cs.AINov 18, 2026

A Neurosymbolic Multimodal Framework for 30-Day Diabetic Readmission Prediction: Integrating Structured EHR Data, Dense Clinical Embeddings, and Knowledge-Grounded Symbolic Extraction

Authors: Una Suman Kumar Patro, Sibangi Subhadarsani, Narendra Badam

Organizations: Independent Researcher, Celina, TX 75009, USA

Abstract

Unplanned 30-day readmissions among patients with diabetes mellitus impose a substantial clinical and economic burden, yet most predictive models use only structured electronic health record (EHR) data and ignore free-text clinical notes, which often contain code-mixed Hindi-English (Hinglish) phrasing and negation that general-purpose language models parse unreliably. We propose a neurosymbolic multimodal framework evaluated on the public Diabetes 130-US Hospitals dataset (101,766 encounters; 71,518 patients) with a patient-level grouped 80/20 split. Three streams are fused: engineered structured features; 32 components of Bio_ClinicalBERT note embeddings obtained by truncated singular value decomposition; and symbolic entities extracted by an open-weight clinical language model within a three-stage hybrid retrieval-augmented generation pipeline (dense retrieval, sparse lexical retrieval, and cross-encoder re-ranking) with reflective negation auditing. A cost-sensitive XGBoost classifier with a decision threshold calibrated by Youden's J statistic produces the prediction. On the held-out test cohort (n = 20,153), the structured baseline achieved an area under the receiver operating characteristic curve (AUROC) of 0.6477, sensitivity of 0.5839, and Brier score of 0.1080. The full multimodal model achieved the highest sensitivity (0.6667; +8.28 percentage points), the best F2-score (0.3824), and the lowest Brier score (0.0977), at a slightly lower AUROC (0.6375) and specificity (0.5161). Shapley additive explanations showed that prior utilization dominates risk, with compressed narrative components among the top predictors. On a 500-note code-switched benchmark, grounded retrieval raised Hinglish symptom recall from 4.8% to 40.2% and precision from 3.1% to 45.2%, while reducing entity hallucinations from 1.74 to 0.00 per note.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV

    Sep 14, 2026Mohamad Najafi, Hongyun Fu, Mathias Brochhausen +2Clinical Outcome PredictionElectronic Health Records

  2. Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis

    Oct 9, 2026Hamza Shafiq, Jialu Tang, Ting Dang +2Clinical Outcome PredictionMultimodal Fusion

  3. Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction

    Jul 10, 2026Nikkie Hooman, Zhongjie Wu, Eric C. Larson +1Multimodal RobustnessClinical Prediction