to guide clinicians regarding viral and bacterial infections or coinfections. In some embodiments, the 108 analyzer may use PCR technology to test for a set of fungal targets or a panfungal target.By applying PCR to samples, the 108 analyzer can provide high sensitivity for detecting clinically low bacterial loads without requiring blood culture or a growth stage. In some implementations, the 108 analyzer can also incorporate PCR technology for rapid resistance detection in addition to pathogen identification. In addition, the 108 analyzer can be configured to analyze the susceptibility of the pathogen causing an infection in a patient. The antibiogram can provide the clinician with treatment options for patients with bacterial or other microbial infections. In some embodiments, the 108 analyzer can be configured to analyze susceptibility to multiple antibiotics or antimicrobials to determine which antibiotic or antimicrobial the pathogen is sensitive or resistant to. In some embodiments, the 108 analyzer can determine the minimum inhibitory concentration (MIC) of an antibiotic that inhibits the growth of a pathogen. The antibiogram results can be used by the 108 analyzer and / or the 106 processing device to determine which antimicrobials to recommend for treating a patient's infection. In some embodiments, the 108 analyzer can be configured to receive a sample from the container or consumable holding a patient sample. In some embodiments, the 108 analyzer user can pipette the patient sample or transfer it directly to the consumable. In some embodiments, the user can insert the consumable into the 108 analyzer. In some embodiments, the consumable can be discarded after a single use or reused to analyze additional samples. In some embodiments, the analyzer 108 can transmit the pathogen identification and antibiogram analysis results to the processing device 106. The processing device 106 can then generate a recommendation for an antibiotic to treat the patient based on the results.In some embodiments, the processing device 106 can access one or more databases 110 to search for epidemiological or antibiotic resistance information for the identified pathogen and generate a recommendation for patient treatment based on the results of the antibiogram analysis and the epidemiological or antibiotic resistance information for the pathogen. In some embodiments, the Raman spectroscopy device 102, the electronic health record (EHR) system 104, the processing device 106, the analyzer 108, and / or the multiple databases 110 can be further coupled to one or more computer devices (not shown) associated with healthcare personnel, such as a physician, physician assistant, registered nurse, nurse, clinical pharmacist, specialist, or similar. The one or more computer devices associated with the healthcare personnel can be a personal digital assistant, desktop workstation, laptop, netbook, tablet, smartphone, mobile phone, smartwatch, or other wearable technology, or any combination thereof. In some embodiments, a healthcare professional can access the results of any of the sepsis detection methods described herein using one or more computer devices.In some embodiments, one or more computer devices associated with healthcare personnel can transmit data requests to the Raman spectroscopy device 102, electronic health record (EHR) system 104, processing device 106, analyzer 108 and / or the multiple databases 110. In some embodiments, one or more computer devices associated with healthcare personnel may receive data related to a patient's sepsis status based on detection methods performed by the Raman spectroscopy device 102, processing device 106, and / or analyzer 108. In some embodiments, one or more computer devices associated with healthcare personnel may receive notifications related to a pathogen identified in a patient and / or recommendations for treating the patient with one or more antibiotics based on the results of susceptibility testing from at least one of the Raman spectroscopy device 102, processing device 106, and analyzer 108. In some embodiments, the sepsis detection system 101 can be configured to monitor EHR data for a patient using the EHR system 104, and identify a probability of infection or sepsis in the patient based on the application of a learning algorithm trained on at least one of the EHR data and data relating to one or more patient variables indicative of a change in the patient's condition using the processing device 106. The sepsis detection system 101 can further be configured to identify a pathogen in a patient sample and identify antibiotic susceptibility and / or resistance for the patient based on the identification of the pathogen using the analyzer 108.In some embodiments, the Sepsis Detection System 101 can receive organ dysfunction data for the patient from one or more databases, where the organ dysfunction data includes one or more scores associated with at least the Sequential Organ Failure Assessment (SOFA), Rapid SOFA, or NEWS scale. The Sepsis Detection System 101 can use the organ dysfunction data to identify the likelihood of infection and / or sepsis in the patient. Finally, the Sepsis Detection System 101 can provide an integrated end-to-end system for sepsis prediction or detection, pathogen identification, and sensitivity analysis to rapidly deliver results to healthcare personnel to improve patient care and response. In some embodiments, the components of the sepsis detection system 101 can be communicatively coupled via network 112. Specifically, network 112 can enable information transmission and communication between the Raman spectroscopy device 102, the electronic health record (EHR) system 104, the processing device 106, the analyzer 108, and / or the multiple databases 110. Network 112 can be one, or any combination thereof, of a LAN (local area network), WAN (wide area network), telephone network, wireless network, point-to-point network, star network, token ring network, concentrator network, or other suitable configuration. The network may comply with one or more network protocols, including the Institute of Electrical and Electronics Engineers (IEEE) protocol, the Third Generation Membership Project (3GPP) protocol, a 4th generation (4G) wireless protocol (e.g., the Long Term Evolution (LTE) standard, LTE Advanced, LTE Advanced Pro), a fifth generation (5G) wireless protocol and / or similar wired and / or wireless protocols, and may include one or more intermediate devices for routing data between the Raman spectroscopy device 102, the electronic health record (EHR) system 104, the processing device 106, the analyzer 108 and / or the multiple databases 110. Raman spectroscopy device: Figure 2 illustrates an example diagram of a Raman spectroscopy device 200 in the sepsis detection system, according to embodiments of the present description. The Raman spectroscopy device 200 represents an exemplary embodiment of the Raman spectroscopy device 102 of Figure 1B. The Raman spectroscopy device 200 includes an optical source 210, a Raman spectrometer 220, and a probe 225. Although the Raman spectroscopy device 200 in Figure 2 shows only three components for reference, any additional number of components may be included to perform Raman spectroscopy in the Raman spectroscopy device 200. In some embodiments, the Raman spectroscopy device 200 may include additional components and / or optical elements, such as lenses, filters, mirrors, gratings, detectors, objectives, and / or the like.Although Figure 2 illustrates only one optical source 210 for reference, there can be any number of optical sources 210 in the Raman spectroscopy device 200. In some embodiments, the optical source 210 may be designed to emit a beam of radiation of only a single wavelength or it may be a scanning source and be designed to emit a range of different wavelengths. In some embodiments, the optical source 210 may comprise a laser or a laser diode. The laser may be configured to emit a beam of laser energy radiation at a wavelength of approximately, or close to, 780 nm or 532 nm. In some embodiments, two optical sources 210 may be used in the Raman spectroscopy device 200, wherein the two optical sources 210 are configured to emit beams of radiation at 780 nm and 532 nm, respectively. In some embodiments, the radiation beam may be generated by the optical source 210 and transmitted through a probe 225 to a sample in the sample tube 230. The sample tube 230 may contain a plasma sample from a patient, which is to be interrogated by the probe 225 to detect the likelihood of sepsis in the patient. In some embodiments, the probe 225 may comprise a fiber optic probe configured to transmit the radiation beam into the sample. In some embodiments, the probe 225 may be configured to interact with the sample in the sample tube 230 by interrogating the sample with the transmitted radiation beam and receiving scattered Raman radiation from the sample. In some embodiments, the probe 225 may collect the beam returned from the sample tube 230 after the interrogating radiation beam has interacted with the sample. In some embodiments, probe 225 can be configured to send the collected radiation to Raman spectrometer 220. In some embodiments, the collected radiation can be