Systems and methods for patient test matching - Patents.com

Abstract

A computer-implemented system for determining tests using a patient's metastatic status can include at least one processor programmed to: receive a selection of a patient; in response to the patient's selection, access a patient dataset associated with the patient; receive a predicted metastatic state associated with the patient; display at least a first portion of the patient dataset and the predicted metastatic state; determine a subset of tests for the patient based on at least a second portion of the patient dataset or the predicted metastatic state, where the subset of tests for the patient is determined from a plurality of tests; and display at least the subset of tests for the patient.

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 851,870, filed May 23, 2019, the entire contents of which are incorporated herein by reference. [Background technology]

[0002] Technical Field The present disclosure relates to systems and methods for determining a test using a patient's metastatic status.

[0003] Background matters Cancer research organizations are continually faced with the challenge of identifying patients who are eligible for clinical trials. There are often many barriers that can prevent patients from participating in clinical trials. Identifying patients at exactly the right time, for example, when they are ready to receive treatment at any time but have not yet started, is often difficult when dozens of trials may be open in a clinic, each with dozens or more of inclusion and / or exclusion criteria, and hundreds of patients are seen in a single day. Further complicating the process is the fact that a patient's metastatic status may change dramatically from day to day, and this change may only be recorded in the physician's handwritten notes. This may lead to patients with ineligible metastatic status receiving trials for which they are not eligible, causing confusion in the outcome of the trials. Therefore, to overcome these challenges faced by existing systems, it is desirable to more efficiently identify patients who are eligible for clinical trials, and trials that are eligible for patients, based on their metastatic status. Furthermore, it is desirable to predict a patient's metastatic status to accurately and efficiently coordinate the matching of patients to trials. Summary of the Invention

[0004] The embodiments of the present disclosure include a system and method for determining test using patient's metastatic status.The embodiments of the present disclosure can overcome one or more aspects of existing technology for determining test based on computer-generated algorithm according to metastatic status.Therefore, the use of computer-generated algorithm according to the embodiments of the present disclosure allows for a faster and more efficient way to provide patients, physicians, and researchers with reliable suggestions about the eligible tests that may benefit patients.

[0005] In one embodiment, a device for determining tests using a patient's metastatic status may include at least one processor programmed to: receive a selection of a patient; in response to the patient selection, access a patient dataset associated with the patient; receive a predicted metastatic state associated with the patient; cause at least a first portion of the patient dataset and the predicted metastatic state to be displayed; determine a subset of tests for the patient based on at least a second portion of the patient dataset or the predicted metastatic state, where the subset of tests for the patient is determined from a plurality of tests; and cause the display of at least the subset of tests for the patient.

[0006] In one embodiment, a method for determining tests using a patient's metastatic status may include receiving a selection of a patient, and in response to the patient selection, accessing a patient dataset associated with the patient, receiving a predicted metastatic state associated with the patient, causing at least a first portion of the patient dataset and the predicted metastatic state to be displayed, and determining a subset of tests for the patient based on at least a second portion of the patient dataset or the predicted metastatic state, where the subset of tests for the patient is determined from a plurality of tests, and causing at least the subset of tests for the patient to be displayed.

[0007] In one embodiment, a non-transitory computer readable medium can include instructions that, when executed by one or more processors, cause the one or more processors to receive a selection of a patient; in response to the patient selection, access a patient dataset associated with the patient; receive a predicted metastatic state associated with the patient; display at least a first portion of the patient dataset and the predicted metastatic state; determine a subset of tests for the patient based on at least a second portion of the patient dataset or the predicted metastatic state, where the subset of tests for the patient is determined from a plurality of tests; and display at least the subset of tests for the patient. [Brief description of the drawings]

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments and, together with the description, serve to explain the principles thereof.

[0009] [Figure 1A] FIG. 1 is a block diagram illustrating an exemplary system for providing one or more proposed patients for a trial according to the present disclosure. [Figure 1B] FIG. 1 is a block diagram illustrating an example computing device for providing one or more suggested patients for a trial according to the present disclosure. [Diagram 2] 1 is a diagram illustrating an exemplary user interface for viewing a test according to the present disclosure. [Diagram 3] 1 is a diagram illustrating an exemplary user interface for receiving user input for creating a new test according to the present disclosure. [Figure 4A-4B] 1 is a diagram illustrating an example expression tree structure for one or more proposed patients for a trial according to the present disclosure. [Diagram 5]1 is a diagram illustrating an example expression tree structure for one or more proposed patients for a trial according to the present disclosure. [Figure 6] 1 is a diagram illustrating an example neural network for providing one or more suggested patients for a trial according to the present disclosure. [Figure 7] 1 is a diagram illustrating an exemplary user interface for providing one or more suggested tests to a patient according to the present disclosure. [Figure 8A-8B] 1 is a diagram illustrating an exemplary user interface for providing patient and proposed test information according to the present disclosure. [Fig. 8C-8E] 1 is a diagram illustrating an exemplary user interface for providing management of a metastatic condition. [Figure 9] 1 is a flowchart illustrating an exemplary process for providing one or more proposed patients for a trial according to the present disclosure. [Figure 10] 1 is a flow chart illustrating an exemplary process for updating a transition state. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. Although some exemplary embodiments are described herein, modifications, variations, and other implementations are possible. For example, substitutions, additions, or modifications can be made to the components illustrated in the drawings, and the exemplary methods described herein can be modified by substituting, rearranging, deleting, or adding steps of the disclosed methods. Therefore, the following detailed description is not limited to the disclosed embodiments and examples. On the contrary, its appropriate scope is defined by the appended claims.

[0011] The embodiments herein include computer-implemented methods, tangible non-transitory computer-readable media, and systems. The computer-implemented methods can be executed, for example, by at least one processor (e.g., processing device) receiving instructions from a non-transitory computer-readable storage medium. Similarly, a system according to the present disclosure can include at least one processor (e.g., processing device) and a memory, which can be a non-transitory computer-readable storage medium. As used herein, a non-transitory computer-readable storage medium refers to any type of physical memory that can store information or data that can be read by at least one processor. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, non-volatile memory, hard drives, CD-ROMs, DVDs, flash drives, disks, and any other known physical storage medium. Singular terms such as "memory" and "computer-readable storage medium" may further refer to multiple structures such as multiple memories and / or computer-readable storage media. As referred to herein, "memory" may include any type of computer-readable storage medium unless otherwise specified. A computer-readable storage medium can store instructions for execution by at least one processor, including instructions for causing the processor to perform steps or stages according to the embodiments herein. Furthermore, one or more computer-readable storage media can be utilized in performing a computer-implemented method. It should be understood that the term "computer-readable storage medium" encompasses tangible articles and excludes carrier waves and ephemeral signals.

[0012] In this disclosure, a system for one or more tests is disclosed.

[0013] FIG 1A illustrates an exemplary system 100 for implementing embodiments according to the present disclosure, which will be described in detail below. As shown in FIG 1A, the system 100 can include one or more client devices 101, computing devices 102, databases 103, and networks 104. It will be understood from this disclosure that the number and arrangement of these components are illustrated and provided for purposes of explanation. Other arrangements and numbers of components can be used without departing from the teachings and embodiments of the present disclosure.

