Jul 2026· 2026 7th International Conference on Smart Systems and Inventive Technology (ICSSIT)· pp. 1290-1295· 0 citations· 17 references
Abstract
Clinical text is an important part of healthcare systems because it is used to store and manage patient information in documents such as discharge summaries, doctor notes, and diagnostic reports. Among these documents, discharge summaries are especially important because they provide a brief overview of a patient’s diagnosis, treatment procedures, medications, and follow-up instructions after hospitalization. These summaries are also useful for healthcare research and medical data analysis. However, strict privacy regulations and hospital policies restrict access to real clinical records, making it difficult for researchers to collect large datasets for developing and testing machine learning models in healthcare. To address this issue, this study proposes a framework for generating and validating synthetic clinical discharge summaries using transformer-based biomedical language models. Initially, the clinical text is preprocessed using cleaning, formatting, and tokenization techniques to improve consistency and readability. Biomedical language models such as BioBERT, RoBERTa, and DistilBERT are then used to generate contextual embeddings and capture semantic relationships within medical text. In addition, semantic similarity analysis, entailment-based validation, and faithfulness evaluation are applied to verify the consistency and reliability of the generated summaries while preserving patient privacy and maintaining clinical relevance.
Abstract Objectives Clinical documentation consumes substantial clinician time, potentially detracting from patient care. Generative artificial intelligence (AI) may support drafting discharge summaries and patient referral documents, but feasibility in non-Western-language oncology settings using real-world electronic health record (EHR) data remains insufficiently evaluated. This study assessed feasibility in a Japanese cancer hospital using an enterprise AI system. Methods Medical records from 61 consenting adult patients at Chiba Cancer Center were analyzed. Although the plan aimed at comprehensive EHR data, actual input was limited to extractable text (physician notes, nursing records); structured laboratory data and imaging, endoscopy, and pathology reports were not directly used, and existing summaries and external referrals were excluded to avoid information leakage. Data were converted to JavaScript Object Notation; GaiXer generated 31 discharge summaries and 30 referral documents. Four evaluators scored them; ≥80/100 was an exploratory threshold for draft-level practical utility. Feedback drove one refinement cycle. Results Generated documents scored approximately 60 to 70. A score ≥80 was reached by 9 of 31 discharge summaries in each evaluation; for referrals, none reached the threshold initially, whereas 5 of 30 did after refinement. Discharge summary scores did not substantially improve; referral scores did. Raw percent agreement among three nonphysician evaluators was high, although chance-corrected agreement varied. Wilcoxon signed-rank tests showed no significant change for discharge summaries ( p = 0.866) but significant improvement for referrals ( p = 0.006). Conclusion This feasibility study suggests AI may support drafting these documents in a secure environment using real-world Japanese EHR data, although the generated documents did not consistently reach the predefined threshold for draft-level utility. Findings should not be interpreted as demonstrating workload reduction or maximum performance under ideal data conditions. Future studies should evaluate larger datasets, multiple institutions and models, blinded evaluations, actual editing time, clinician acceptance, and workflow impact.
N. Michihata, Hiroshi Ishii, H. Tsujimura et al.· Applied Clinical Informatics· 0 citations
Effective detection of ADEs in clinical notes may benefit from NLP models that approximate the clinical reasoning of health care providers as models evolve.
Alan Katz, Abhishek Dhankar, Gillian Fransoo et al.· Journal of Medical Internet...· 0 citations
Hospital readmission following discharge remains a persistent challenge because clinically relevant risk indicators
are distributed across narrative discharge summaries, medication histories, diagnostic findings, follow-up instructions,
social factors, and fragmented health-information systems. This study proposes an artificial-intelligence framework for
predicting hospital readmission and strengthening transitions of care through integrated analysis of Consolidated Clinical
Document Architecture (C-CDA) discharge summaries and Fast Healthcare Interoperability Resources (FHIR)-enabled
clinical data. A novel algorithm, termed C2FHIR-ReadmitNet, is developed to combine transformer-based clinical language
representation, structured FHIR resource embeddings, temporal transition modelling, and cross-modal attention for
patient-level readmission risk estimation. The framework extracts clinically significant concepts from C-CDA sections
including diagnoses, discharge medications, procedures, laboratory findings, allergies, functional status, care instructions,
and follow-up plans and maps them to standardized FHIR resources such as Patient, Encounter, Condition, Observation,
MedicationRequest, Procedure, CarePlan, and ServiceRequest. C2FHIR-ReadmitNet employs a clinical transformer
encoder for contextual text representation, a resource-aware embedding network for structured FHIR features, a temporal
attention module for modelling longitudinal encounters, and a calibrated risk-classification layer for estimating 30-day
readmission probability. The proposed model is comparatively evaluated against Logistic Regression, Random Forest,
XGBoost, Bidirectional Long Short-Term Memory networks, ClinicalBERT, and conventional multimodal fusion models
using AUROC, AUPRC, accuracy, precision, recall, F1-score, sensitivity, specificity, Brier score, and calibration error.
Comparative ROC curves, precision-recall curves, calibration plots, confusion matrices, feature-importance graphs, and
ablation-analysis charts are incorporated to examine predictive discrimination, reliability, interpretability, and the
contribution of individual architectural components. The study further introduces a transition-of-care risk index that
integrates predicted readmission probability with medication complexity, unresolved clinical concerns, follow-up urgency,
comorbidity burden, and continuity-of-care indicators to support post-discharge prioritization. The experimental design is
structured to determine whether C2FHIR-ReadmitNet can achieve superior predictive discrimination, calibration, and
clinical interpretability relative to conventional machine-learning and transformer-based baselines while preserving
semantic interoperability across heterogeneous electronic health-record environments. The proposed approach provides a
technically scalable foundation for converting C-CDA discharge information into FHIR-compatible, AI-assisted decision
intelligence capable of supporting early identification of high-risk patients, targeted transitional-care interventions,
interoperable clinical workflows, and data-driven reduction of avoidable hospital readmissions.
Unknown authors· International Journal of Inn...· 0 citations
This review provides researchers and practitioners with a structured framework for method selection based on their specific constraints and identifies six prioritized research directions for future investigation, identifying critical research gaps including the preservation of multi-word clinical concepts, scarce evaluation in real-world clinical workflows, and persistent hallucination risks in model-based extraction.
This approach combines semantic understanding of clinical narratives with structural modeling of patient-disease-treatment relationships and successfully validates synthetic EHR data utility for privacy-preserving healthcare AI development while addressing critical requirements necessary for clinical decision support system.
U. Luke, P. Asuquo, Victor Anaga et al.· E3S Web of Conferences· 0 citations
Text2FHIRwallet demonstrates that domain-specific fine-tuning of a Portuguese-language pretrained language model achieves near-ceiling clinical NER accuracy, enabling scalable, interoperable, and privacy-compliant patient summary generation from unstructured cardiology text, offering an end-to-end pathway for integrating AI-driven NLP into clinical workflows and FHIR-based health information ecosystems.
João C. Ferreira, Isabel Rosa, Ricardo Correia· Applied Sciences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