processed or filtered by one or more optical elements during transmission from probe 225 to Raman spectrometer 220. In some embodiments, Raman spectrometer 220 can be configured to receive the collected radiation beam (e.g., scattered Raman radiation) from probe 225. In some embodiments, Raman spectrometer 220 can include a detector (not shown) configured to obtain a Raman signal from the collected radiation beam. In some embodiments, the detector can include a charge-coupled device (CCD) or a photomultiplier tube (PMT) that is highly sensitive to detecting the Raman signal. In some embodiments, the detector can include a diffraction grating, either transmitting or reflecting. In some embodiments, the Raman 200 spectroscopy device may include a processor (not shown) that can be configured to receive the Raman signal from the Raman 220 spectrometer and process the Raman signal to generate Raman spectrum data of the sample. In some embodiments, the Raman spectrum data may include one or more peaks representing a host response signature of the sample.In some realizations, Raman spectrum data can provide information on baseline parameters of a patient's immune profile, as well as information on specific parameters directly related to the septicemic cascade, including the identification of procalcitonin (PCT) and C-reactive protein as indicators of infection, the identification of a cytokine storm as an indicator of a dysregulated host response, and the identification of bilirubin and creatinine as indicators of organ failure. The Raman spectrometer processor 220 can obtain Raman spectrometer data from the sample and compare the reading with previous Raman spectral data from samples of known septicemic patients to identify a patient's septicemic state (e.g., preseptic or at different levels of sepsis severity). In some embodiments, the processor in the Raman spectroscopy device 200 can access a Raman spectral collection that may be stored in memory in the Raman spectroscopy device 200 or in one or more databases 110 in the sepsis detection system 101. The processor in the Raman spectroscopy device 200 can use the data in the Raman spectral collection to determine a patient's probability of sepsis by comparing the current Raman spectral data with historical Raman data stored in the Raman spectral collection. In additional or alternative embodiments, the Raman spectroscopy device 200 may be communicatively coupled to a separate computing device comprising a processor configured to receive the Raman signal from the Raman spectrometer 220 and perform Raman signal processing to generate Raman spectrum data of the sample. In some embodiments, the separate computing device may be separate from the spectroscopy device 200 and coupled to the Raman spectroscopy device 200 via a wired or wireless connection. In some embodiments, the separate computing device coupled to the Raman spectroscopy device 200 may be the same as, or different from, the processing device 106 in the sepsis detection system 101. In some embodiments, the Raman spectroscopy device 200 can be configured to perform non-contact Raman spectroscopy readings on liquid plasma samples from patients. In some embodiments, the plasma used for testing may not require any sample preparation steps. In some embodiments, the probe 225 can be configured to perform a Raman reading within the primary tube (e.g., sample tube 230) where the plasma is separated from the patient sample by centrifugation. In some embodiments, the plasma can be contained in a cuvette or tube (e.g., sample tube 230) with a size and dimensions that do not affect the Raman signal reading, thus avoiding the use of an expensive substrate that is devoid of Raman signal. In some embodiments, the Raman 200 spectroscopy device can be used as a standalone device for sepsis detection and patient sample management for triaging patients who may be at risk of developing sepsis. In other embodiments, the Raman 200 spectroscopy device can be used in combination with, or integrated into, a sepsis diagnostic device. For example, the Raman 200 spectroscopy device can be integrated within the 108 analyzer to form a diagnostic instrument configured to perform Raman spectroscopy readings of samples and subsequently carry out pathogen identification and susceptibility testing using the respective components. Approximately 90% of sepsis cases occur after patients are admitted to a hospital. Therefore, in some implementations, the Raman 200 spectroscopy device can use Raman spectrum data in combination with multiple diagnostic parameters collected from patients (e.g., in a hospital emergency department) to further improve the accuracy of sepsis detection. In some implementations, the Raman 200 spectroscopy device can receive diagnostic parameter data from patients being tested in the Emergency Department via the EHR 104 system.In some implementations, the diagnostic parameters obtained from the EHR system may include measured data from complete blood counts, including red blood cell count, white blood cell count, platelet count, hemoglobin, and hematocrit; coagulation data, including prothrombin time, activated partial thromboplastin time, and fibrinogen; and biochemical data, including urea, creatinine, sodium, potassium, aspartate aminotransferase (AST) or glutamate oxaloacetate transaminase (GOT), alanine aminotransferase, and total bilirubin. In some implementations, the Raman 200 spectroscopy device may combine the Raman spectrum data with the results of other diagnostic tests (e.g., biomarker measurements) or additional information available in a patient's medical record to refine the results and perform patient phenotyping. Processing device: Figure 3 illustrates an example diagram of a processing device 300 in the sepsis detection system, according to embodiments of the present description. The processing device 300 represents an exemplary embodiment of the processing device 106 in Figure 1B. In some embodiments, the processing device 300 may be referred to herein as a processing device 300 for sepsis detection. In some embodiments, the 300 processing device includes one or more computing devices that can be implemented in many ways. For example, the modules, other functional components, and data can be deployed on a single computing device, a cluster of computing devices, a server farm or data center, a cloud-hosted computing service, etc., although other computing architectures can be used additionally or as an alternative. Furthermore, although the figures illustrate the components and data of the 300 processing device as if they were present in a single location, these components and data can alternatively be distributed across different computing devices and locations in any manner. Consequently, the functions can be implemented on one or more computing devices, with the different functionalities described above distributed differently among the various computing devices. In the illustrated example, the processing device 300 includes one or more processors 302, one or more computer-readable media 304, and one or more communication interfaces 306. Each processor 302 is a single processing unit or multiple processing units, and may include one or more compute units, or multiple processing cores. The one or more processors 302 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operational instructions. For example, the one or more processors 302 may be one or more physical processors and / or logic circuits of any suitable type specifically programmed or configured to execute the algorithms and procedures described herein.One or more 302 processors can be configured to fetch and execute computer-readable instructions stored on 304 computer-readable media, which can program the one or more 302 processors to perform the functions described herein. 304 computer-readable media includes volatile and non-volatile memory, and / or removable and non-removable media implemented in any type of technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.Such computer-readable media 304 include, but are not limited to, RAM, ROM, EEPROM, USB flash drives or other memory technologies, optical storage, solid-state storage, magnetic tape, magnetic disk storage, network-attached storage, storage area networks, cloud storage, or any other medium that can be used to store the desired information and is accessible by a computing device. Depending on the configuration of the processing device 300, computer-readable media 304 may be a type of computer-readable storage medium and / or may be a tangible non-transient medium to the extent that, when mentioned, non-transient computer-readable media excludes media such as energy, carrier signals, electromagnetic waves, and signals per se. The computer-readable medium 304 is used to store any number of functional components that are executable by the processors 302. In many implementations, these functional components comprise instructions or programs that are executable by the processors and that, when executed, specifically configure one or more processors 302 to perform the actions attributed above to the processing device 300. In addition, the computer-readable medium 304 may store data that will be used to perform the operations described