AMIA ... Annual Symposium Proceedings / AMIA Symposium. AMIA Symposium[JOURNAL]
Sun
200 papers
Automated Image Registration Method for In Vivo Confocal Microscopy of the Corneal Sub-basal Nerve Plexus.
Siu N, Vinet M, Shettiwar P … +7 more , Tran T, Chen K, Stoddard-Bennett T, Bonnet C, Arnold C, Speier W, Deng SX
AMIA Annu Symp Proc · 2024 · PMID 41726503
In vivo confocal microscopy (IVCM) assesses corneal innervation in the sub-basal nerve plexus but is typically quantified manually from a single z-scan, limiting biomarker extrapolation for diagnosing limbal stem cell de...
In vivo confocal microscopy (IVCM) assesses corneal innervation in the sub-basal nerve plexus but is typically quantified manually from a single z-scan, limiting biomarker extrapolation for diagnosing limbal stem cell deficiency (LSCD). We developed an automated 3D reconstruction method of IVCM image volumes to improve sub-basal nerve density quantification. Our dataset comprised 99 IVCM stacks from 63 LSCD eyes (51 patients) and 23 stacks from 15 normal eyes. We designed an image registration algorithm combining phase correlation and homography transformation, which achieved a pairwise image correlation of 0.69 and mutual information of 0.60, significantly outperforming manual registration (0.60 and 0.43, respectively; p<0.001). Validation on an independent dataset of 325 volume scans from 24 eyes of 12 unilateral, severe LSCD patients yielded a correlation of 0.75 and MI of 0.76. This method enhances sequential IVCM scan alignment and supports more accurate, reproducible 3D evaluation of LSC biomarkers.
A Comprehensive Approach for Assessing the Impact of Ambient Documentation.
Siegrist C, Harberger S, Tavares S … +4 more , Obert K, Vawdrey DK, Hohmuth B, Stametz R
AMIA Annu Symp Proc · 2024 · PMID 41726502
Workforce challenges are a significant issue facing many healthcare organizations. One variable contributing to this market dynamic is provider burnout, which remains high and is largely driven by administrative demands...
Workforce challenges are a significant issue facing many healthcare organizations. One variable contributing to this market dynamic is provider burnout, which remains high and is largely driven by administrative demands that continue to increase. Healthcare organizations are rapidly adopting enabling digital capabilities, such as generative artificial intelligence (AI) technologies, that have the potential to decrease administrative burden. One such tool is ambient documentation, which aims to make clinical documentation workflows smarter and more efficient. In September 2024, ambient documentation became the first broad clinical use of generative AI at Geisinger, when the technology was deployed to 100 ambulatory providers. This paper outlines Geisinger's evaluation and implementation approach to ambient documentation and the impact this technology has made on administrative burden, provider burnout, and patient experience.
Predicting Early-Onset Colorectal Cancer with Large Language Models.
Lau W, Kim Y, Parasa S … +3 more , Haque ME, Oka A, Nanduri J
AMIA Annu Symp Proc · 2024 · PMID 41726501
The incidence rate of early-onset colorectal cancer (EoCRC, age < 45) has increased every year, but this population is younger than the recommended age established by national guidelines for cancer screening. In this pap...
The incidence rate of early-onset colorectal cancer (EoCRC, age < 45) has increased every year, but this population is younger than the recommended age established by national guidelines for cancer screening. In this paper, we applied 10 different machine learning models to predict EoCRC, and compared their performance with advanced large language models (LLM), using patient conditions, lab results, and observations within 6 months of patient journey prior to the CRC diagnoses. We retrospectively identified 1,953 CRC patients from multiple health systems across the United States. The results demonstrated that the fine-tuned LLM achieved an average of 73% sensitivity and 91% specificity.
To what Degree can LLMs Support Medical Informatics Research? Examining the Interplay of Research Support LLMs with LLM Critics.
Khatwani N, Wang L, Geller J
AMIA Annu Symp Proc · 2024 · PMID 41726500
The rapid development of Large Language Models (LLMs) has opened up new possibilities for their role in supporting research. This study assesses whether LLMs can generate "thoughtful" research plans in the domain of Medi...
