Tempus Labs, Inc.

The present disclosure relates to predicting a data element in an electronic health record (EHR) for a subject using a trained machine learning model including an attention module. An example method includes obtaining a query for the prediction of the data element, obtaining a plurality of observations about the subject, processing the query and observations with the trained machine learning model having an attention module to generate a prediction of the subject characteristic, and providing the prediction of the data element as an output.

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.

Systems and methods are provided for balancing a probe set for enriching a plurality of genomic loci. A nucleic acid probe set containing pools of nucleic acid probe species is obtained. Each probe species aligns to a different subsequence of a respective locus and includes proportions of a capture moiety conjugated version and a capture moiety-free version. Each probe species in a pool aligns to a portion of the genome that is at least 100 nucleotides away from any other probe species in the pool. Each pool in the probe set is separately analyzed against reference nucleic acid samples to obtain recovery rates and identify probe species that do not satisfy a minimum or a maximum recovery rate threshold. An adjusted version of a final design for the probe set is established by adjusting proportions of capture moiety conjugated and capture moiety-free versions for the identified probe species.

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.

Systems and methods for phenotyping clinical data are provided. The method includes obtaining episodic records comprising unstructured clinical data from an electronic medical record (EMR) or electronic health record (EHR) for patients. The method also includes filtering the episodic records by language pattern recognition to identify episodic records that each includes an expression related to a clinical condition. The method also includes splitting each episodic record to obtain snippets comprising tokens. The method also includes predicting if an episodic record represents an instance of the clinical condition using a trained classifier. The trained classifier includes an aggregation function that aggregates the snippets to output a corresponding representation for the episodic record, and an interpretation function that interprets the corresponding representation to output a corresponding prediction for whether the episodic record represents an instance of the clinical condition.

A system for identifying biomarkers in a digital image of a Hematoxylin and Eosin-stained slide of a target tissue includes a processor and an electronic network; and a memory having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: process segmented tile images determine a predicted biomarker presence; and transmit the predicted presence. A non-transitory computer-readable medium includes a set of computer-executable instructions that, when executed by one or more processors, cause a computer to: process segmented tile images; determine a predicted biomarker presence; and transmit the predicted presence. A computer-implemented method includes processing segmented tile images; determining a predicted biomarker presence; and transmitting the predicted presence.

A system and method for analyzing a data store of de-identified patient data to generate one or more dynamic user interfaces usable to predict an expected response of a particular patient population or cohort when provided with a certain treatment. The automated analysis of patterns occurring in patient clinical, molecular, phenotypic, and response data, as facilitated by the various user interfaces, provides an efficient, intuitive way for clinicians to evaluate large data sets to aid in the potential discovery of insights of therapeutic significance.

The following relates generally to determining genomic biomarkers from biological data (e.g., a read of a nucleic acid, or an image, such as an image of a slide). In some embodiments, a transform orchestrator: (i) receives an order to transform biological data to one or more genomic biomarkers; (ii) selects a transform for deriving each of the received one or more genomic biomarkers; (iii) associates each selected transform with a cloud computing platform; (iv) executes instructions for each selected transform; (v) communicates an operational status of each selected transform; (vi) stores the genomic biomarker output from each selected transform; and (vii) provides a notification of a final operational status of each selected transform.

Methods, systems, and software are provided for detecting gene fusions in a subject with a cancer condition through mRNA boundary analysis of next generation sequencing of a transcriptome or relevant part thereof. Methods, systems, and software are provided for detecting splice variants in a subject with a cancer condition through mRNA boundary analysis of next generation sequencing of a transcriptome or relevant part thereof. Methods, systems, and software are provided for evaluating the complexity of an RNA-seq sequencing reaction through mRNA boundary analysis. Generally, the methods described herein include obtaining sequences of mRNA molecules for a plurality of genes in a sample of a subject. For each gene, an RNA boundary distribution including relative abundance value for each respective RNA boundary sub-sequence of the gene is determined from the plurality of sequences. These abundance values are evaluated using one or more models to provide the analyses described herein.

A system and method for analyzing a data store of de-identified patient data to generate one or more dynamic user interfaces usable to predict an expected response of a particular patient population or cohort when provided with a certain treatment. The automated analysis of patterns occurring in patient clinical, molecular, phenotypic, and response data, as facilitated by the various user interfaces, provides an efficient, intuitive way for clinicians to evaluate large data sets to aid in the potential discovery of insights of therapeutic significance.