herein. In the illustrated example, the computer-readable medium 304 further includes an EHR module 308, a Raman module 310, a machine learning module 312, an identification module 316, and an antibiogram module 318. In some embodiments, the different modules in the processing device 300 can provide tools that help physicians, healthcare assistants, and / or caregivers make better decisions regarding treatment for patients based on the identification of infection, dysregulated host response, or organ dysfunction or organ failure in a patient. The EHR 308 module can communicate and interface with the EHR 104 system to provide the processing device 300, Raman spectroscopy device 102, and / or analyzer 108 with access to EHR data for multiple patients, including patient data and medical history data. In some implementations, the EHR 308 module on the processing device 300 can receive and / or access EHR data from the electronic health record in the EHR 104 system. In some implementations, patient data received from the EHR 104 system by the EHR 308 module may be encrypted and can be decrypted upon receipt by the EHR 308 module. In some implementations, the EHR 308 module can monitor data for one or more patient variables from the EHR data for multiple patients.In some implementations, by monitoring EHR data, the EHR 308 module can provide an early warning of potential sepsis in a patient. In some implementations, the EHR 308 module can monitor EHR data for multiple patients over a predetermined period or periodically at a predetermined interval to detect whether any patient variables in the EHR data indicate a change in the condition of any of the patients. In some implementations, changes in a patient's condition can be represented by predetermined changes in patient variables, and these changes can indicate organ dysfunction in the patient. In some implementations, the EHR 308 module can initiate a sepsis screening procedure after detecting that one or more patient variables exceed or equal one or more predetermined threshold values, indicating a change in a patient's condition. In some implementations, after detecting that one or more patient variables are greater than or equal to one or more predetermined threshold values, the EHR 308 module can transmit a notification to at least one of the Raman 310 module, the ID 316 module, and the Antibiogram 318 module, indicating that a change in a patient's condition has been detected. The notification transmitted by the EHR 308 module can cause at least one of the Raman 310 module, the ID 316 module, and / or the Antibiogram 318 module to perform one or more steps of a sepsis screening procedure.In some implementations, the EHR 308 module can also communicate with one or more 110 databases to retrieve clinical parameter data and organ dysfunction data, such as SOFA scores. The data retrieved from the one or more 110 databases can also be used to assess the likelihood of sepsis in a patient using the EHR 308 module and / or the Raman 310 module. The Raman 310 module can communicate with the Raman 200 spectroscopy device to process and analyze Raman spectral data obtained from patient samples. In some embodiments, the Raman 310 module can receive Raman spectral data from patient samples from the Raman 200 spectroscopy device, process and analyze the Raman spectral data, and perform rapid sepsis detection based on the Raman spectral data. In some embodiments, the Raman 310 module can process and analyze the Raman spectral data to identify one or more peaks representing a Raman signature from a patient sample. In some embodiments, the Raman 310 module can perform Raman spectral data analysis to identify a Raman fingerprint of the pathogen and one or more biomarkers indicative of infection and dysregulated host response.In some embodiments, the Raman 310 module can correlate the sample's Raman signature with a host response signature. In some embodiments, the Raman 310 module can predict the likelihood of a patient having an infection, the likelihood of a patient having bacteremia (e.g., the presence of bacteria in the patient's bloodstream), and / or the likelihood of a patient developing sepsis based on the sample's host response signature. The use of Raman spectrum data by the Raman 310 module can enable the 300 processing device to provide inexpensive and highly accurate results for the rapid detection and prediction of sepsis in patients. In some embodiments, the Raman 310 module in the processing device 300 can identify one or more biomarkers indicative of organ failure or organ dysfunction using Raman spectral data obtained from the Raman spectroscopy device 200. In some embodiments, the Raman 310 module can determine one or more variables of a SOFA score using spectroscopic data from a patient sample obtained with the Raman spectroscopy device 200. In some embodiments, the Raman 310 module can use SOFA scores (e.g., calculated based on Raman spectroscopic data) to determine organ dysfunction. To perform sepsis detection (e.g., to detect organ dysfunction, dysregulated host response, and / or infection), the Raman module 310 can communicate with a machine learning system 312 that includes a learning algorithm 314. In some embodiments, the machine learning system 312 can be configured to train the learning algorithm 314 using Raman spectra data, EHR data, and the sepsis status corresponding to each patient among multiple patients. In some embodiments, the machine learning system 312 can receive multiple EHR data sets for multiple patients from the EHR system 104 via the EHR module 308. The machine learning system 312 can also receive multiple Raman spectra data sets generated by the Raman spectroscopy device 102, 200 via the Raman module 310.In addition to EHR and Raman data, machine learning 312 can also receive multiple sepsis status determinations from EHR system 104 via EHR module 308, where each sepsis status determination corresponds to a specific patient among the multiple patients. In some embodiments, machine learning 312 can train learning algorithm 314 using multiple EHR datasets, multiple Raman spectra datasets, and multiple sepsis status determinations, where learning algorithm 314 is trained to identify the likelihood of infection or sepsis in future patients based on a classification of each EHR dataset and each Raman spectra dataset. In some embodiments, the EHR module 308 and / or the Raman module 310 can communicate with the machine learning module 312 to train the learning algorithm 314 and apply machine learning technology to EHR data and / or Raman spectra data to identify sepsis in future patients based on the trained learning algorithm 314. In some embodiments, the learning algorithm 314 can be trained to identify the likelihood of infection or sepsis in future patients based on a classification of each EHR data point and each Raman spectra data point. In some embodiments, the learning algorithm 314 may be referred to herein as a learning model and / or a sepsis prediction model. In some embodiments, the learning algorithm 314 may comprise any learning algorithm, such as a Bayesian network, a neural network, a deep learning algorithm, or similar.In some embodiments, the Raman module 310 and / or the EHR module 308 may implement the learning algorithm 314 to classify patients as having or not having sepsis based on Raman spectrum data and / or EHR data corresponding to the patients. In some embodiments, the Raman module 310 may acquire one or more patient variables from EHR data for a patient (e.g., from the EHR module 308 and / or the EHR system 108), receive Raman spectrum data for a patient sample (e.g., from the Raman spectroscopy device 102, 200), and classify the patient into an immune profile group by applying the trained learning algorithm 314 to at least one of the acquired EHR and Raman spectrum data. In addition to using the Raman module 310 and / or the EHR module 308 to stratify patients according to their septic status, the processing device 300 can also include the identification module 316 and the antibiogram module 318 to manage PCR and antibiogram testing of patient samples using the analyzer 108. In some implementations, the identification module 316 can communicate with the analyzer 108 to initiate a PCR assay to identify a pathogen in a patient sample. In some implementations, the identification module 316 can transmit a notification to the corresponding module in the analyzer 108 (e.g., PCR module 420 in Figure 4), and the notification can cause the analyzer 108 to initiate a PCR to identify the pathogen using the corresponding module. In some implementations, the identification module 316 can transmit a notification to the analyzer 108 to perform PCR after receiving data from the Raman module 310 and / or the EHR module 308 indicating a high probability of sepsis in the patient. In some implementations, the identification module 316 may not transmit a notification to the analyzer 108 to perform PCR unless the probability of sepsis in a given patient, as determined by the Raman module 310 and / or the EHR module 308, is greater than or equal to a predetermined threshold value or within a predetermined range. In some implementations, the identification module 316 can receive results