[0014] The client device 101 (e.g., client devices 101-1, 101-2, 101-3) can be configured to receive user input from a user to create a new trial. For example, the client device 101 can reside at a clinic, and a user (e.g., a doctor or administrator) can enter information to create a new trial schedule at an input device (e.g., input device 153) of the client device 101. The client device 101 can include a processor, memory, input devices, output devices, or other computing components. For example, the client device 101 can have components that correspond to components of the computing device 102. As an example, a user can enter an identification number (e.g., a National Clinical Trials (NCT) number or a ClinicalTrials.gov identifier) ​​at an interface of the client device 101 to create a new trial, and the client device 101 can transmit the identification number to the computing device 102. The computing device 102 can create a trial schedule for the new trial based on the identification number. Client device 101 can also receive and present information received from computing device 102. For example, client device 101 can receive information about patients proposed for one or more tests from computing device 102 and present that information to a user in an interface of client device 101. In some embodiments, client devices 101-1, 101-2, and 101-3 can be at the same site or at different sites.

[0015] The computing device 102 can be configured to receive information from the client device 101 to create a new trial specification from the client device 101. The computing device 102 can also create the trial specification based on the information received from the computing device 102. The trial information received by the computing device 102 can include at least a portion of the trial eligibility criteria associated with the trial, such as a metastatic status eligibility restriction. The computing device 102 can also create a new trial specification for the trial based on the trial information. The trial specification can include one or more trial eligibility criteria for determining whether a patient is eligible for the trial. For example, the trial eligibility criteria may include a metastatic status restriction that an eligible patient must have a verified metastatic status. The computing device 102 can further automatically generate an algorithm for suggesting one or more eligible patients for the new trial based on the trial eligibility criteria. For example, the computing device 102 can automatically generate an algorithm that represents an expression tree (e.g., the expression tree structures 401, 402 illustrated in FIG. 4A and FIG. 4B) based on the study eligibility criteria, where the nodes and / or leaves of the expression tree can represent the study eligibility criteria. In some embodiments, the strength of eligibility can be determined, and the strength can be based on the degree to which the patient matches the set of criteria. For example, a patient matching 90% of the set of criteria can have a higher strength of eligibility than a patient matching 50% of the set of criteria. As another example, a patient with a metastatic condition verified to be “metastatic” can have a higher strength of eligibility than a patient with only a predicted metastatic condition for a study with an eligibility restriction of “metastatic” condition. In some embodiments, the strength of eligibility can be stored and / or transmitted by the client device 101, the computing device 102, and / or any other device suitable for managing patient data.In some embodiments, the strength of eligibility may be judged against criteria designated as preferred, but not against criteria designated as absolute limitations on eligibility.

[0016] The computing device 102 may also be configured to retrieve electronic medical records associated with multiple patients to determine whether one or more patients may be eligible for the new trial based on the algorithm and the electronic medical records. For example, the computing device 102 may retrieve electronic medical records associated with patients of the clinic L222 (e.g., the clinic associated with the client device 101). For example, the client device 101 and / or the computing device 102 may be configured to receive and / or process input information for the model. For example, the client device 101 may include or be connected to a scanning device, which may scan documents (e.g., documents including unstructured data) associated with the patient. For example, the scanning device (e.g., a portable document scanner) may scan handwritten notes from a doctor and convert the notes into an image or other data entity (e.g., structured data). The computing device 102 may determine one or more patients among the patients in the clinic who may be eligible for the new trial based on the algorithm and the electronic medical records (e.g., structured or unstructured data). As an example, the computing device 102 can create named tuples having a number and a series of letters for each of the patients based on the electronic medical records (e.g., age, disease, biomarkers). The computing device 102 can evaluate the created named tuples associated with the patients against an expression tree, which can return a number indicating the eligibility of each of the patients. For example, the expression tree algorithm can output a "0" for ineligible or a "1" for eligible. Alternatively, the algorithm can output a probability value indicating the eligibility of each of the patients.

[0017] The computing device 102 can be further configured to output one or more proposed eligible patients for the new trial. For example, the computing device 102 can output the one or more proposed patients to an output device (e.g., a display, a printer). Alternatively, or in addition, the computing device 102 can transmit instructions to cause the client device 101 to display information representing the one or more proposed patients, which the client device can present to a user.

[0018] In some embodiments, the computing device 102 can be configured to provide one or more suggested tests to the patient. For example, a user can select a patient via an input device of the client device 101 (or computing device 102), and the computing device 102 can provide one or more tests for which the patient may be eligible based on one or more patient-test matching algorithms and the electronic medical record associated with the patient.

[0019] In some embodiments, the client device 101 and the computing device 102 may be integrated into one device configured to perform the functions of the client device 101 and the computing device 102 disclosed in this application. For example, a user may input information for creating a new study via an input device 153 of the computing device 102, which may display one or more suggested patients for the new study via an output device (e.g., output device 154, discussed below).

[0020] The database 103 can be configured to store information and data for one or more components of the system 100. For example, the database 103 can store electronic medical records associated with one or more patients. The database 103 can also store information regarding one or more trials. For example, the database 103 can store trial eligibility criteria associated with each of the trials, such as metastatic status criteria. In some embodiments, the database 103 can also store one or more proposed eligible patients for a trial, and / or a patient-trial matching algorithm for determining one or more proposed eligible trials for a patient. The client device 101 and / or the computing device 102 can be configured to access and retrieve data stored on the database 103 via the network 104. In some embodiments, the database 103 may be operated by a third party. For example, the computing device 102 can request information regarding a particular trial from the database 103, which can transmit the requested information to the computing device 102. As an example, the computing device 102 can request information for a trial by sending a trial identifier (e.g., an NCT number) to the database 103, which can send the requested information (e.g., trial eligibility criteria) to the computing device 102.

[0021] The network 104 may be configured to facilitate communication between the components of the system 100. The network 104 may include a local area network (LAN), a wide area network (WAN), a portion of the Internet, an intranet, a cellular network, a short-range network (e.g., a Bluetooth-based network), etc., or a combination thereof.

[0022] 1B is a block diagram illustrating an example computing device 102. Computing device 102 can include at least one processor (e.g., processor 151), memory 152, input devices 153, output devices 154, and a database 160.

[0023] The processor 151 can be configured to perform one or more functions described in this application. The computing device 102 can also include a memory 152 that can store instructions for various components of the computing device 102. For example, the memory 152 can store instructions that, when executed by the processor 151, can be configured to cause the processor 151 to perform one or more functions described herein.

[0024] The input device 153 can be configured to receive input from a user of the computing device 102, and one or more components of the computing device 102 can perform one or more functions in response to the received input. In some embodiments, the input device 153 can include a touch screen, a keyboard, a microphone, a speaker, a haptic device, a camera, a button, a dial, a switch, a knob, a touch pad, a button, a microphone, a position sensor, an accelerometer, a camera, a fingerprint scanner, a retina scanner, a biometric input device, an ultrasound scanner, a transceiver, an input device, an output device, or other input device for performing the methods of the disclosed embodiments. For example, the input device 153 can include an interface displayed on a touch screen (e.g., the output device 154). The output device 154 can be configured to output information and / or data to a user. For example, the output device 154 can include a display configured to display one or more suggested patients for the trial. In some embodiments, the output device 154 can include a touch screen.

