Title: Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing
Abstract ObjectiveLeverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. Materials and MethodsWe trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment. ResultsThe metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user. DiscussionOur model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings. ConclusionEHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting. more »« less
The large amount of time clinicians spend sifting through patient notes and documenting in electronic health records (EHRs) is a leading cause of clinician burnout. By proactively and dynamically retrieving relevant notes during the documentation process, we can reduce the effort required to find relevant patient history. In this work, we conceptualize the use of EHR audit logs for machine learning as a source of supervision of note relevance in a specific clinical context, at a particular point in time. Our evaluation focuses on the dynamic retrieval in the emergency department, a high acuity setting with unique patterns of information retrieval and note writing. We show that our methods can achieve an AUC of 0.963 for predicting which notes will be read in an individual note writing session. We additionally conduct a user study with several clinicians and find that our framework can help clinicians retrieve relevant information more efficiently. Demonstrating that our framework and methods can perform well in this demanding setting is a promising proof of concept that they will translate to other clinical settings and data modalities (e.g., labs, medications, imaging).
IntroductionWith the increasing utilization of text-based suicide crisis counseling, new means of identifying at risk clients must be explored. Natural language processing (NLP) holds promise for evaluating the content of crisis counseling; here we use a data-driven approach to evaluate NLP methods in identifying client suicide risk. MethodsDe-identified crisis counseling data from a regional text-based crisis encounter and mobile tipline application were used to evaluate two modeling approaches in classifying client suicide risk levels. A manual evaluation of model errors and system behavior was conducted. ResultsThe neural model outperformed a term frequency-inverse document frequency (tf-idf) model in the false-negative rate. While 75% of the neural model’s false negative encounters had some discussion of suicidality, 62.5% saw a resolution of the client’s initial concerns. Similarly, the neural model detected signals of suicidality in 60.6% of false-positive encounters. DiscussionThe neural model demonstrated greater sensitivity in the detection of client suicide risk. A manual assessment of errors and model performance reflected these same findings, detecting higher levels of risk in many of the false-positive encounters and lower levels of risk in many of the false negatives. NLP-based models can detect the suicide risk of text-based crisis encounters from the encounter’s content.
BackgroundMetastatic cancer remains one of the leading causes of cancer-related mortality worldwide. Yet, the prediction of survivability in this population remains limited by heterogeneous clinical presentations and high-dimensional molecular features. Advances in machine learning (ML) provide an opportunity to integrate diverse patient- and tumor-level factors into explainable predictive ML models. Leveraging large real-world datasets and modern ML techniques can enable improved risk stratification and precision oncology. ObjectiveThis study aimed to develop and interpret ML models for predicting overall survival in patients with metastatic cancer using the Memorial Sloan Kettering-Metastatic (MSK-MET) dataset and to identify key prognostic biomarkers through explainable artificial intelligence techniques. MethodsWe performed a retrospective analysis of the MSK-MET cohort, comprising 25,775 patients across 27 tumor types. After data cleaning and balancing, 20,338 patients were included. Overall survival was defined as deceased versus living at last follow-up. Five classifiers (extreme gradient boosting [XGBoost], logistic regression, random forest, decision tree, and naive Bayes) were trained using an 80/20 stratified split and optimized via grid search with 5-fold cross-validation. Model performance was assessed using accuracy, area under the curve (AUC), precision, recall, and F1-score. Model explainability was achieved using Shapley additive explanations (SHAP). Survival analyses included Kaplan-Meier estimates, Cox proportional hazards models, and an XGBoost-Cox model for time-to-event prediction. The positive predictive value and negative predictive value were calculated at the Youden index–optimal threshold. ResultsXGBoost achieved the highest performance (accuracy=0.74; AUC=0.82), outperforming other classifiers. In survival analyses, the XGBoost-Cox model with a concordance index (C-index) of 0.70 exceeded the traditional Cox model (C-index=0.66). SHAP analysis and Cox models consistently identified metastatic site count, tumor mutational burden, fraction of genome altered, and the presence of distant liver and bone metastases as among the strongest prognostic factors, a pattern that held at both the pan-cancer level and recurrently across cancer-specific models. At the cancer-specific level, performance varied; prostate cancer achieved the highest predictive accuracy (AUC=0.88), while pancreatic cancer was notably more challenging (AUC=0.68). Kaplan-Meier analyses demonstrated marked survival separation between patients with and without metastases (80-month survival: approximately 0.80 vs 0.30). At the Youden-optimal threshold, positive predictive value and negative predictive value were approximately 70% and 80%, respectively, supporting clinical use for risk stratification. ConclusionsExplainable ML models, particularly XGBoost combined with SHAP, can strongly predict survivability in metastatic cancers while highlighting clinically meaningful features. These findings support the use of ML-based tools for patient counseling, treatment planning, and integration into precision oncology workflows. Future work should include external validation on independent cohorts, integration with electronic health records via Fast Healthcare Interoperability Resources–based dashboards, and prospective clinician-in-the-loop evaluation to assess real-world use.