from the analyzer 108 regarding a pathogen identified in the patient, and the identification module 316 can communicate with the antibiogram module 318. In some embodiments, the antibiogram module 318 can receive data on the identified pathogen from the identification module 316, and the antibiogram module 318 can communicate with the analyzer 108 to perform a susceptibility test on the identified pathogen. The antibiogram module 318 can transmit a notification to the corresponding module in the analyzer 108 (e.g., the antibiogram module 424 in Figure 4), and the notification can cause the analyzer 108 to initiate a susceptibility test on the identified pathogen using the corresponding module. In some embodiments, the antibiogram module 318 can receive the results of the susceptibility test from the analyzer 108, where the results can indicate whether the identified pathogen was susceptible or resistant to one or more antimicrobials and / or antibiotics. In some implementations, the antibiogram module 318 can access one or more databases 110 to obtain epidemiological or antibiotic resistance information for the pathogen and generate a treatment recommendation for a patient based on at least one of the susceptibility test results and the epidemiological or antibiotic resistance information for the pathogen. In some implementations, the antibiogram module 318 can also communicate with the EHR module 308 to incorporate a patient's immune profile data or EHR data from the EHR system 104 with the susceptibility test results to determine which antibiotics may be most effective for the patient. In some implementations, a number of antibiotics may be less effective for certain patient populations compared to other patient populations.Therefore, the 318 antibiogram module can take into account the patient's EHR data when generating the treatment recommendation. In other words, the 318 antibiogram module can generate the patient's treatment recommendation based on at least one of the patient's EHR data points, an identification of a probability of infection and / or sepsis in the patient (e.g., as determined by the 308 EHR module and / or the 310 Raman module), the identified pathogen (e.g., received from the 316 identification module and the 108 analyzer), and the antibiotic susceptibility and / or resistance results from the 108 analyzer. Other functional components stored on the computer-readable medium 304 include an operating system 330 for controlling and managing various functions of the processing device 300. The processing device 300 also includes or maintains other functional components and data, such as other modules and data, including programs, drivers, and the like, and data used or generated by the functional components. In addition, the processing device 300 includes many other logical, programmatic, and physical components, of which those described above are merely examples related to the explanations included in this document. The one or more communication interfaces 306 include one or more physical interfaces and components to enable communication with various other devices, including a Raman spectroscopy device 102, an electronic health record (EHR) system 104, an analyzer 108, and multiple databases 110 over a network 112. For example, the one or more communication interfaces 206 facilitate communication via one or more Internet, wired networks, mobile networks, wireless networks (e.g., Wi-Fi, mobile), and wired networks. By way of example, the processing device 300 and other devices communicate and interact with each other using any combination of suitable communication and network protocols, such as the Internet Protocol (IP), Transmission Control Protocol (TCP), Hypertext Transfer Protocol (HTTP), mobile or radio communication protocols, etc.Examples of communication interfaces include a modem, a network interface (such as an Ethernet card), a communications port, a PCMCIA (Personal Computer Memory Card International Association) slot and card, and the like. Analyzing device: Figure 4 illustrates an example diagram of an analyzer 400 in the sepsis detection system according to embodiments of the present description. The analyzer 400 represents an exemplary embodiment of the analyzer 108 of Figure 1B. In some embodiments, the analyzer 400 may be referred to herein as an analyzer device or apparatus. The analyzer 400 may comprise a sample handling unit 410, a PCR module 420, an antibiogram module 424, one or more processors 426, a memory 428, a network interface 430, and input / output (I / O) devices 432. The sample handling unit 410 may include components configured to handle and / or process a sample for analysis using the PCR module 420 and the antibiogram module 424. The sample handling unit 410 may include a sample container 412, a centrifuge 414, a gripper 416, and a waste container 418. The sample container 412 can be used as a holder for a patient sample (e.g., whole blood or plasma). In some embodiments, a user of the analyzer 400 may load at least a portion of a patient sample (e.g., by pipetting) into the sample container 412, and the user may insert the sample container 412 into the analyzer 400 for analysis. In some embodiments, the sample container 412 may be referred to as a consumable or cartridge in this specification.In some embodiments, the 412 sample container may contain multiple wells, allowing for the concurrent analysis of many samples or many antibiotics. In some embodiments, the multiple wells of the 412 sample container are specifically designed to allow the separation of a sample into different wells for PCR and antibiogram analysis using the 420 PCR module and the 424 antibiogram module, respectively. In some embodiments, the 412 sample container may include one or more reagents that interact with the sample when the 412 sample container is inserted into the 400 analyzer. In other embodiments, the 410 sample handling unit in the 400 analyzer includes a reagent container that stores reagents that can be added to the sample in the 412 sample container.In some embodiments, the reagent container may be separate from the sample container 412 and may include materials (e.g., reagents, buffers, etc.) used for PCR and / or antibiogram testing. In some embodiments, the sample container 412 may be a test tube, such as a blood collection tube, a blood collection tube with a vacuum seal inside the tube, or similar. In some embodiments, the sample may be transferred at the beginning of the preparation procedure to a second container, where reagents stored in a reagent container are added or removed during the sample preparation procedure. In some embodiments, each well among the multiple wells of the 412 sample container may be connected to the corresponding reaction chamber among the multiple reaction chambers, providing a site for PCR amplification and detection of nucleic acids in the samples. In some embodiments, the 412 sample container may be constructed with multiple reservoirs, one or more channels for eluate recovery, a spin column for filtration, and / or a septum for necessary liquid transfers. In some embodiments, the 412 sample container may also include a spin-up preparation element for extracting and filtering samples, as well as a molded lid made of a thermoplastic elastomer (TPE) to allow opening and closing of the wells and reaction chambers of the 412 sample container.In some embodiments, some wells of the 412 sample container may include beads for cell lysis or magnetic beads for extracting nucleic acids. In some embodiments, the sample handling unit 410 may incorporate a centrifuge 414 within the analyzer 400. The centrifuge 414 can separate one or more samples in the sample container 412 for sample processing or for isolating nucleic acids for detection. In addition to the centrifuge 414, the sample handling unit 410 may also include a pipetting system (not shown) to enable multifunctional interactions between the sample container 412 and the components of the analyzer 400. In some embodiments, the pipetting system of the sample handling unit 410 can perform the operations necessary for pathogen identification using PCR and growth-based antibiograms via the PCR module 420 and the antibiogram module 424, respectively. The sample handling unit 410 may also contain a gripper 416. The gripper 416 enables the movement of the sample container 412 between different components within the sample handling unit 410, including its movement back and forth between the PCR module 420 and the antibiogram module. In some embodiments, the gripper 416 prevents the sample container 412 from slipping, thus providing a firm grip to hold it securely in place within the various components of the analyzer 400. In addition to the gripper 416, the sample handling unit 410 may include other components that enable the sample container 412 to be moved automatically within the analyzer 400, allowing it to interact with the PCR module 420 and the antibiogram module 420 for analysis. The sample handling unit 412 may also include a waste container 418. The waste container 418 may be configured to hold any liquid waste or unreacted materials resulting from PCR reactions and sensitivity testing of samples. In some embodiments, the sample container 