[0025] The database 160 can be configured to store various data and information of one or more components of the computing device 102. For example, the database 160 can include a study database 161, a model database 162, and an electronic medical record (EMR) database 163. The study database 161 can be configured to store information about one or more studies. For example, the study database 161 can store a study specification for each of the studies, which can include study eligibility criteria for the study. The study eligibility criteria for the study can include study status, study disease, study treatment line, eligibility age, study biomarker criteria, predicted metastatic state criteria, verified metastatic state criteria, and the like, or a combination thereof. In some embodiments, the study specification can also include study name, study content, and the like, or a combination thereof. The study database 161 can further store an edit history including changes made to the study. The computing device 102 can retrieve information about the study from the study database 161 and modify the information, if necessary. For example, the computing device 102 may create a test specification for a new test and store the test specification in the test database 161 .

[0026] The model database 162 may store a patient-study matching model or algorithm. A patient-study matching algorithm refers to an algorithm for determining one or more eligible patients for a study and / or for determining one or more proposed eligible studies for a patient. The computing device 102 may obtain the algorithm from the model database 162. In some embodiments, the computing device 102 may create an algorithm for a new study and store the created algorithm in the model database 162. The EMR database 163 may store electronic medical records associated with a patient. The processor 151 may receive one or more electronic medical records from the EMR database 163.

[0027] 2 is a diagram illustrating an example user interface 200 for viewing tests according to the present disclosure. The user interface 200 can be displayed via the output device 154 (e.g., a display or a touch screen) of the computing device 102. Alternatively, or in addition, the computing device 102 can send instructions to the client device 101 via the output device (e.g., a display or a touch screen) of the client device 101 to display the user interface 200. The computing device 102 can retrieve test data from a database (e.g., database 103, database 160) and render the user interface 200 based on the retrieved test data.

[0028] The user interface 200 can include a study list 201. The study list 201 can include study name, study content, study status, study disease, study treatment schedule, etc., or combinations thereof. The user interface 200 can also include one or more filters, such as filters by study name, study content, study status, study disease, study treatment schedule, etc., or combinations thereof. In some embodiments, for each study, the user interface 200 can display an edit history, which can include changes made to the study information by the user at the clinic. Thus, a user can access one place to see all clinical trials across their practice, the study status, and the diseases and treatment schedules for which the studies are recruiting. This can help the user understand where there may be gaps in the user's study schedule and where the user may need to publish another study.

[0029] The user interface 200 may also include at least one filter 202 (several are shown), which may be interacted with by a user to filter the studies in the study list 201. For example, a user may enter a search term into the filter 202, and studies associated with the search term (e.g., studies that include study data) will be displayed in the study list 201. As another example, the filter 202 may include a drop-down menu that may enable a user to select a particular study status, disease, treatment schedule, metastatic status, etc.

[0030] The user interface 200 may also include a study classification data element 203, which may indicate any of the study name, study description, study recruitment status, disease, treatment timeline, metastatic status, etc. that may be associated with a particular study. In some embodiments, the study classification data element 203 may be selectable by a user for further configuration. For example, selecting the study classification data element 203 may cause an interface similar to the user interface 300 to be displayed. In some embodiments, only users with appropriate permissions may modify the study data (e.g., users logged into an authorized account on the client device 101 or computing device 102).

[0031] The user interface 204 may also include classification indicators 204, which may correspond to particular types of test classification data elements 203 and may be interactable by a user. In some embodiments, the classification indicators may filter, unfilter, and / or sort the displayed test information when selected by the user. In some embodiments, user input on a classification indicator may remove the classification data element 203 corresponding to that classification indicator from the user interface 204.

[0032] The user interface 200 may also include a button 205 for adding a new test. For example, a user may click or select the button 205 (e.g., using a data entry device or via selection on a touch screen) and the computing device 102 may render another user interface for the user to enter information about the new test.

[0033] 3 is a diagram illustrating an example user interface 300 for receiving user input for creating a new test according to the present disclosure. The user interface 300 can be displayed via the output device 154 (e.g., a display or touch screen) of the computing device 102, and a user can input information via the input device 153. Alternatively, or in addition, the computing device 102 can send instructions to the client device 101 for displaying the user interface 300 via the output device (e.g., a display or touch screen) of the client device 101 and for receiving user input via the input device of the client device 101.

[0034] The user interface 300 may include one or more input areas (e.g., fields) for a user to enter and add a new study. For example, the user may enter a study identification number. The computing device 102 may also retrieve or generate a study based on the study identification number. As an example, the user may enter an NCT number, and the computing device 102 may retrieve study information from a database or a third party (e.g., clinicaltrials.gov) based on the received NCT number, including, for example, study name, investigational drug, sponsor, type of study, study description, diagnosis, biomarker criteria, treatment schedule, and the like, or a combination thereof. The computing device 102 may also load the information retrieved in the user interface 300 accordingly (e.g., automatically). In some embodiments, the user may manually enter at least a portion of the study information. For example, if the NCT number is unavailable, the user may check a box to indicate that it is unavailable. The user interface 300 may prompt the user to manually complete these input areas.

[0035] In some embodiments, the trial information can include site information that identifies where the new trial will be conducted. For example, a user can enter site information that can help medical clinics oversee operations at their clinics and receive reports on their trial performance. Operational data fields can include site ID, investigator, trial status, enrollment start date, enrollment close date, Institutional Review Board (IRB) approval date, site start visit date, contract implementation date, number of days for data entry, enrollment goal (e.g., number of patients), links to external sources, and the like, or combinations thereof.

[0036] The computing device 102 can create a trial specification for a new trial and store the trial information in the database 103 and / or database 160. The trial specification may include the trial eligibility criteria for the trial (e.g., metastatic status). A potential advantage of this approach may be that a user of the system (e.g., administrator, physician, clinical research coordinator) can determine eligible patients at a clinic (e.g., clinical site) against the eligibility criteria. Additionally, the system can provide its user with operational reports regarding trials and patients. This approach can significantly reduce the number of patients a user needs to screen for potential trial eligibility, thereby improving trial recruitment at the clinic, as the user spends more time screening likely eligible patients.

[0037] The computing device 102 can be configured to determine one or more proposed eligible patients for a new study. For example, the computing device 102 can create a patient-study matching algorithm to determine one or more patients eligible for a new study based on the study eligibility criteria of the study. The computing device 102 can also retrieve electronic medical records associated with the multiple patients. For example, the computing device 102 can retrieve electronic medical records associated with the patients from a database (e.g., database 103, database 160) at the client device 101 and / or one or more clinical sites where the computing device 102 operates. The computing device 102 can further determine one or more patients eligible for the study based on the electronic medical records and the algorithm.

