Isaac S. Kohane
YOU?
Author Swipe
View article: A global log for medical AI
A global log for medical AI Open
Modern computer systems often rely on syslog, a simple, universal protocol that records every critical event across heterogeneous infrastructure. However, healthcare's rapidly growing clinical AI stack has no equivalent. As hospitals rush …
View article: A standards-based approach to digital health research: implementing the people heart study
A standards-based approach to digital health research: implementing the people heart study Open
Objective To assess whether HL7 Fast Healthcare Interoperability Resources (FHIR) can underpin a fully standards-based, end-to-end digital research architecture, demonstrate it in a live study, and quantify its benefits for interoperabilit…
View article: Heterogeneous Effect of Automated Alerts on Mortality
Heterogeneous Effect of Automated Alerts on Mortality Open
We analyzed data from 13,483 hospitalized patients with acute kidney injury (AKI) from three randomized controlled trials to assess the heterogeneous effects of automated electronic alerts on 14-day mortality. We modeled and predicted indi…
View article: Joint, multifaceted genomic analysis enables diagnosis of diverse, ultra-rare monogenic presentations
Joint, multifaceted genomic analysis enables diagnosis of diverse, ultra-rare monogenic presentations Open
Genomics for rare disease diagnosis has advanced at a rapid pace due to our ability to perform in-depth analyses on individual patients with ultra-rare diseases. The increasing sizes of ultra-rare disease cohorts internationally newly enab…
View article: Label efficient phenotyping for Long COVID using electronic health records
Label efficient phenotyping for Long COVID using electronic health records Open
View article: Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases Open
View article: One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence
One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence Open
Medical AI, including clinical language models, vision-language models, and multimodal health record models, already summarizes notes, answers questions, and supports decisions. Their adaptation to new populations, specialties, or care set…
View article: Heterogeneity of continuous glucose monitoring features and their clinical associations in a type 2 diabetes population
Heterogeneity of continuous glucose monitoring features and their clinical associations in a type 2 diabetes population Open
Objective Data from continuous glucose monitors (CGM) enable the extraction of features descriptive of glycemic dynamics that may provide insight into underlying health status. In this work, we analyse CGM data from a large population of i…
View article: Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence
Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence Open
Background Objective assessment of left ventricular function remains a key prognosticator that is used to guide therapeutic decisions for patients with heart failure (HF). However, the left ventricular ejection fraction (LVEF) is dynamic, …
View article: GENIE: Generative Note Information Extraction model for structuring EHR data
GENIE: Generative Note Information Extraction model for structuring EHR data Open
Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured natu…
View article: A case study on using a large language model to analyze continuous glucose monitoring data
A case study on using a large language model to analyze continuous glucose monitoring data Open
Continuous glucose monitors (CGM) provide valuable insights about glycemic control that aid in diabetes management. However, interpreting metrics and charts and synthesizing them into linguistic summaries is often non-trivial for patients …
View article: The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study
The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study Open
View article: Geoinference of author affiliations using NLP-based text classification
Geoinference of author affiliations using NLP-based text classification Open
Author affiliations are essential in bibliometric studies, requiring relevant information extraction from free-text affiliations. Precisely determining an author's location from their affiliation is crucial for understanding research netwo…
View article: Implications of mappings between International Classification of Diseases clinical diagnosis codes and Human Phenotype Ontology terms
Implications of mappings between International Classification of Diseases clinical diagnosis codes and Human Phenotype Ontology terms Open
Objective Integrating electronic health record (EHR) data with other resources is essential in rare disease research due to low disease prevalence. Such integration is dependent on the alignment of ontologies used for data annotation. The …
View article: Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions
Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions Open
As large language models (LLMs) are increasingly deployed in high-stakes domains like healthcare, understanding how well their decision-making aligns with human preferences and values becomes crucial, especially when we recognize that ther…
View article: Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions
Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions Open
