Abstract: Disclosed herein are systems, methods, and compositions for treating a subject diagnosed with, or suffering from cancer. In some embodiments, the method comprises determining whether a tumor sample from the subject includes a cytotoxic gene signature, and treating the subject based on the determination. In some embodiments, the subject has or is suspected of having a loss of heterozygosity in human leukocyte antigen (HLA) class I genes. In some embodiments, the therapy comprises one or more checkpoint inhibitors. In some embodiments, the cancer is colorectal, uterine, stomach, lung, skin, head or neck, or non-small cell lung carcinoma.

Abstract: Methods for determining a cancer composition of a subject are provided that include generating machine-learning models configured to identify cell types based on respective cell-type RNA expression profiles, and using the models to determine the cancer composition of the subject.

Abstract: A computer-implemented method, computing system and computer-readable medium include receiving training data and training a machine learning model to generate a cell expression map. A computer-implemented method, computing system and computer-readable medium includes receiving a histology image and a cell segmentation map and processing them using a trained machine learning model.

Abstract: Methods, systems, and software are provided for determining a homologous recombination pathway status of a cancer in a test subject, e.g., to improve cancer treatment predictions and outcomes. In some embodiments, classifiers using one or more of (i) a heterozygosity status for DNA damage repair genes in a cancerous tissue, (ii) a measure of the loss of heterozygosity across the genome of the cancerous tissue, (iii) a measure of variant alleles detected in a second plurality of DNA damage repair genes in the genome of the cancerous tissue, (iv) a measure of variant alleles detected in the second plurality of DNA damage repair genes in the genome of a non-cancerous tissue, and (v) tumor sample purity are provided.

Abstract: A method includes displaying a cohort report; receiving a request to determine a therapy identification; causing information to be transmitted to a remote cloud server; receiving clinical trial data; and updating the cohort report. A computing system includes a processor; and a memory having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: display a cohort report; receive a request to determine a therapy identification; cause information to be transmitted to a remote cloud server; receive clinical trial data; and update the cohort report. A computer-readable medium having stored thereon a set of computer-executable instructions that, when executed by one or more processors, cause a computer to: display a cohort report; receive a request to determine a therapy identification; cause information to be transmitted to a remote cloud server; receive clinical trial data; and update the cohort report.

Abstract: In the disclosed systems and methods for characterizing a cancer condition of a tissue in a subject, a computer system inputs information into an ensemble model. The information includes, for each respective class of radiomics features in a plurality of classes of radiomics features, a corresponding value for each respective radiomic feature in a corresponding plurality of radiomics features of the respective class of radiomics features obtained from a medical imaging dataset. The ensemble model comprises a plurality of component models. The computer system obtains as output from each respective component model in the plurality of component models a corresponding component prediction for the cancer condition, thereby obtaining a plurality of component predictions for the cancer condition. The computer system combines the plurality of component predictions to obtain as output of the ensemble model a characterization of the cancer condition.

Abstract: This application describes, amongst other things, methods and systems for building and deploying agents. An example method includes obtaining orchestration data about a set of task-specific components selected to provide a response to the prompt, where each respective task-specific components in the set of task-specific components is configured to assist with a respective clinical task of the one or more clinical tasks. The method further includes, determining an order in which each respective task-specific components of the set of task-specific components should be utilized to prepare a complete response to the prompt that address the one or more clinical tasks based on the obtained orchestration data about the set of task-specific components. The method also includes, in accordance with the determined order, providing first data related to the prompt to a first task-specific component and receiving a first response from the first task-specific component.

Abstract: A generalizable and interpretable deep learning model for predicting biomarker status and biomarker metrics from histopathology slide images is provided.

Abstract: Methods, systems, and software are provided for determining a relationship between a subject and a health entity. An electronic health record (EHR) for the subject is split into sections by detecting delineating section headers, and sections are subdivided into text spans. Text spans are filtered by language pattern recognition into a set of text spans having an expression related to the health entity. The natural language context of the expression in each text span in the set is evaluated to obtain a corresponding scoring representation. Scoring representations are inputted into a model comprising a plurality of parameters. The model outputs, for each text span in the set, at least a prediction that the text span is associated with the health entity. Models for determining relationships between subjects and health entities and methods for training models to determine relationships between subjects and health entities are also provided.

Abstract: A method and system for predicting the likelihood that a patient will suffer from atrial fibrillation is provided. The method includes receiving electrocardiogram data associated with the patient, providing at least a portion of the electrocardiogram data to a trained model, receiving a risk score indicative of the likelihood the patient will suffer from atrial fibrillation within a predetermined period of time from when the electrocardiogram data was generated, and outputting the risk score to at least one of a memory or a display for viewing by a medical practitioner or healthcare administrator. The system includes at least one processor executing instructions to carry out the steps of the method.