[0038] By way of example only, study eligibility criteria for an exemplary study may include the following criteria: 1. Is the patient over 18 years of age? If yes, go to step 2. If no, the patient is ineligible. 2. Does the patient have breast cancer? If yes, go to step 3. If no, go to step 4. 3. Is the patient estrogen receptor negative (ER-) and progesterone receptor negative (PR-)? If yes, the patient is eligible. If no, the patient is ineligible. 4. Does the patient have colorectal cancer? If yes, go to step 5. If no, the patient is ineligible. 5. Does the patient have a genetic Kirsten rat sarcoma viral oncogene homolog (KRAS) mutation? If yes, the patient is eligible. If no, the patient is ineligible.

[0039] The above study eligibility criteria can be expressed using Boolean operators as follows:

[0040] (age>18) AND (ER=negative AND PR=negative AND disease=breast) OR (KRAS=positive AND disease=colorectal). This can be represented as an example expression tree 401 shown in FIG. 4A.

[0041] As shown in FIG. 4A, the expression tree 401 can include operators 411, 412, 413, and 414, and criteria elements 421, 422, 423, 424, 425, and 426. For example, element 412 can represent that the patient must be over 18 years old. As another example, operators 413 and 414 and elements 422-426 represent that the patient must either (1) be ER-negative and PR-negative and have breast cancer, or (2) have colorectal cancer and KRAS-positive. As the computing device 102 evaluates each node, the computing device 102 can elevate the result to the node above the node to obtain a result of whether the patient is eligible for the test. For example, for a patient who has breast cancer and is ER- and PR-, but does not have colorectal cancer and is not tested KRAS+, the patient may be eligible for the test because of the left subtree of the expression tree 401.

[0042] In some embodiments, each leaf node in the expression tree represents a single inclusion or exclusion criterion. These nodes (and their criteria) can be mixed and matched to different trees to form criteria for different studies. Each leaf node can be responsible for determining whether a patient is eligible, for example taking the patient's clinical information as its input and returning values ​​as output that may affect eligibility. Using expression trees, the system can allow the user to visualize the study matching criteria and can query various data sources (e.g., the patient's electronic medical record) through a unified interface.

[0043] In some embodiments, the computing device 102 can be configured to receive updated patient eligibility criteria for a study. The computing device 102 can also update a patient-study matching algorithm based on the updated patient eligibility criteria to determine at least one new proposed patient for the updated new study based on the updated patient-study matching algorithm and the electronic patient medical record. For example, a user can update the study eligibility criteria for a study, and the computing device 102 can automatically update the expression tree and the patient-study matching algorithm. As another example, the computing device 102 can receive updated study eligibility criteria from an external database and automatically update the algorithm for the study based on the updated study eligibility criteria. As an example, the computing device 102 can receive user input from a user to delete a KRAS criterion. The computing device 102 can update the expression tree 401 by removing a leaf node 426 of the expression tree 402, as shown in FIG. 4B. Similarly, if a user adds a new criterion, the computing device 102 can insert a new leaf node into the expression tree in the appropriate location. Alternatively, or in addition, the computing device 102 may modify the leaf nodes based on input from a user or the system.

[0044] 5 is a diagram illustrating an exemplary (simplified) expression tree structure according to the present disclosure. FIG. 5 provides an example to further illustrate the expression tree and algorithm. The expression tree 500 can represent study eligibility criteria including: (A, B, C only) AND (<1000) AND (A only OR <50).

[0045] Expression tree 500 can include operator nodes 511 and 512, which are two operator classes (AND and OR). The operator classes can include child classes that are added as leaf classes (e.g., leaves 521, 522, 523, and 524).

[0046] The computing device 102 can automatically generate an algorithm to represent the expression tree 500 based on the test eligibility criteria. Exemplary code for the algorithm is provided below: class OrMatchOperator(): def init(self): self.children=[] def match(self,patient): prob_no_match=1.0 for child in self.children: prob_no_match*=float(1-child.match(patient)) return1 - prob_no_match class AndMatchOperator(): def init(self): self.children=[] def match(self,patient): prob_match=1.0 for child in self.children: prob_match*=float(child.match(patient)) return prob_match #Mock leaf node that checks if MockClass has only certain characters #Attribute class LetterMatchLeaf() in that 'letter': def init(self,allowable_letters): self.allowable_letters=allowable_letters def match(self,patient): if set(patient.letters)-set(self.allowable_letters): return 0 return 1 #Mock leaf node that checks if MockClass has a number #max_number class less than NumberMatchLeaf(): def init(self,max_number): self.max_number=max_number def match(self,patient): return int(patient.number<=self.max_number) from collections import namedtuple MockClass=namedtuple('MockClass',['number','letters']) tree=AndMatchOperator() tree.children.append(LetterMatchLeaf(['A','B','C']))tree.children.append(NumberMatchLeaf(1000)) subtree=OrMatchOperator() subtree.children.append(NumberMatchLeaf(50))subtree.children.append(LetterMatchLeaf(['A'])) tree.children.append(subtree) print('Match!(50,[C])')print(tree.match(MockClass(50,['C'])))print('Match!(50,[A])')print(tree.match(MockClass(55,['A'])))) print('Fits neither attribute in the subtree.No match.(50, [C])') print(tree.match(MockClass(55,['C']))) print('Number is too big for the top-level number constraint.No match.(1005, [A])') print(tree.match(MockClass(1005,['A'])))

[0047] The above example code can represent an expression tree 500 that includes the study eligibility criteria. The computing device 102 can also generate a MockClass for each of the patients, which can be a named tuple with a number and a set of letters. For example, the computing device 102 can create a named tuple based on an electronic medical record associated with the patient. The codes also include a leaf class, LetterMatchLeaf, that can only allow a certain subset of letters, and another leaf class, NumberMatchLeaf, that can only allow numbers below a certain number. Those skilled in the art will appreciate that these classes are for illustrative purposes only, and other types of classes can be used for the algorithm. For example, the algorithm can include a leaf class, DiseaseMatchLeaf, for disease matching, and a leaf class, BiomarkerMatchLeaf, for biomarker matching.

[0048] The computing device 102 can use an algorithm to evaluate different MockClass objects (i.e., patients) against the expression tree 500, which can return a 1 (eligible) or a 0 (not eligible). In some embodiments, the patient-study matching algorithm can output a probability, and the computing device 102 can determine whether the patient is eligible for the study based on that probability (e.g., a probability above a certain threshold).

[0049] In some embodiments, the computing device 102 can obtain or generate a machine learning algorithm for determining one or more proposed eligible patients for a study based on the study eligibility criteria. For example, the computing device 102 can access a neural network to determine one or more proposed eligible patients for a study.

[0050] FIG. 6 illustrates an exemplary neural network 600. The neural network 600 may include an input layer, one or more hidden layers, and an output layer. Each of the layers may include one or more nodes. In some embodiments, the output layer may include one node. Alternatively, the output layer may include multiple nodes, each of which may output data. The input layer may be configured to receive an input (e.g., an electronic medical record associated with a patient). In some embodiments, every node in one layer is connected to every other node in the next layer. A node may take a weighted sum of its inputs and pass the weighted sum to a nonlinear activation function, the results of which may be output as an input for another node in the next layer. The data may flow from left to right, and a final output may be calculated at the output layer based on the calculations of all the nodes. The neural network 600 may output a probability indicating the patient's eligibility for the trial, which may be based on information from the received inputs.