412, centrifuge 414, gripper 418, and waste container 418 may be coupled together to properly handle a sample intended for the PCR module 420 and the antibiogram module 424. In some embodiments, the sample handling unit 412 may be configured to receive a sample from a patient using the sample container 412, and at least a portion of the sample may be processed using at least one of the centrifuge 414 and the waste container 418. The sample container 412 may be handled using the gripper 418.In some embodiments, the operations of the centrifuge 414, the gripper 418, and any other component of the sample handling unit 410 can be controlled by one or more processors 426 in the analyzer 400. In some embodiments, the 400 analyzer may include whole blood collection and sample processing devices that enable the separation of pathogenic cells for clean and sensitive PCR or rapid, direct-to-cell antibiograms from blood. In some embodiments, the 400 analyzer's sample processing devices may utilize antimicrobial neutralization technology to ensure that pathogenic bacteria in a blood sample are not affected by antibiotics that may have been present in a patient's bloodstream, and to prevent adverse effects on the 400 analyzer results. In some embodiments, the 420 PCR module and the 424 antibiogram module may be communicatively coupled to the 410 sample handling unit and may use the same 412 sample container for pathogen detection and susceptibility testing.In some embodiments, the 412 sample container may comprise a tube that is multifunctional, supporting preparation for PCR and growth-based microbiological antibiogram. In some embodiments, the PCR module 420 can perform real-time PCR to identify pathogens directly from a patient blood sample. In some embodiments, the PCR module 420 may include one or more components used to perform the PCR, including a thermocycler configured to control temperatures during PCR, an optical system for collecting data from multiple wells in the sample container 412, reaction modules, and the like. In some embodiments, the PCR module 420 can be configured to receive a patient sample in the sample container 412 from the sample handling unit 410. The PCR module 420 can amplify a nucleic acid within the patient sample using a PCR procedure, detect the amplified nucleic acid (e.g.,The PCR module 420 can detect a nucleic acid product and identify a pathogen present in the patient sample based on the detection of the amplified nucleic acid. In some embodiments, the PCR module 420 can detect a nucleic acid product and identify a pathogen directly from that nucleic acid product. In additional or alternative embodiments, the PCR module 420 can detect a nucleic acid product and identify a transcriptomic product indicative of an infection in a patient, where the transcriptomic product includes RNA. In additional or alternative embodiments, the PCR module 420 can include different areas that are exposed to different cycling conditions, so that several reactions with different cycling conditions can be performed in parallel. After pathogen identification, the PCR module 420 can communicate with the antibiogram module 424, such as by transmitting a command or instruction to perform an antibiogram test. The antibiogram module 424 can be configured to perform susceptibility testing for an identified pathogen. After pathogen identification (e.g., with the PCR module 420 on the analyzer 400 and / or with the processing device 106), the antibiogram module 424 can receive the sample container 412, which contains multiple wells with different concentrations of various antibiotics or antimicrobials to perform different susceptibility tests for the identified pathogen. The 424 antibiogram module can expose pathogen samples to different antibiotics or antimicrobials in each well. The 424 antibiogram module can then process the results from the 412 sample container and determine which antibiotics or antimicrobials the pathogen (e.g., infection in the patient) is sensitive, intermediate, or resistant (S / I / R) to. In some embodiments, the 424 antibiogram module can perform an enrichment step on a sample containing the pathogen before performing an antibiogram analysis. In some embodiments, the 424 antibiogram module can identify a minimum inhibitory concentration (MIC) of an antibiotic that inhibits the growth of a bacterium or pathogen. In some embodiments, the 424 antibiogram module can perform rapid antibiotic susceptibility testing directly from blood using single-cell microscopy and specialized stains.In some embodiments, the 424 antibiogram module can perform antibiotic susceptibility testing of the pathogen by enriching a patient sample with the pathogen, aliquoting the enriched sample among multiple wells in the 412 sample container, and performing susceptibility testing of the patient pathogen using single-cell microscopy. In some embodiments, the 424 antibiogram module may include a microscope configured to perform single-cell microscopy of the sample in the 412 sample container. In some embodiments, by using single-cell microscopy, the 412 antibiogram module may provide a faster result or improve the ability to detect resistance mechanisms by analyzing patterns created by proliferating microorganisms, such as filaments or chains. In some embodiments, the microscope of the 424 antibiogram module may acquire images of individual microorganisms and identify phenotypic resistance of microorganisms (e.g., pathogens) to antibiotics based on the acquired images, leading to a diagnostic pathway for treatment. In some embodiments, the 424 antibiogram module may also use PCR techniques to detect the genotypic resistance information of a pathogen.In some embodiments, the antibiogram procedure of the 424 antibiogram module may include preparing different concentrations of isolated pathogens and / or concentrations of different antibiotics or antimicrobials, enriching and cleaning the sample, performing a phenotypic antibiotic susceptibility test, contacting the pathogens with the antibiotics, and monitoring growth. In some embodiments, the PCR module 420 and the antibiogram module 424 can use a single sample container 412 or different sample containers 412 to perform pathogen identification and antibiogram testing. In some embodiments, the sample container 412 can be manufactured and designed to provide efficient cleaning, concentration separations, cell preparation, cellular debris removal, and the like, for rapid direct blood identification, along with pathogen concentration and viability maintenance for rapid antibiogram testing. The analyzer 400 further includes one or more processors 426. Each processor 426 is a single processing unit or multiple processing units and can include one or more compute units or multiple processing cores.The one or more 426 processors can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operational instructions. For example, the one or more 426 processors can be one or more physical processors and / or logic circuits of any suitable type specifically programmed or configured to execute the algorithms and procedures described herein. The one or more 426 processors can be configured to fetch and execute computer-readable instructions stored in 428 memory, which can program the one or more 426 processors to perform the functions described herein. In some embodiments, memory 428 may represent a computer-readable medium that can include volatile and non-volatile memory, and / or removable and non-removable media implemented in any type of technology for storing information, such as instructions, data structures, program modules, or other computer-readable data. Such computer-readable media include, but are not limited to, RAM, ROM, EEPROM, USB flash drives or other memory technologies, optical storage, solid-state storage, magnetic tape, magnetic disk storage, network-attached storage, storage area networks, cloud storage, or any other medium that can be used to store the desired information and is accessible by a computing device.According to the configuration of the 400 analyzer, the computer-readable medium can be a type of computer-readable storage medium and / or it can be a tangible non-transient medium to the point that when mentioned, the computer-readable non-transient medium excludes media such as energy, carrier signals, electromagnetic waves and signals per se. The computer-readable medium can be used to store any number of functional elements that are executable by the 426 processors. In many implementations, these functional elements comprise instructions or programs that are executable by the processors and that, when executed, specifically configure one or more 426 processors to perform the actions described herein. In addition, the computer-readable medium can store the data used to perform the operations described below in this document. The network interface 430 includes one or more physical interfaces and components that enable communication with other different devices in the sepsis detection system 101, such as the Raman spectroscopy device 102 or 200, the EHR system 104, the processing device 106 or 300, and / or the multiple databases 110 over the network 112. For example, the network interface 430 facilitates communication