The rapid development of Large Language Models (LLMs) has opened up new possibilities for their role in supporting research. This study assesses whether LLMs can generate "thoughtful" research plans in the domain of Medical Informatics and whether LLM-generated critiques can improve such plans. Using an LLM pipeline, we prompt four LLMs to generate primary research plans. Subsequently, these plans are mutually critiqued and then the LLMs are prompted to refine their outputs based on these critiques. These original and improved responses are then reviewed by human evaluators for errors, hallucinations, etc. We employ ROUGE scores, cosine similarity, and length differences to quantify similarities across responses. Our findings reveal variations in outputs among four LLMs, the impact of critiques, and differences between primary and secondary outputs. All LLMs produce cogent outputs and critiques, integrating feedback when generating improved outputs. Human evaluators can distinguish between primary and secondary responses in most cases.
Revisiting Disproportionality: Prescription-Adjusted and TF-IDF-Inspired Metrics for Post-Market ADR Detection.
Kaz-Onyeakazi I, Kim H
AMIA Annu Symp Proc · 2024 · PMID 41726499
Adverse drug reaction (ADR) detection in post-market surveillance is limited by underreporting and the absence of drug utilization data. This study proposes three signal detection metrics-including a TF-IDF-inspired meth...
Adverse drug reaction (ADR) detection in post-market surveillance is limited by underreporting and the absence of drug utilization data. This study proposes three signal detection metrics-including a TF-IDF-inspired method (EF-IDF) and two prescription-adjusted measures-to improve pharmacovigilance, using ADHD medications and the FDA Adverse Event Reporting System (FAERS) as a case study. We standardized drug and ADR entities, integrated prescription data from Bloomberg Intelligence, and evaluated performance across 12 ingredients using precision-at-10%. EF-IDF achieved the highest mean precision (0.56), significantly outperforming traditional PRR and prescription-adjusted metrics. Correlation analysis showed that prescription volume negatively influenced all metrics, particularly EF-IDF, underscoring the role of contextual factors in ADR detection. Despite limitations in temporal granularity and the lack of prescription data specific to ADHD use, this work demonstrates the value of bias-aware, data-integrated methods for signal detection. Future directions include temporal modeling and more targeted identification of ADHD-related prescriptions using public data.
Developing RxNorm Extension: A Step Toward Global Drug Data Harmonization in Observational Drug Research.
Ostropolets A, Zhuk A, Korchmar E … +2 more , Ryan P, Reich C
AMIA Annu Symp Proc · 2024 · PMID 41726498
This paper presents RxNorm Extension (RxE), a standardized drug vocabulary system designed to harmonize drug data across international databases. RxE integrates drugs from multiple national drug repositories, enhancing g...
This paper presents RxNorm Extension (RxE), a standardized drug vocabulary system designed to harmonize drug data across international databases. RxE integrates drugs from multiple national drug repositories, enhancing global drug safety and effectiveness research by standardizing drug representations in disparate drug vocabularies to a structure following RxNorm, a reference standard in the US. We developed an attribute-based mapping approach that improves consistency and reduce manual data processing. Based on 12 vocabularies included, we observe similar dose form and ingredient usage patterns but many more brand names available worldwide. The quality of RxE depends on the thorough examination of the source vocabulary, where challenges include discrepancies in brand names, poorly structured dosage forms, and faulty dosages. Despite the challenges, RxE has been used in numerous clinical and methodological studies. Future directions focus on expanding coverage, improving mapping automation, and fostering international collaboration to optimize global drug safety and effectiveness efforts.
EHR-Based Social Needs Screening and Referral in Primary Care: Clinician and Staff Perspectives on Practices, Barriers, and Benefits.
Ji Z, Wedgeworth P, Mertens K … +5 more , Jackson SL, Akinsoto NO, Klein JW, Isaac ML, Hartzler AL
AMIA Annu Symp Proc · 2024 · PMID 41726497
Identifying social drivers of health (SDoH) can help healthcare professionals connect patients with community resources that impact health outcomes. However, screening and referral require time and effort, highlighting t...