[0051] In some embodiments, the computing device 102 can determine patient-study matches between a plurality of patients and a plurality of studies based on a patient-study matching algorithm associated with the patient's studies and electronic medical records. For example, the computing device 102 can determine one or more proposed eligible patients for each of the studies, and / or one or more proposed eligible studies for each of the patients. The computing device 102 can also generate a data structure representing the relationship between the patients and studies and store the data structure in a database (e.g., database 103, database 160). The computing device 102 can further present the data representing the relationship between the patients and studies to a user. For example, the computing device 102 can be configured to generate a patient-study matching report. As an example, the computing device 102 can receive user input to define filters for data to appear on the report, including, for example, patient information (e.g., gender, age, location, patient schedule, diagnosis, biomarkers, predicted metastatic status, verified metastatic status, etc., or combinations thereof), treatment information (e.g., treatment, included and / or excluded drugs), and study information (study name, investigational drug, sponsor, type of trial, trial description, diagnosis, biomarker criteria, treatment timeline, etc., or combinations thereof). The computing device 102 can compile patients and / or studies that match the filtered data into a report.

[0052] 7 is a diagram illustrating an exemplary user interface for providing one or more proposed tests to a patient according to the present disclosure. The user interface 700 may be displayed via the output device 154 (e.g., a display or touch screen) of the computing device 102, and a user may input information via the input device 153. Alternatively, or in addition, the computing device 102 may send instructions to the client device 101 to display the user interface 700 via the output device (e.g., a display or touch screen) of the client device 101 and to receive user input via the input device of the client device 101.

[0053] A user can select a patient's schedule, and the computing device 102 can access the patient's schedule to determine which patients are scheduled for visits according to the patient's schedule. For example, a user can select a date (e.g., November 8, 2018 shown in FIG. 700), and the computing device 102 can access the patient's schedule to determine which patients are scheduled for visits on that day. Alternatively, or in addition, a user can view a patient's schedule for a period of time (e.g., a week, a month). The computing device 102 can also provide a user with an interface showing information about the patient and the visit. For example, as shown in FIG. 7, the user interface 700 can include the patient's name, diagnosis, type of visit (e.g., outpatient, treatment), the doctor the patient is visiting, location of the visit, etc., or a combination thereof.

[0054] The computing device 102 may further determine one or more proposed tests for the patient based on algorithms associated with the tests and the patient's electronic medical record, as described elsewhere in this disclosure. The computing device 102 may also present a user interface 700 to the user, including a list of proposed tests for the patient. As shown in FIG. 7, the user interface 700 may include a patient list 701, which may include information for each patient, such as the patient's name, diagnosis, type of visit, tests, patient status, etc., or a combination thereof. The user interface 700 may also include a filter 702 configured to receive a user's input to filter patients and / or tests, for example, according to physician, location, patient diagnosis, type of visit, tests, patient status, etc., or a combination thereof. By presenting proposed tests for patients who are scheduled to visit, patient-study matching may be directly tied to the clinic's (e.g., clinical) patient schedule, such that a user of the system may identify eligible patients who are visiting the clinic at a particular date and time and schedule meetings with these patients to discuss potential opportunities to participate in the tests. This may improve patient recruitment. For example, the computing device 102 can provide the user with one or more suggested eligible patients scheduled to visit the clinic at a particular date and time. As another example, the user can filter the studies and / or patients according to disease, type of study, etc., or a combination thereof. The computing device 102 can notify the physician and / or clinical trial coordinator to discuss with the patient the studies in which the patient may be eligible to participate. For example, the computing device 102 can include the study information in the patient's medical record so that the physician can remember when to discuss with the patient.

[0055] In some embodiments, the user interface 700 may display a patient schedule including at least one proposed patient appointment. Alternatively, or in addition, the user interface 700 may display physician information or a location associated with the patient appointment.

[0056] In some embodiments, the computing device 102 can update the user interface 700 according to the user's input. For example, if a patient name or patient record is selected (e.g., clicked), the user interface 700 can indicate that the patient name or patient record is displayed as "Viewed L452" (e.g., while displaying a "Viewed" icon by patient name or by another patient identifier). The user interface 700 can include a filter to filter the viewed patients.

[0057] In some embodiments, the user interface 700 may also include different views depending on the user's preferences. For example, the user interface 700 may include a "Proposed Tests" view, as shown in FIG. 7, which may display patients with proposed tests (e.g., actively recruiting or pending tests that match the patient's diagnosis and biomarkers). Alternatively, or in addition, the user interface 700 may include a "New Patients" view (not shown), which may display patients who are new to the clinic and are visiting the clinic for the first time. Alternatively, or in addition, the user interface 700 may include a "Recent Updates" view, which may display patients with proposed tests or patients who were previously marked as "candidates" or "observation" and are currently to be considered (or reconsidered) due to a recent scan or pathology report. As another example, recent updates may include recent scans, such as pathology or scan reports received, or scan orders created in the electronic health record associated with the patient since the patient's last visit.

[0058] In some embodiments, when a user clicks or selects a patient name in the user interface 700, the computing device 102 can provide another user interface to process the input and display the patient's information to the user. For example, FIGS. 8A and 8B are diagrams illustrating an exemplary user interface 800 for providing patient and proposed test information according to the present disclosure. The user interface 800 can be displayed via the output device 154 (e.g., a display or touch screen) of the computing device 102, and the user can input information via the input device 153. Alternatively, or in addition, the computing device 102 can send instructions to the client device 101 to display the user interface 800 via the output device (e.g., a display or touch screen) of the client device 101 and to receive user input via the input device of the client device 101.

[0059] As shown in FIG. 8A, a user can click or select patient "Ollie X. Sitedemann" in user interface layout 810 (which is similar to user interface 700). Computing device 102 can provide user interface layout 820 to the user, which may overlap with user interface layout 810 to display information for the patient. By way of example, user interface layout 820 can include area 821, which can display notifications related to the patient and / or trials. These notifications can include, but are not limited to, new trials available for which the patient is eligible, trials for which the patient is no longer eligible, changes to patient information, changes to trial eligibility criteria, and / or user notes.

[0060] The user interface layout 820 may also include an area 822 that displays the patient's clinical information, which may include, for example, the patient's diagnosis information, last visit, disease, etc., or a combination thereof. In some embodiments, the user interface layout 820 may enable the user to open the patient's electronic medical record. In some embodiments, the area 822 may include a disease status sub-area, as further described with respect to FIGS. 8C-8E.