through one or more of the Internet, wired networks, mobile networks, wireless networks (e.g., Wi-Fi, mobile), and wired networks. In some embodiments, the 400 analyzer and the 106 or 300 processing device communicate and interact with each other using any combination of suitable communication protocols and networks, such as the Internet protocol (IP), the Transmission Control Protocol (TCP), the Hypertext Transfer Protocol (HTTP), mobile or radio communication protocols, etc.Examples of communication interfaces include a modem, a network interface (such as an Ethernet card), a communication port, a PCMCIA slot and card, and the like. The Analyzer 400 may be equipped with various input / output (I / O) devices. These I / O devices may include various user interface controls, such as buttons, joysticks, keyboards, mice, displays, touchscreens, and similar devices, as well as connection ports. Furthermore, the Analyzer 400 may include other components not shown, such as removable storage, a power source (like a battery), and a power control unit. The Analyzer 400 may also include or maintain other functional components and data, such as additional modules and data, including programs, drivers, and similar items, and the data used or generated by the functional components. In addition, the Analyzer 400 may include many other logical, programmatic, and physical components, of which those described above are merely examples relevant to the explanation in this document. Example operating methods: Figure 5 illustrates an example flowchart of a Method 500 for training a learning algorithm to identify sepsis in patients according to the realizations described herein. The steps of Method 500 can be performed using either the Processing Device 106 or 300 in the Sepsis Detection System 101. Method 500 in Figure 5 begins with step 502, where multiple electronic health record (EHR) data points from multiple patients are received from an EHR system. In some implementations, the processing device 300 can receive EHR data for the patients from the EHR system 104. In step 504, multiple Raman spectrum data points are received from a Raman spectrometer. In some implementations, the processing device 300 can receive the Raman spectrum data from the Raman spectroscopy device 102 or 200. In some implementations, each Raman spectrum data point corresponds to a blood sample from the corresponding patient among the multiple patients. In step 506, multiple septic status determinations can be received. In some embodiments, the processing device 300 can receive data regarding septic status determinations from at least one of the one or more databases 110, the EHR system 104, or the Raman spectroscopy device 102, 200. In some embodiments, each septic status determination corresponds to the corresponding patient among the multiple patients. In stage 508, a deep learning algorithm is trained using multiple EHR data points, multiple Raman spectra data points, and multiple sepsis status determinations. In some embodiments, the machine learning algorithm 312 on the processing device 300 can train the learning algorithm 314 to identify a probability of infection or sepsis in future patients based on a classification of each EHR data point and each Raman spectra data point. Figure 6 illustrates an example flowchart of a Method 600 for determining the probability of sepsis in a patient according to the realizations described herein. The steps of Method 600 can be performed using the Processing Device 106 or 300 in the Sepsis Detection System 101. Method 600 in Figure 6 begins with step 602, where a patient's electronic health record (EHR) data is monitored from an EHR system. In some embodiments, the processing device 300 can monitor and / or acquire a patient's EHR data from the EHR system 104. In step 604, one or more patient variables indicative of a change in a patient's condition can be determined based on the monitoring. In step 606, Raman spectrum data from a patient sample can be received from a Raman spectrometer. In some embodiments, the processing device 300 can receive Raman spectrum data from the patient sample from the Raman spectroscopy device 102 or 200. In step 608, a patient's probability of infection and / or sepsis can be identified based on applying a trained learning algorithm to the patient's EHR data, Raman data, and / or variable data. In some embodiments, the processing device 300 can identify a patient's probability of infection and / or sepsis based on applying the trained learning algorithm 314 (e.g., after training with the machine learning device 312) to at least one of the patient's EHR data, Raman spectrum data, and data regarding one or more patient variables. In step 610, a notification indicating the identification results can be generated. In some implementations, the processing device 300 can generate a notification indicating the identification results and can transmit the notification to a device associated with a physician or healthcare worker of the patient. Example computer system: Figure 7 is a block diagram of example components of a 700 computer system. One or more 700 computer systems can be used, for example, to implement any of the embodiments discussed herein, as well as combinations and subcombinations thereof. In some embodiments, one or more 700 computer systems can be used to implement the 500 and 600 methods shown in Figures 5 and 6, respectively, the 106, 300 processing device, the 108, 400 analyzer, the 102, 200 Raman spectroscopy device, and the 104 HCE system shown in Figures 1B and 2-4, as described herein. The 700 computer system may include one or more processors (also called central processing units or CPUs), such as a 704 processor. The 704 processor may be connected to a 706 communication infrastructure or bus. The computer system 700 may also include one or more user input / output interfaces 702, such as monitors, keyboards, pointing devices, etc., which can communicate with the communication infrastructure 706 through one or more user input / output devices 703. One or more of the 704 processors may be a graphics processing unit (GPU). In one embodiment, a GPU is a processor that is a specialized electronic circuit designed to process mathematically intensive applications. The GPU may have a parallel architecture that is efficient for the parallel processing of large blocks of data, such as the mathematically intensive data typical of computer graphics applications, images, videos, etc. The computer system 700 may also include a main or primary memory 708, such as random access memory (RAM). The main memory 708 may include one or more levels of cache. The main memory 708 may contain control logic (i.e., computer programs) and / or data. In some embodiments, the main memory 708 may include optical logic configured to perform sepsis detection, prediction of the probability of sepsis, pathogen identification and sensitivity analysis, and consequently generate recommendations for patient treatment. The computer system 700 may also include one or more secondary storage devices or memory 710. Secondary storage 710 may include, for example, a hard disk 712 and / or a removable storage disk 714. Removable storage disk 714 can interface with removable storage unit 718. Removable storage unit 718 can include a usable or computer-readable storage device that has computer programs (control logic) and / or data stored on it. Removable storage unit 718 can be a cartridge with the program and a cartridge interface (such as those found in video game devices), a removable memory chip (such as an EPROM or PROM) and its associated female connector, a USB memory stick and its USB port, a memory card and its associated memory card slot, and / or any other removable storage device and its associated interface. Removable storage disk 714 can read from and / or write to removable storage unit 718. Secondary memory 710 may include other means, devices, components, instruments, or other strategies to enable the computer system 700 to access computer programs and / or other instructions and / or data. Such means, devices, components, instruments, or other strategies may include, for example, a removable storage unit 722 and an interface 720. Examples of the removable storage unit 722 and interface 720 may include a cartridge containing the program and an interface for the cartridge (such as those found in video game devices), a removable memory chip (such as an EPROM or PROM) and an associated female connector, a USB flash drive and its USB port, a memory card and the associated memory card slot, and / or any other removable storage unit and its associated interface. The computer system 700 may further include a communication or network interface 724. The communication interface 724 may allow a computer system 700 to communicate and interact with any combination of external devices, external networks, external entities, etc. (individually and collectively referred to by reference number 728). For example, the communication interface 724 may allow the computer system 700 to communicate with external or remote devices 728 over the communication path 726, which may be wired and / or wireless (or a combination thereof), and which may include any combination of