Cardenas, Erika; Shorten, Connor; Khoshgoftaar, Taghi M; Furht, Borivoje
(, The International FLAIRS Conference Proceedings)
Purchasing a home is one of the largest investments most people make. House price prediction allows individuals to be informed about their asset wealth. Transparent pricing on homes allows for a more efficient market and economy. We report the performance of machine learning models trained with structured tabular representations and unstructured text descriptions. We collected a dataset of 200 descriptions of houses which include meta-information, as well as text descriptions. We test logistic regression and multi-layer perceptron (MLP) classifiers on dividing these houses into binary buckets based on fixed price thresholds. We present an exploration into strategies to represent unstructured text descriptions of houses as inputs for machine learning models. This includes a comparison of term frequency-inverse document frequency (TF-IDF), bag-of-words (BoW), and zero-shot inference with large language models. We find the best predictive performance with TF-IDF representations of house descriptions. Readers will gain an understanding of how to use machine learning models optimized with structured and unstructured text data to predict house prices.
Baughman, Derek J; Qassem, Layth; Sulieman, Lina; Matheny, Michael E; Fabbri, Daniel; Tindle, Hilary A; Goodman, Aubrey Cole; Nelson, Scott D; Wright, Adam
(, JAMIA Open)
Abstract ObjectivesTo develop CigStopper, a real-time, automated medical billing prototype designed to identify eligible tobacco cessation care codes, thereby reducing administrative workload while improving billing accuracy. Materials and MethodsChatGPT prompt engineering generated a synthetic corpus of physician-style clinical notes categorized for CPT codes 99406/99407. Practicing clinicians annotated the dataset to train multiple machine learning (ML) models focused on accurately predicting billing code eligibility. ResultsDecision tree and random forest models performed best. Mean performance across all models: PRC AUC = 0.857, F1 score = 0.835. Generalizability testing on deidentified notes confirmed that tree-based models performed best. DiscussionCigStopper shows promise for streamlining manual billing inefficiencies that hinder tobacco cessation care. ML methods lay the groundwork for clinical implementation based on good performance using synthetic data. Automating high-volume, low-value tasks simplify complexities in a multi-payer system and promote financial sustainability for healthcare practices. ConclusionCigStopper validates foundational methods for automating the discernment of appropriate billing codes for eligible smoking cessation counseling care.
Jiang, Sharon, Lam, Barbara_D, Agrawal, Monica, Shen, Shannon, Kurtzman, Nicholas, Horng, Steven, Karger, David_R, and Sontag, David. Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing. Journal of the American Medical Informatics Association 31.7 Web. doi:10.1093/jamia/ocae092.
Jiang, Sharon, Lam, Barbara_D, Agrawal, Monica, Shen, Shannon, Kurtzman, Nicholas, Horng, Steven, Karger, David_R, & Sontag, David. Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing. Journal of the American Medical Informatics Association, 31 (7). https://doi.org/10.1093/jamia/ocae092
Jiang, Sharon, Lam, Barbara_D, Agrawal, Monica, Shen, Shannon, Kurtzman, Nicholas, Horng, Steven, Karger, David_R, and Sontag, David.
"Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing". Journal of the American Medical Informatics Association 31 (7). Country unknown/Code not available: Oxford University Press. https://doi.org/10.1093/jamia/ocae092.https://par.nsf.gov/biblio/10504580.
@article{osti_10504580,
place = {Country unknown/Code not available},
title = {Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing},
url = {https://par.nsf.gov/biblio/10504580},
DOI = {10.1093/jamia/ocae092},
abstractNote = {Abstract ObjectiveLeverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. Materials and MethodsWe trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment. ResultsThe metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user. DiscussionOur model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings. ConclusionEHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting.},
journal = {Journal of the American Medical Informatics Association},
volume = {31},
number = {7},
publisher = {Oxford University Press},
author = {Jiang, Sharon and Lam, Barbara_D and Agrawal, Monica and Shen, Shannon and Kurtzman, Nicholas and Horng, Steven and Karger, David_R and Sontag, David},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
An official website of the United States government