[0061] The user interface layout 820 may also include an area 823 that displays one or more proposed and / or existing tests for the patient, which may include test information such as test name, test description, test status, test disease, test timeline of treatment, etc., or combinations thereof. In some embodiments, the user interface 800 may display information associated with two or more tests, which may include the status of the test. For example, tests may be categorized into different groups based on test status (e.g., on file status, screened status, not yet evaluated status, etc.). In some embodiments, the area 823 may display criteria associated with the test criteria, which may have a corresponding positive eligibility indicator 824, predicted eligibility indicator 825, and / or negative eligibility indicator 826 for the patient. The eligibility indicators may include a combination of shapes, colors, text, animations, etc., which may indicate different eligibility statuses to the user. As an example, the positive eligibility indicator 824 may include a bold, green circle, which may indicate that the patient meets certain eligibility criteria. As another example, the negative eligibility indicator 826 may include a bold red circle that may indicate that the patient does not meet certain eligibility criteria. In some embodiments, patients who meet the eligibility criteria may be predicted. For example, a predicted eligibility status may be determined based on computer models according to disclosed embodiments, medical records, medical documentation, etc., and the eligibility status may be displayed as a predicted eligibility indicator 825. As an example, if the patient has a predicted metastatic state that matches the metastatic state criteria of the study, a light green circle may be displayed as the predicted eligibility indicator 825. The predicted eligibility indicator 825, like any eligibility indicator, may include text to assist the user in determining details about the eligibility criteria. For example, the predicted eligibility indicator 825 may include text describing a level of confidence in the predicted metastatic state.In some embodiments, a particular predicted eligibility indicator 825 may be associated with a particular level of confidence. For example, if the predicted confidence level reaches a threshold level (e.g., a 60% likelihood that the patient has a "metastatic" metastatic status), a particular indicator (e.g., a yellow circle) may be displayed. Other aspects of the predicted metastatic status are discussed with respect to other techniques described herein.

[0062] The above are described as examples, as many combinations of color, shape, text, animation, and other visual features can be used to display informative eligibility indicators.

[0063] In some embodiments, the user interface 800 can present more detailed information about the test. For example, the user can select a test designated "NSCLC-1234" in area 823, as shown in FIG. 8B, and the computing device 102 can update area 823 of the user interface 800 to display more information about the test. For example, area 823 can update to display a test timeline for the test.

[0064] Exemplary FIG. 8B shows information that may be displayed related to a test. In some embodiments, area 823 may include a timeline with interactable elements. For example, the timeline may include several medical events associated with a patient, which the user may select. In some embodiments, interactable options (e.g., edit, delete, add) may be displayed that may enable the user to edit, delete, and / or add information (e.g., elements) to the timeline. In some embodiments, some interactable options may only be displayed after an element on the timeline is selected (e.g., edit, delete).

[0065] In some embodiments, the user interface 800 may enable a user to take action on one or more of the patient's information and / or the trials. For example, the user interface 800 may enable a user to update the information (e.g., mark a patient as not viewed, mark a trial as viewed, etc.). The updated information may be displayed on the user interface 800 accordingly. In some embodiments, the updated information may be stored for further use and / or made available to another user of the system. For example, when a first user views a patient (e.g., by clicking or selecting within the user interface 800), the computing device 102 may label the patient as "viewed." The computing device 102 may also provide a user interface to a second user that includes an indicator that the patient has been viewed. Alternatively, or in addition, the user interface 800 may enable the user to set a reminder to have the user, a physician, or a clinical trial coordinator, or the like, or a combination thereof, view the information. As an example, the user interface 800 may enable the user to create a reminder for a physician who is scheduled to see the patient to look for potentially eligible tests.

[0066] 8C, 8D, and 8E show exemplary user interfaces for providing management of a metastasis state. In some embodiments, a sub-area 830 according to the disclosed embodiments can be displayed after a metastasis state is predicted for a patient. The sub-area 830 can include a prediction level indicator 831, which can correspond to the predicted eligibility indicator 825. For example, the prediction level indicator 831 can indicate a level of confidence that the patient has a particular metastasis state. In some embodiments, the sub-area 830 can include an update status indicator 832, which can display a date and / or time when information associated with the metastasis state (e.g., metastasis state, level of confidence, verified state, etc.) was last updated. The sub-area 830 can also include an interactable verification initiator 833, which can enable a user to verify the metastasis state. For example, the verification initiator 833 can be selectable by a user, and upon selection, the sub-area 830 can update to the sub-area 840.

[0067] Sub-region 840 may include a metastasis status element 841 and a non-metastasis status element 842. In some embodiments, selection of metastasis status element 841 may verify a patient's metastasis status (which may have previously only been predicted) as metastatic. In some embodiments, selection of non-metastasis status element 842 may verify a patient's metastasis status (which may previously only have been predicted) as non-metastatic. According to disclosed embodiments, verifying the metastasis status may include updating patient data, test data, and / or a user interface. For example, selection of metastasis status element 841 or non-metastasis status element 842 may cause sub-region 840 to update to sub-region 850.

[0068] Sub-area 850 can include an interactable validation confirmation indicator 851, which can display the validated transition state. In some embodiments, validation confirmation indicator 851 can be selectable by a user, which can allow a user to change the patient's currently validated transition state. In some embodiments, sub-area 850 can also include a history indicator 852, which can display information associated with previous changes to the transition state. For example, history indicator 852 can display the user who last modified (e.g., validated) the transition state, the time the transition state was last changed, the date the transition state was last changed, etc.

[0069] 9 is a flow chart illustrating an example process 900 for providing one or more suggested patients for a trial according to the present disclosure. Although the process 900 is described with reference to the client device 101, one skilled in the art will understand that one or more steps of the process 900 can be performed by other components of the system (e.g., the computing device 102 or the processor 151).

[0070] In step 902, the client device 101 may receive a selection of a patient. For example, the client device 101 may receive user input via a user interface of the client device 101 to select a patient. As an example, a user may select a patient from a list of patients (e.g., in the user interface 700). In some embodiments, the user may search for a patient in a search interface (e.g., using the patient's name, the patient's date of birth, a unique patient identifier, etc.) before selecting the patient.

[0071] In step 904, the client device 101 may access a patient dataset. In some embodiments, the client device 101 may access a patient dataset in response to a patient selection (e.g., in step 901). For example, the accessed patient dataset may be associated with the selected patient. Accessing the patient dataset may include retrieving the patient dataset from a database (e.g., database 103). In some embodiments, the patient dataset may be stored in the database among multiple patient datasets. As a further example, the client device 101 may send a request to the computing device 102 to retrieve the patient dataset from the database 103. In some embodiments, the request to retrieve the patient dataset may be formatted to include a unique patient identifier or other information that enables the computing device 102 to distinguish the requested patient dataset from among the patient datasets stored in the database 103.

[0072] In step 906, the client device 101 may receive the metastasis state. In some embodiments, the received metastasis state may be a verified metastasis state or a predicted metastasis state of the patient. In some embodiments, the metastasis state may be associated with the patient (e.g., the patient selected in step 902). The predicted metastasis state may have been predicted by a trained model configured to receive a document that may include unstructured information. For example, the computing device 102 may have received a document (e.g., from the client device 101, which may or may not be the same device performing the steps of the process 900), applied the trained model to the document to extract information from the document, and / or converted the document into a format having structured information. In some embodiments, the predicted metastasis state may include a degree of likelihood determined by a machine learning model. Steps related to determining and / or updating the metastasis status are further described with respect to the process 1000.