Abstract: A method for determining whether a patient may be enrolled into a clinical trial includes the steps of examining the patient's medical record from an electronic health record system, deriving a plurality of first concepts from the medical record, normalizing each concept in the plurality of first concepts to produce, for each normalization, a normalized concept, comparing each normalized concept to a list of study criteria, to indicate if the normalized concept meets the criteria, and if each criteria is met, indicating that the patient is not ineligible for enrollment in the clinical trial

Abstract: Methods, systems, and software are provided for using organoid cultures, e.g., patient-derived tumor organoid cultures, to improve treatment predictions and outcomes.

Abstract: An evaluation of a cancer treatment start date for a cancer medication identifies a first plurality of subjects and, for each, the treatment start date. A subject is selected for a second plurality of subjects by applying features for the subject to a model at a propensity value threshold. One subset of the features is associated with a time period and another subset is static. The applying obtains anchor point predictions, each associated with a time in the time period and including a probability that the time is the start date. The time of the anchor point prediction having the greatest probability is assigned the anchor point of the subject. The start date is evaluated with a survival objective based on the start date for each subject in the first plurality and the assigned anchor point for each subject in the second plurality.

Abstract: Systems and methods are provided for determining an optimized probe set. The method proceeds by obtaining a set of probes, where each probe has a respective concentration. The set of probes is assayed against a sample library, and at least i) a respective recovery rate for each probe in the set of probes, and ii) a median recovery rate for the set of probes are obtained. Modify the respective concentration of each probe that does not satisfy predetermined recovery rate threshold. Reevaluate the set of probes against the sample library. Repeat the modifying and reevaluation until the respective updated recovery rate for each probe in the updated set of probes satisfies the predetermined recovery rate threshold, thereby providing the optimized set of probes for the sample library.

Abstract: A system and method are provided for identifying a multimodal biomarker of a prognostic prediction, using a deep learning framework trained to analyze different modality data, including radiomic image data, pathology image data, and molecular image data to obtain unimodal embedding predictions from those modality data and generate multimodal embedding predictions, through application of a loss minimization and attention-based fusion processes.

Abstract: An artificial intelligence engine for directed hypothesis generation and ranking uses multiple heterogeneous knowledge graphs integrating disease-specific multi-omic data specific to a patient or cohort of patients. The engine also uses a knowledge graph representation of ‘what the world knows’ in the relevant bio-medical subspace. The engine applies a hypothesis generation module, a semantic search analysis component to allow fast acquiring and construction of cohorts, as well as aggregating, summarizing, visualizing and returning ranked multi-omic alterations in terms of clinical actionability and degree of surprise for individual samples and cohorts. The engine also applies a moderator module that ranks and filters hypotheses, where the most promising hypothesis can be presented to domain experts (e.g., physicians, oncologists, pathologists, radiologists and researchers) for feedback.

Abstract: A platform is provided for generating 3D models of a tumor segmented from a series of 2D medical images and for identifying from these 3D models, radiomic features that may be used for diagnostic, prognostic, and treatment response assessment of the tumor. The radiomic features may be shape-based features, intensity-based features, textural features, and filter-based features. The radiomic features are compared to remove sufficiently redundant features, thereby producing a reduced set of radiomic features, which is then compared to separate genomic data and/or outcome data to identify clinically and biologically significant radiomic features for diagnostic, prognostic, and treatment response assessment, other applications.

Abstract: The present disclosure provides methods, systems, compositions, and kits for the high-throughput detection of multi-molecule biomarkers in a biological sample. The disclosed methods, systems, compositions, and kits utilize antibody-oligonucleotide tags to detect two or more molecules that are in close proximity.

Abstract: A method and system of audibly broadcasting responses to a user based on user queries about a specific patient report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration device, identifying at least one intent associated with the audible query, identifying at least one data operation associated with the at least one intent, associating each of the at least one data operations with a first set of data presented on the report, executing each of the at least one data operations on a second set of data to generate response data, generating an audible response file associated with the response data and providing the audible response file for broadcasting via a speaker coupled to the collaboration device.

Abstract: A computer program product includes multiple microservices for interrogating clinical records according to one or more projects associated with patient datasets obtained from electronic copies of source documents from the clinical records. A first microservice generates a user interface including a first portion displaying source documents and, concurrently, a second portion displaying structured patient data fields organized into categories for entering structured patient data derived from the source documents displayed in the first portion. Categories and their organization are defined by a template and include cancer diagnosis, staging, tumor size, genetic results, and date of recurrence. A second microservice validates abstracted patient data according to validation rules applied to the categories, validation rules being assigned to the projects and performed on the categories as they are populated.