LAN, WAN, Internet, etc. Control logic and / or data may be transmitted to and from the computer system 700 via the communication path 726.The 700 computer system can also be any of a personal digital assistant (PDA), desktop workstation, laptop, netbook, tablet, smartphone, smartwatch or other wearable technology, household appliance, part of the Internet of Things and / or embedded system, to name a few non-limiting examples, or any combination thereof. The 700 computing system can be a client or server, accessing or hosting any application and / or data through any delivery paradigm, including but not limited to remote or distributed cloud computing solutions; local or on-premises software (on-premises cloud-based solutions); "as a service" models (e.g., content as a service (CaaS), digital content as a service (DCaaS), software as a service (SaaS), managed software as a service (MSaaS), platform as a service (PaaS), desktop as a service (DaaS), framework as a service (FaaS), maintenance as a service (BaaS), mobile maintenance as a service (MBaaS), infrastructure as a service (IaaS), etc.); and / or a hybrid model that includes any combination of the above examples or other services or delivery paradigms. Any data structures, file formats, and schemas applicable in the 700 computer system may be derived from standards including, but not limited to, JavaScript Object Notation (JSON), Extensible Markup Language (XML), Another Plus Markup Language (YAML), Extensible Hypertext Markup Language (XHTML), Wireless Markup Language (WML), MessagePack, XML User Interface Language (XUL), or any other functionally similar representation, alone or in combination. Alternatively, proprietary data structures, formats, or schemas may be used, either exclusively or in combination with known or open standards. In some embodiments, a tangible non-transient apparatus or manufactured article comprising a tangible, non-transient, usable, or computer-readable medium having control logic (computer program) stored therein may also be referred to herein as a computer program-type product or program storage device. This includes, but is not limited to, computer system 700, main memory 708, secondary memory 710, and removable storage units 718 and 722, as well as tangible manufactured articles embodying any combination thereof. Such control logic, when executed by one or more data-processing devices (such as computer system 700), can cause such data-processing devices to operate as described herein. Based on the lessons contained in this description, it will be evident to experts in the relevant techniques how to implement and utilize the realizations of this description using data processing devices, computer systems and / or computer architectures different from those shown in Figure 7. Specifically, the realizations can function with program implementations, equipment and / or operating systems different from those described in this document. The following clauses define aspects and embodiments of the present invention: Clause 1. A system comprising: a first subsystem configured to detect the presence of an infection in a patient; a second subsystem configured to detect the presence of a dysregulated immunological response in the patient; a third subsystem configured to detect organ dysfunction in the patient; and a processing device, wherein the first subsystem, the second subsystem, the third subsystem, and the processing device are communicatively coupled to each other by means of a network, and where the processing device is configured to: Determine the presence of sepsis in the patient based on the presence of infection, the presence of dysregulated host response, and clinical data indicative of organ dysfunction in the patient. Clause 2. The system in accordance with clause 1, wherein the first subsystem determines the presence of infection by at least one, or a combination, of the following means: polymerase chain reaction (PCR) analysis of a patient sample; analysis of spectroscopic data from a patient sample obtained with a Raman spectrometer; analysis of measured data from a pathogen causing the infection in the patient; and / or analysis of data related to a patient's immune response. Clause 3. The system in accordance with any of clauses 1 to 2, wherein the first subsystem is configured to detect infection in the patient and comprises: a polymerase chain reaction (PCR) module configured to perform PCR processing of a first patient sample and detect a nucleic acid-type product; and an identification module configured to identify a pathogen directly from the nucleic acid-like product. Clause 4. The system in accordance with any of clauses 1 to 2, wherein the first subsystem is configured to detect infection in the patient and comprises: a polymerase chain reaction (PCR) module configured to perform the PCR procedure on a first patient sample and detect a nucleic acid-type product; and an identification module configured to identify a transcriptomic product indicative of infection in the patient, wherein the transcriptomic product comprises RNA. Clause 5. The system in accordance with any of clauses 1 to 2, wherein the presence of infection in the first subsystem is determined using spectroscopic data from a first patient sample obtained with a Raman spectrometer. Clause 6. The system in accordance with any of clauses 1 to 2, wherein the presence of the infection is determined by an analysis of measured data from a pathogen causing the infection in the patient. Clause 7. The system in accordance with any of clauses 1 to 2, wherein the presence of the infection is determined by an analysis of data related to a patient's immune response. Clause 8. The system in accordance with any of clauses 1 to 7, wherein the second subsystem determines the presence of the dysregulated host response by at least one, or a combination, of the following means: analysis of spectroscopic data from a patient sample obtained with a Raman spectrometer; and / or polymerase chain reaction (PCR) analysis of a patient sample. Clause 9. The system in accordance with clause 8, wherein the presence of the dysregulated host response in the second subsystem is determined using spectroscopic data from a first patient sample obtained with a Raman spectrometer. Clause 10. The system of agreement of any of clauses 8 to 9, wherein the second subsystem comprises: a Raman spectrometer configured to obtain Raman spectrum data from a first sample from the patient; and a processor configured to analyze Raman spectrum data to identify one or more signals indicative of dysregulated host response. Clause 11. The system in accordance with clause 8, wherein the second subsystem comprises: a polymerase chain reaction (PCR) module configured to perform a PCR procedure on a first patient sample and detect a nucleic acid-type product; and an identification module configured to identify a transcriptomic product indicative of dysregulated host response, wherein the transcriptomic product comprises RNA. Clause 12. The system in accordance with clause 1, wherein the first subsystem determines the presence of the infection by polymerase chain reaction (PCR) analysis of a patient sample and the second subsystem determines the presence of the dysregulated host response by analysis of spectroscopic data from a patient sample obtained with a Raman spectrometer. Clause 13. The system in accordance with any of clauses 1 to 12, wherein the third subsystem is configured to detect organ dysfunction in the patient by at least one, or a combination, of the following means: Collection of clinical data indicative of organ dysfunction in the patient from at least one of the patient's electronic medical records and one or more databases; using spectroscopic data from an initial patient sample obtained with a Raman spectrometer; and / or using a Sequential Organ Failure Assessment (SOFA) score, and wherein at least one or more variables of the SOFA score are determined using spectroscopic data from a first patient sample obtained with a Raman spectrometer. Clause 14. The system in accordance with clause 13, wherein the third subsystem is further configured to: Collect clinical data indicative of organ dysfunction in the patient from at least one of the patient's electronic medical records and one or more databases. Clause 15. The system in accordance with clause 14, wherein the clinical data indicative of organ dysfunction in the patient comprise one or more scores associated with at least one of the Sequential Organ Failure Assessment (SOFA), Rapid SOFA, British Emergency Severity Scale (NEWS), patient vital signs, and patient biomarkers. Clause 16. The system in accordance with clause 13, wherein the organic dysfunction in the third subsystem is determined using spectroscopic data from a first patient sample obtained with a Raman spectrometer. Clause 17. The system in accordance with clause 13, wherein the organic dysfunction in the third subsystem is determined using a combination of clinical data and spectroscopic data from a first sample of the patient obtained with a Raman spectrometer. Clause 18. The system in accordance with clause 13, wherein organ dysfunction in the third subsystem is determined using a Sequential Organ Failure Assessment (SOFA) score, and