[0073] In step 908, the client device 101 or computing device 102 may cause at least a portion of the patient dataset and the metastasis status (e.g., the predicted metastasis status) to be displayed. For example, according to disclosed embodiments, the displayed portion may be displayed within a user interface (e.g., user interface 800). In some embodiments, the displayed portion may include a subset or the entirety of the patient dataset accessed in step 902 and / or the metastasis status received in step 906.

[0074] In step 910, the client device 101 may determine a subset of tests for the patient. In some embodiments, determining the subset of tests for the patient may be based on at least a portion of the patient dataset, or the metastatic state (whether or not the same portion of the patient dataset in step 908). For example, the subset of tests may be determined based on a predicted or verified metastatic state. As an example, a first subset of tests may be determined based on a first predicted metastatic state, and a second subset of tests may be determined based on a second verified metastatic state. In some embodiments, the subset of tests for the patient may be determined from a plurality of tests. As an example, the computing device 102 may use the patient dataset and / or the metastatic state to determine the tests for the subset from among a set of tests (e.g., stored in the database 103). In some embodiments, the set of tests may be associated with a metastatic state criterion (e.g., at least one metastatic state criterion may be associated with each test in the set), and the metastatic state criterion may be used in determining the subset of tests. For example, the client device 101 may compare the transition state (e.g., the predicted transition state) to the transition state criteria of the test. In some embodiments, the client device 101 may determine that the predicted transition state meets the transition state criteria of the test (e.g., based on the comparison, the client device 101 may determine that the predicted transition state matches the transition state criteria), and then based on this determination, may include the test in the subset of tests. In some embodiments, the client device 101 may determine that the predicted transition state does not meet the transition state criteria of the test (e.g., based on the comparison, the client device 101 may determine that the predicted transition state does not match the transition state criteria), and then based on this determination, may exclude the test from the subset of tests.

[0075] In step 912, the client device 101 may display (e.g., on a display of the client device 101) a subset of tests for the patient (e.g., the subset determined in step 910). In some embodiments, the computing device 102 may display (e.g., on a display of the client device 101) a subset of tests for the patient. In some embodiments, displaying the subset of tests may include displaying criteria for the subset of tests and an indicator of patient eligibility status for the criteria (e.g., as shown in exemplary area 823). As described with respect to other figures, displaying the subset of tests may include displaying at least one indicator, interactable element, or the like, which may dynamically change based on updates to the patient dataset, metastatic status, test criteria, or the like.

[0076] 10 is a flow chart illustrating an example process 1000 for updating a transition state according to the present disclosure. Although the process 1000 is described with reference to the computing device 102, those skilled in the art will appreciate that one or more steps of the process 1000 may be performed by other components of the system (e.g., the client device 101).

[0077] In step 1002, the computing device 102 may receive unstructured information. In some embodiments, the unstructured information may be a scanned document, a handwritten note, an electronically written note, or part of another medical document. In some embodiments, the unstructured information may include medical data associated with a patient (e.g., metastatic status, patient age, disease type, disease stage, etc.).

[0078] In step 1004, the computing device 102 may parse the unstructured information (e.g., unstructured information in a patient document). In some embodiments, parsing the unstructured information may include identifying information contained within the document (e.g., identifying the patient's metastatic status, identifying the patient's name, admission date, treatment schedule, medications, etc.) and / or converting all or a portion of the document into a structured format. By way of example, the document may be an electronic document having structured and / or unstructured information (e.g., pdf document, XML file, etc.), images, charts, drawings, or any other medical information source. In some embodiments, the electronic document may be generated by a scanning device (e.g., a portable document scanner, a multifunction printer, etc.), which may be connected to the network 104. For example, the scanning device may scan a physical document to generate an electronic (e.g., structured) document that includes information from the physical document.

[0079] In some embodiments, parsing the unstructured information may include extracting metastatic information, which may be used to predict a metastatic status. In some embodiments, the extracted metastatic information may be associated with a patient identifier (e.g., linked to an electronic record of a patient identified in the document). In some embodiments, a trained model (e.g., implemented by the computing device 102) may parse the unstructured information. According to disclosed embodiments, the trained model may be any one of, but is not limited to, a computer software module, an algorithm, a machine learning model, a data model, a statistical model, a recurrent neural network (RNN) model, a long short-term memory (LSTM) model, or another neural network model. The trained model may be implemented on the computing device 102 or another computing device connected to the network 104. In some embodiments, the metastatic information may be identified from structured information (e.g., structured information that is part of a patient dataset).

[0080] In step 1006, the computing device 102 may predict a metastatic state, which may include generating a predicted metastatic state (e.g., a predicted metastatic state that may be used in the process 900) for a patient (e.g., a patient identified in a document, manually identified by a user, etc.). For example, the computing device 102 may predict the metastatic state based on identifying the metastatic state of the patient (e.g., identifying the metastatic state of the patient from unstructured information associated with the patient). In some embodiments, the computing device 102 may also determine a level of confidence of the predicted metastatic state. For example, the computing device 102 may determine a level of confidence of the predicted metastatic state according to a trained model. The level of confidence may be expressed as a percentage (e.g., 90% likelihood that the patient is in a particular metastatic state), a combination of words (e.g., “likely”, “somewhat likely”, “highly likely”, “suspect”, etc.), a type of visual indicator (e.g., as described with respect to FIGS. 8A-8E), etc. In some embodiments, different levels of confidence may be associated with different expressions. By way of example only, the phrase "highly likely" may be associated with a level of confidence that reaches a threshold of 90% certainty of a particular transition state. In some embodiments, the computing device 102 will predict the transition state based on at least two documents.

[0081] In step 1008, the computing device 102 may store the transition state (e.g., the transition state determined in step 1006). The transition state may be stored locally on the computing device 102, in the database 103, or in any storage device connected to the network 104.

[0082] In step 1010, the computing device 102 may receive a verified metastasis state, which may have been transmitted by the client device 101. In some embodiments, the verified metastasis state may be transmitted from the client device 101 to the computing device 102 in response to a predicted metastasis state received by the client device. In some embodiments, the verified metastasis state may be received in response to a user input at the client device 101 (e.g., a user input of the verified metastasis state into a user interface, as illustrated in an exemplary manner with respect to FIGS. 8C-8E). Alternatively, or in addition, the verified metastasis state may be received in response to a user input (e.g., input of a stage IV state) into a data element (e.g., a structured data element of a patient's medical record). In some embodiments, the computing device 102 may transmit the predicted metastasis state and / or the verified metastasis state to a remote device (e.g., the database 103, the client device that transmitted the verified state, a client device separate from the client device that transmitted the verified state, etc.). For example, the computing device 102 may transmit the predicted metastasis state and / or the verified metastasis state to a mobile device (e.g., a cell phone, laptop, smartwatch, or other portable network device). In some embodiments, the computing device 102 may forgo updating the predicted metastasis state based on the verified metastasis state (e.g., a verified metastasis state indicating that the patient is non-metastatic or metastatic). For example, in response to receiving a verified metastasis state indicating that the patient is metastatic, the computing device 102 may stop extracting metastasis information from received documents associated with the patient, may stop predicting metastasis states for the patient, and / or may stop transmitting predicted metastasis states for the patient.

