MétaCan
Menu
Back to cohort

Data-Driven Machine Learning Approaches to Cut Hospital Readmissions in USA

2025· article· W4415518076 on OpenAlexaff
Tahmidur Rahman Chowdhury, Mizanur Rahman, Faysal Ahmed, Shamima Afrose, M. M. H. Bhuiyan

Bibliographic record

VenueInternational Journal of Research and Innovation in Applied Science · 2025
Typearticle
Language
FieldComputer Science
TopicMachine Learning in Healthcare
Canadian institutionsInstitute of Health Economics
Fundersnot available
KeywordsGeneralizability theoryHealth careWorkflowRandom forestClinical decision support systemTelehealthPredictive powerPatient confidentialityVariety (cybernetics)

Abstract

fetched live from OpenAlex

Readmissions in hospitals are a major challenge to healthcare systems globally and lead to increased cost, burden on clinical resources, and poor patient outcomes. Conventional methods of identifying readmission risk that commonly rely on rule-based models and clinician judgment have demonstrated poor predictive validity. New developments in machine learning (ML) offer potent alternatives, via the utilization of vast amounts of structured and unstructured healthcare information to detect intricate patterns, related to the risk of readmission. This paper will discuss the use of machine learning models, including logistic regression, random forests, gradient boosting and deep learning, to predict hospital readmissions in a variety of patients. We speak about the contribution of electronic health records (EHRs), demographic factors, comorbidities, medication adherence, and post-discharge follow-up variables to the enhanced model performance. Explainable AI methods are given a special focus to make the model prediction transparent and trusted by clinicians. Other important challenges that are identified in the review are data quality, class imbalance, bias, and generalizability in healthcare settings. Case studies reveal how predictive models can be used to initiate specific interventions, including improved discharge planning, telehealth monitoring, and tailored care coordination, which can in turn lead to a reduction in avoidable readmissions and eventually lead to better patient outcomes. A combination of machine learning with clinical workflows will enable healthcare organizations to transition to more proactive, data-driven, and cost-beneficial care. The results highlight the disruptive power of machine learning to solve the long-standing problem of hospital readmissions and define the areas of future research in designing ethical applications, interoperability, and policy.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.018
metaresearch head score (Gemma)0.008
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesBibliometrics, Scholarly communication, Open science, Research integrity
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 score0.814
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0180.008
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0120.018
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0060.004
Research integrity0.0000.003
Insufficient payload (model declined to judge)0.0000.000

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 head0.232
GPT teacher head0.451
Teacher spread0.219 · 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 teacher head, not a consensus.

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueInternational Journal of Research and Innovation in Applied ScienceSame topicMachine Learning in HealthcareFrench-language works237,207