Search

Hospital discharge summaries are critical for care transitions, directly impacting readmission prevention and medication reconciliation, yet physicians spend 15-30 minutes per patient drafting these documents, contributing substantially to documentation burden and professional burnout. Manual summarization of daily progress notes and laboratory results is repetitive, time-consuming, and error-prone, as clinicians must sift through lengthy unstructured notes across multiple hospital days while identifying salient events and trends. We propose a large language model with parameter-efficient fine-tuning for automated discharge summary generation that processes chronologically ordered daily progress notes alongside time-series laboratory results to produce structured discharge documentation. The framework consists of a base LLM augmented with LoRA adapters, a progress note encoder for section segmentation, a laboratory result integrator that computes trend indicators, and a summary generator that produces sectioned discharge output. Parameter-efficient fine-tuning enables domain adaptation to clinical text with minimal computational resources, preserving patient-specific information while reducing hallucination through retrieval of key factual details from the input notes. This framework offers a practical pathway to reduced documentation burden and improved discharge quality, with potential for widespread deployment across health systems given the modest computational requirements of PEFT approaches.

Healthcare administration generates large volumes of textual data, including clinical notes, billing documentation, incident narratives, portal messages, and operational records. These data create administrative burden but also provide opportunities for natural language processing to support documentation, coding, communication, safety review, and workflow automation. This systematic review examined natural language processing models applied to healthcare administration from 2017 to 2024. The review focused on five domains: clinical documentation, coding support, incident reporting, patient communication, and workflow automation. A PRISMA 2020-compliant review was conducted using structured searches of PubMed, Scopus, IEEE Xplore, and Web of Science for studies published between 2017 and 2024. Eligible studies were screened by two reviewers, extracted using a structured template, and synthesized narratively by administrative domain, model type, evaluation approach, and implementation maturity. Transformer-based models were increasingly prominent across the reviewed literature, particularly in documentation support, automated coding, and clinical text classification. Clinical documentation and coding support had the strongest evidence base, while incident reporting, patient communication, and workflow automation remained less mature and less frequently evaluated in real-world settings. Natural language processing for healthcare administration is technically promising, but most applications remain at the retrospective or proof-of-concept stage. Prospective validation, workflow integration, governance, and human oversight are needed before widespread operational adoption.

Prior authorization delays impede timely patient care and contribute to administrative pressure across clinical and revenue cycle workflows. These delays can affect scheduling, medication access, procedural planning, and patient confidence in the care process. Current authorization management tools are largely reactive and often focus on tracking request status after submission. They rarely predict which requests are likely to experience approval delays or explain the operational, clinical, or payer-specific reasons behind those delays. This article proposes an interpretable machine learning model for predicting the likelihood of prior authorization approval delays. The model is designed to provide transparent, request-level explanations that can guide pre-submission correction and authorization preparation. The proposed framework uses a gradient-boosted tree model trained conceptually on historical authorization requests. Inputs include payer-specific rules, clinical documentation features, procedure type, medical necessity indicators, and historical approval timelines, with SHAP used to attribute predicted delay risk to individual features. Conceptually, the model would output a delay probability and an explanation of the dominant drivers of that prediction. These drivers could include incomplete documentation, mismatch with payer medical necessity criteria, procedure categories associated with additional review, or payer-procedure combinations with historically slow turnaround. An interpretable prior authorization delay model could support earlier correction of incomplete requests, reduce administrative waste, and improve patient access. By aligning predictive analytics with transparent explanations, the framework could make authorization preparation more proactive and accountable.