MétaCan
Menu
Back to cohort

Predicting 30-Day Readmissions in Patients With Heart Failure Using Administrative Data: A Machine Learning Approach

2021· article· en· W4200044765 on OpenAlexafffund
Vishal Sharma, Vinaykumar Kulkarni, Finlay A. McAlister, Dean T. Eurich, Shanil Keshwani, Scot H. Simpson, Don Voaklander, Salim Samanani

Bibliographic record

VenueJournal of Cardiac Failure · 2021
Typearticle
Languageen
FieldMedicine
TopicHeart Failure Treatment and Management
Canadian institutionsBoehringer Ingelheim (Canada)University of Alberta
FundersMitacs
KeywordsMedicineReceiver operating characteristicLikelihood ratios in diagnostic testingMachine learningDecision treePredictive valuePredictive modellingArtificial intelligenceClassifier (UML)Heart failureStatisticsArtificial neural networkEmergency medicineInternal medicineComputer scienceMathematics

Abstract

fetched live from OpenAlex

BACKGROUND: We sought to develop machine learning (ML) models trained on administrative data which predict risk of readmission in patients with heart failure and to evaluate and compare the ML model with the currently used LaCE score using clinically informative metrics. METHODS AND RESULTS: This prognostic study was conducted in Alberta, Canada, on 9845 patients with confirmed heart failure admitted to hospital between 2012 and 2019. The outcome was unplanned all-cause hospital readmission within 30 days of discharge. We used 80% of the data for the ML model development and 20% for independent validation. We reported, using the validation set, c-statistics (area under the receiver operating characteristic curves)and performance metrics (likelihood ratio, positive predictive values) for the XGBoost model and a modified LaCE score within their respective predictive thresholds. Boosted tree-based classifiers had higher area under the receiver operating characteristic curves (0.65 for XGBoost) compared with others (0.58 for neural networks) and 0.57 for the modified LaCE. Within the predicted threshold range of the XGBoost classifier, the positive likelihood ratio was 1.00 at the low end of predicted risk and 6.12 at the high end, resulting in a positive predictive value (post-test probability) range of 21%-62%; the pretest probability of readmission was 20.9% using prevalence. The corresponding positive likelihood ratios and positive predictive values across LaCE score thresholds were 1.00-1.20 and 21%-24%, respectively. CONCLUSIONS: Despite predicting readmissions better than the LaCE, even the best ML model trained on administrative health data (XGBoost) did not provide substantially informative prediction performance as it only generated a moderate shift from pre to post-test probability. Health systems wishing to deploy such a tool should consider training ML models with additional data. Adding other techniques like natural language processing, along with ML, to use other clinical information (like chart notes) might improve prediction performance.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.018
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.012
Threshold uncertainty score0.025

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.018
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.002
Science and technology studies0.0010.000
Scholarly communication0.0020.001
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.036
GPT teacher head0.300
Teacher spread0.264 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations44
Published2021
Admission routes2
Has abstractno

Explore more

Same venueJournal of Cardiac FailureSame topicHeart Failure Treatment and ManagementFrench-language works237,207