[0083] At step 1012, the computing device 102 may update the metastatic status. In some embodiments, the computing device 102 may update the metastatic status of the patient based on a verified (e.g., received at the computing device 102 from the client device 101) metastatic status for that patient. In some embodiments, updating the metastatic status may include replacing a metastatic status stored in a device separate from the computing device 102 (e.g., database 103). Updating the metastatic status may also include modifying the displayed information. For example, the computing device 102 may cause a display of at least one indicator to be updated, which may be based on the verified metastatic status of the patient. As a further example, the computing device 102 may generate a predicted eligibility indicator 825, which may be changed and displayed at the client device 101 to a positive eligibility indicator 824 or a negative eligibility indicator 826. In some embodiments, the change in the displayed visualization element may be based on whether the verified metastatic status indicates that the patient is metastatic or non-metastatic and / or on the criteria of the test. In some embodiments, the computing device 102 may cause the user device 101 to remove at least one test from the subset of tests based on the patient's verified metastatic status. For example, the computing device 102 may cause the user device 101 to remove an indicator, region, sub-region, interface, etc. from the display. By way of mere further example, when the computing device 102 determines that the patient does not meet the criteria for a test (e.g., a test included in sub-region 823) based on the verified metastatic status, etc., the computing device may remove the ineligible test from the interface (e.g., user interface 800 that may be displayed at the client device 101).

[0084] The foregoing description has been presented for illustrative purposes. It is not exhaustive and is not limited to the precise forms or embodiments disclosed. Modifications and alterations in light of the specification and practice of the disclosed embodiments will be apparent to those skilled in the art. Furthermore, although aspects of the disclosed embodiments are described as being stored in memory, those skilled in the art will understand that these aspects can also be stored in other types of computer readable media, such as secondary storage devices, for example, hard disks or CDROMs, or other forms of RAM or ROM, USB media, DVDs, Blu-rays, 4K ultra-high density Blu-rays, or other optical drive media.

[0085] The written description and computer programs based on the disclosed methods are within the skill of an experienced developer. The various programs or program modules can be created using any of the techniques known to those skilled in the art or can be designed in conjunction with existing software. For example, program sections or program modules can be designed in or with .NetFramework, .NetCompactFramework (and related languages ​​such as VisualBasic, C, etc.), Java, Python, R, C++, Objective-C, HTML, HTML / AJAX combination, XML, or HTML, including Java applets.

[0086] Furthermore, while exemplary embodiments are described herein, the scope of any and all embodiments has equivalent elements, modifications, omissions, combinations (e.g., of aspects across various embodiments), alterations and / or adaptations as would be understood by one of ordinary skill in the art based on this disclosure. Restrictions in the claims should be interpreted broadly based on the language used in the claims, and should not be limited to the examples described herein, or during prosecution of this application. The examples should be interpreted as non-exclusive. Furthermore, the steps of the disclosed methods can be modified in any manner, including rearranging, repeating, inserting and / or deleting steps. Thus, it is intended that the specification and examples be considered merely as illustrative, with the true scope and spirit being indicated by the following claims, and the full scope of their equivalents.

Claims

1. 1. A system for determining a subset of a plurality of clinical trials for a patient using a metastatic status of the patient, the system comprising: At least one processor, receiving a selection of the patient; responsive to said selection of said patient, accessing a patient dataset associated with said patient; receiving a predicted metastatic status associated with the patient; displaying at least a first portion of the patient dataset and the predicted metastatic status; determining a subset of clinical trials for the patient from among the plurality of clinical trials based on the predicted metastatic status; displaying at least the subset of the clinical trials for the patient; and A system comprising a processor programmed to:

2. 2. The system of claim 1, wherein the predicted transition state is predicted by a trained model configured to receive documents including unstructured information.

3. The system of claim 2 , wherein the trained model comprises a machine learning model.

4. The system of claim 3 , wherein the predicted metastatic state includes a degree of likelihood determined by the machine learning model.

5. The system of claim 3 , wherein the document comprises an electronic document.

6. The system of claim 5 , wherein the unstructured information comprises medical data associated with the patient.

7. The system of claim 5 , wherein the electronic document is generated by scanning a physical document with a scanning device.

8. The system of claim 1 , wherein the patient data set is stored among a plurality of patient data sets in a database.

9. The system of claim 1 , wherein the at least one processor is further programmed to receive an input including a verified metastatic status of the patient.

10. The system of claim 9 , wherein the at least one processor is further programmed to transmit the predicted transition state and the verified transition state to a remote device.

11. The system of claim 10 , wherein the remote device comprises a mobile device.

12. The system of claim 9 , wherein determining the subset of clinical trials is based on the verified metastatic status.

13. The at least one processor 10. The system of claim 9, further programmed to forgo updating the predicted metastatic status based on the verified metastatic status indicating that the patient is metastatic.

14. each of said plurality of clinical trials is associated with metastatic status criteria; 2. The system of claim 1, wherein determining the subset of clinical trials comprises comparing the predicted metastatic status to clinical trial metastatic status criteria included in the plurality of clinical trials.

15. the at least one processor is further programmed to determine that the predicted metastatic state meets the metastatic state criteria of the clinical trial of the plurality of clinical trials based on the comparison; 15. The system of claim 14, wherein determining the subset of clinical trials comprises including in the subset of clinical trials the clinical trials associated with the met metastatic status.

16. the at least one processor is further programmed to determine that the predicted metastatic state does not meet the metastatic state criteria of the clinical trial of the plurality of clinical trials based on the comparison; 15. The system of claim 14, wherein determining the subset of clinical trials comprises excluding, in the subset of clinical trials, the clinical trials associated with the unmet metastatic status.

17. 10. The system of claim 1, wherein displaying the subset of clinical trials comprises displaying criteria for the subset of clinical trials and an indicator of a patient's eligibility for the criteria.

18. The at least one processor: receiving an input including a verified metastatic status of the patient; 20. The system of claim 17, further programmed to: update the display of at least one of the indicators based on the verified metastatic status of the patient.

19. The at least one processor: receiving an input including a verified metastatic status of the patient; 20. The system of claim 17, further programmed to: cause removal of at least one clinical trial from the subset of clinical trials based on the verified metastatic status of the patient.

20. 1. A method, executed by at least one processor, for determining a subset of a plurality of clinical trials for a patient using a metastatic status of the patient, the method comprising: receiving a selection of the patient; responsive to said selection of said patient, accessing a patient dataset associated with said patient; receiving a predicted metastatic status associated with the patient; displaying at least a first portion of the patient dataset and the predicted metastatic status; determining a subset of clinical trials for the patient from among the plurality of clinical trials based on the predicted metastatic status; and displaying at least a subset of the clinical trials to the patient.

21. A non-transitory computer-readable medium containing instructions that, when executed by one or more processors, cause the one or more processors to: receiving a patient selection; responsive to said selection of said patient, accessing a patient dataset associated with said patient; receiving a predicted metastatic status associated with the patient; displaying at least a first portion of the patient dataset and the predicted metastatic status; determining a subset of clinical trials for the patient from among a plurality of clinical trials based on the predicted metastatic status; displaying at least a subset of said clinical trials for said patient; A non-transitory computer-readable medium for causing

Images