As large language models (LLMs) are deployed in high-stakes domains like healthcare, understanding how well their decision-making aligns with human preferences and values becomes crucial, especially when we recognize that there is no singl…
View article: The literacy barrier in clinical trial consents: a retrospective analysis
The literacy barrier in clinical trial consents: a retrospective analysis Open
View article: Implications of mappings between ICD clinical diagnosis codes and Human Phenotype Ontology terms
Implications of mappings between ICD clinical diagnosis codes and Human Phenotype Ontology terms Open
Objective: Integrating EHR data with other resources is essential in rare disease research due to low disease prevalence. Such integration is dependent on the alignment of ontologies used for data annotation. The International Classificati…
View article: Dominant missense variants in SREBF2 are associated with complex dermatological, neurological, and skeletal abnormalities
Dominant missense variants in SREBF2 are associated with complex dermatological, neurological, and skeletal abnormalities Open
View article: Polygenic risk scores for autoimmune related diseases are significantly different in cancer exceptional responders
Polygenic risk scores for autoimmune related diseases are significantly different in cancer exceptional responders Open
A small number of cancer patients respond exceptionally well to therapies and survive significantly longer than patients with similar diagnoses. Profiling the germline genetic backgrounds of exceptional responder (ER) patients, with extrem…
View article: Geoinference of Author Affiliations using NLP-based Text Classification
Geoinference of Author Affiliations using NLP-based Text Classification Open
Author affiliations are essential in bibliometric studies, requiring relevant information extraction from free-text affiliations. Precisely determining an author's location from their affiliation is crucial for understanding research netwo…
View article: Leveraging Large Language Models to Analyze Continuous Glucose Monitoring Data: A Case Study
Leveraging Large Language Models to Analyze Continuous Glucose Monitoring Data: A Case Study Open
Continuous glucose monitors (CGM) provide patients and clinicians with valuable insights about glycemic control that aid in diabetes management. The advent of large language models (LLMs), such as GPT-4, has enabled real-time text generati…
View article: Causal machine learning for predicting treatment outcomes
Causal machine learning for predicting treatment outcomes Open
View article: Disease progression strikingly differs in research and real-world Parkinson’s populations
Disease progression strikingly differs in research and real-world Parkinson’s populations Open
Characterization of Parkinson’s disease (PD) progression using real-world evidence could guide clinical trial design and identify subpopulations. Efforts to curate research populations, the increasing availability of real-world data, and a…
View article: Policy in Progress — The Race to Frame AI in Health Care
Policy in Progress — The Race to Frame AI in Health Care Open
Experts from across four continents convened at the October 2023 RAISE (Responsible AI for Social and Ethical Healthcare) meeting to actively engage public and policy discourse and health care stakeholders in addressing concerns before pol…
View article: Loss of the endoplasmic reticulum protein Tmem208 affects cell polarity, development, and viability
Loss of the endoplasmic reticulum protein Tmem208 affects cell polarity, development, and viability Open
Nascent proteins destined for the cell membrane and the secretory pathway are targeted to the endoplasmic reticulum (ER) either posttranslationally or cotranslationally. The signal-independent pathway, containing the protein TMEM208, is on…
View article: Disease progression strikingly differs in research and real-world Parkinson's populations
Disease progression strikingly differs in research and real-world Parkinson's populations Open
Characterization of Parkinson's disease (PD) progression using real-world evidence could guide clinical trial design and identify subpopulations. Efforts to curate research populations, the increasing availability of real-world data and re…
View article: Joint, multifaceted genomic analysis enables diagnosis of diverse, ultra-rare monogenic presentations
Joint, multifaceted genomic analysis enables diagnosis of diverse, ultra-rare monogenic presentations Open
Genomics for rare disease diagnosis has advanced at a rapid pace due to our ability to perform "N-of-1" analyses on individual patients with ultra-rare diseases. The increasing sizes of ultra-rare disease cohorts internationally newly enab…
View article: Assessing the Potential of GPT-4 to Annotate Medical Notes Across Different Languages and Countries: A Model Evaluation Study
Assessing the Potential of GPT-4 to Annotate Medical Notes Across Different Languages and Countries: A Model Evaluation Study Open
View article: Why We Support and Encourage the Use of Large Language Models in <i>NEJM AI</i> Submissions
Why We Support and Encourage the Use of Large Language Models in <i>NEJM AI</i> Submissions Open
Large language models (LLMs) promise to revolutionize many aspects of the creation and dissemination of scientific knowledge; however, their use in scientific writing remains controversial, because of concerns about authorship, originality…