wherein at least one or more variables of the SOFA score are determined using spectroscopic data from a first patient sample obtained with a Raman spectrometer. Clause 19. A system comprising: a first subsystem configured to detect the presence of an infection in a patient; a second subsystem configured to detect the presence of a dysregulated response occurring in the patient; a third subsystem configured to detect organ dysfunction in the patient; a fourth subsystem configured to detect antibiotic resistance (ARB) of a pathogen in the patient from a sample; and a processing device, wherein the first subsystem, the second subsystem, the third subsystem, the fourth subsystem and the processing device are communicatively coupled to each other through a network; and where the processing device is configured to: Determine the presence of sepsis in the patient based on the presence of infection, the presence of dysregulated host response, and clinical data indicative of organ dysfunction in the patient. Clause 20. The system in accordance with clause 19, wherein the RAB of the pathogen is determined by at least one, or a combination, of the following means: the genotypic information obtained from a PCR that selectively recognizes one or more resistance genes of the pathogen; and / or The phenotypic information obtained using an antibiotic susceptibility analysis module (antibiogram) configured to perform an antibiogram analysis of the pathogen in the patient. Clause 21. The system in accordance with clause 20, wherein the RAB of the pathogen is determined by genotypic information obtained from a PCR that selectively recognizes one or more resistance genes of the pathogen. Clause 22. The system in accordance with clause 20, wherein the RAB of the pathogen is determined by phenotypic information obtained by means of an antibiotic susceptibility analysis module (antibiogram) configured to perform an antibiogram analysis of the pathogen in the patient. Clause 23. The system in accordance with clause 22, wherein the antibiogram module comprises a microscope configured to acquire one or more images of the pathogen, and wherein the pathogen comprises a unicellular microorganism. Clause 24. The system in accordance with clause 22, wherein the first subsystem comprises an identification module configured to identify the pathogen in the patient from the sample, and wherein the processing device is further configured to: receive the data related to the pathogen from the identification module and the results of the antibiogram analysis from the antibiogram module; access one or more databases to obtain epidemiological information or antibiotic resistance information for the pathogen; and Generate a recommendation for patient treatment based on the results of the antibiogram analysis and on epidemiological information or on antibiotic resistance information for the pathogen from one or more databases. Clause 25. The system in accordance with clause 24, wherein the processing device is further configured to: access the patient's electronic health record (EHR) to identify the patient's immune profile; and generate the recommendation for the patient's treatment based also on the patient's immune profile. Clause 26. A system comprising: a first subsystem configured to receive a first sample from the patient; a second subsystem configured to obtain Raman spectrum data from the patient using the first sample; a processing device configured to: acquire one or more patient variables from the electronic health record (EHR) data for the patient; receive the patient's Raman spectrum data from the second subsystem; and classify the patient into an immune profile group by applying a learning algorithm trained on at least one of the EHR data and the Raman spectrum data. Clause 27. The system in accordance with clause 26, wherein one or more patient variables comprises at least one of the following: temperature, heart rate, systolic blood pressure, respiratory rate, white blood cell count, platelet count, ratio of partial pressure of arterial oxygen to fraction of inspired oxygen (PaO2 / FiO2), bilirubin concentration, Glasgow Coma Scale score, mean cardiovascular arterial pressure, creatinine concentration, lactate concentration, C-reactive protein concentration, and procalcitonin concentration. Clause 28. The system in accordance with any of clauses 26 to 27, wherein the processing device is further configured to: to identify a probability of infection and / or sepsis in the patient based on the application of the learning algorithm trained for at least one of the EHR data, the Raman spectrum data and the data relating to one or more patient variables for the patient; and generate a notification indicating the identification results. Clause 29. The system in accordance with clause 28, where the results of the identification indicate a low probability of infection and / or sepsis in the patient, where a probability value is less than a predetermined threshold value. Clause 30. The system in accordance with clause 28, where the results of the identification indicate a high probability of infection and / or sepsis in the patient, where a probability value is greater than or equal to a predetermined threshold value. Clause 31. The system in accordance with clause 28, wherein the processing device is further configured to: generate a recommendation for patient treatment based on the results of the identification, wherein the treatment recommendation is based on the antibiotic sensitivity analysis (antibiogram) of a patient sample. The realizations described herein have been illustrated above using functional building blocks that demonstrate the implementation of specific functions and their relationships. The boundaries of these functional building blocks have been arbitrarily defined in this document for ease of description. Alternative boundaries may be defined as long as the specific functions and their relationships are implemented appropriately. The foregoing description of the specific embodiments fully reveals the general nature of the invention, which others, applying their knowledge within the scope of their artistic expertise, can readily modify and / or adapt for other applications without experimentation and without departing from the general concept of the present description. Therefore, it is intended that such adaptations and modifications fall within the meaning and range of equivalents of the described embodiments, based on the teachings and guidance presented herein. It should be understood that the phraseology or terminology in this specification is for descriptive, not limiting, purposes, and that the terminology or phraseology of this specification should be interpreted by a person skilled in the art in light of the teachings and guidance provided. The breadth and scope of the present description shall not be limited by any of the exemplary embodiments described above, but shall be defined only in accordance with the following claims and their equivalents.

Claims

1. A system comprising: a first subsystem configured to receive a first sample from the patient; a second subsystem configured to obtain patient Raman spectrum data from the first sample; a processing device configured to: acquire one or more patient variables from the patient's electronic health record (EHR) data; receive the patient's Raman spectrum data from the second subsystem; and classify the patient into an immune profile group by applying a machine learning algorithm trained on at least one of the EHR data and the Raman spectrum data. 2.The system according to claim 1, wherein one or more patient variables comprises at least one of the following: temperature, heart rate, systolic blood pressure, respiratory rate, white blood cell count, platelet count, ratio of partial pressure of arterial oxygen to fraction of inspired oxygen (PaO2 / FiO2), bilirubin concentration, Glasgow Coma Scale score, mean cardiovascular arterial pressure, creatinine concentration, lactate concentration, C-reactive protein concentration, and procalcitonin concentration. 3.The system according to any one of claims 1 to 2, wherein the processing device is further configured to: identify a probability of infection and / or sepsis in the patient based on the application of the machine learning algorithm trained on at least one of the EHR data, Raman spectrum data, and data relating to one or more patient variables for the patient; and generate a notification indicating the identification results.

4. The system according to claim 3, wherein the identification results indicate a low probability of infection and / or sepsis in the patient, wherein a probability value is less than a predetermined threshold value.

5. The system according to claim 3, wherein the identification results indicate a high probability of infection and / or sepsis in the patient, wherein a probability value is greater than or equal to a predetermined threshold value.

6. The system according to claim 3, wherein the processing device is further configured to: generate a recommendation for patient treatment based on the identification results, wherein the treatment recommendation is based on the antibiotic sensitivity analysis (antibiogram) of a patient sample.

Images