Identifying social drivers of health (SDoH) can help healthcare professionals connect patients with community resources that impact health outcomes. However, screening and referral require time and effort, highlighting the potential for electronic health record (EHR) support to improve efficacy. We surveyed primary care clinicians and staff (n=122) about current SDoH screening and referral practices, as well as perceived barriers and benefits for standardizing those practices with EHR support. Although the majority currently screen and refer patients for SDoH at least occasionally, most respondents document in the EHR using unstructured formats and rate current practices as only moderately feasible and acceptable. While the majority feel competent with SDoH screening, key barriers included time constraints, lack of dedicated staff, and a desire for access to more community resources. Findings underscore the need for an EHR-based standardized screening and referral implementation with flexibility to adapt workflows in different clinic settings and clinical positions.
Large Language Model-Powered Conversational Agent Delivering Problem-Solving Therapy (PST) for Family Caregivers: Enhancing Empathy and Therapeutic Alliance Using In-Context Learning.
Wang L, Carrington D, Filienko D … +5 more , El Jazmi C, Xie SJ, De Cock M, Iribarren S, Yuwen W
AMIA Annu Symp Proc · 2024 · PMID 41726496
Family caregivers often face substantial mental health challenges due to their multifaceted roles and limited resources. This study explored the potential of a large language model (LLM)-powered conversational agent to d...
Family caregivers often face substantial mental health challenges due to their multifaceted roles and limited resources. This study explored the potential of a large language model (LLM)-powered conversational agent to deliver evidence-based mental health support for caregivers, specifically Problem-Solving Therapy (PST) integrated with Motivational Interviewing (MI) and Behavioral Chain Analysis (BCA). A within-subject experiment was conducted with 28 caregivers interacting with four LLM configurations to evaluate empathy and therapeutic alliance. The best-performing models incorporated Few-Shot and Retrieval-Augmented Generation (RAG) prompting techniques, alongside clinician-curated examples. The models showed improved contextual understanding and personalized support, as reflected by qualitative responses and quantitative ratings on perceived empathy and therapeutic alliances. Participants valued the model's ability to validate emotions, explore unexpressed feelings, and provide actionable strategies. However, balancing thorough assessment with efficient advice delivery remains a challenge. This work highlights the potential of LLMs in delivering empathetic and tailored support for family caregivers.
A Machine-Assisted Framework for Ontology Development and Standardization: Case Study in Digital Health Technologies.
Chen F, Harrison TB, Fu S … +6 more , He L, Yue Z, Lu S, Wang L, Ruan X, Liu H
AMIA Annu Symp Proc · 2024 · PMID 41726495
Digital health technologies (DHTs) are reshaping healthcare by enabling personalized care, improving patient outcomes, and accelerating clinical research. However, the surge in DHT-related literature creates new challeng...
Digital health technologies (DHTs) are reshaping healthcare by enabling personalized care, improving patient outcomes, and accelerating clinical research. However, the surge in DHT-related literature creates new challenges in effectively organizing, retrieving, and applying the resulting knowledge. Ontologies, structured frameworks for categorizing and connecting concepts, are central to meeting these challenges. Traditional ontology development in digital health often depends on manual processes, limiting efficiency, scalability, and cross-disciplinary adaptability. Building on previous work categorizing DHTs, we propose a new framework combining DHT lexicon extraction, ontology enrichment, and human-in-the-loop validation. In this study, we illustrate how the concept of a "adaptive ontology," powered by large language models, can classify and enhance DHT ontologies systematically, yet semi-automatically. Thus, providing a practical path to managing the evolving landscape of digital health.
Mitigating Stigma and Fostering Support: Improving AI-Generated Counterspeech for Microaggressions.
Ryu H, Kang S, Pratt W
AMIA Annu Symp Proc · 2024 · PMID 41726494
In societies where sexual and reproductive health (SRH) is stigmatized, many women hesitate to seek care, increasing health risks. In South Korea, cultural norms associating promiscuity with SRH care in unmarried women f...
In societies where sexual and reproductive health (SRH) is stigmatized, many women hesitate to seek care, increasing health risks. In South Korea, cultural norms associating promiscuity with SRH care in unmarried women further discourage them from accessing care. While online spaces offer support, they also perpetuate stigma through microaggressions. To mitigate the harms of microaggressions, counterspeech provides a promising approach. This study examines counterspeech by generative artificial intelligence (AI) using ChatGPT-4 and Copilot GPT-4, analyzes the strategies AI tools claim to use, evaluates their alignment with recommended counterspeech strategies, and identifies potential harms. Our findings reveal critical limitations: failures to recognize implicit biases and challenge relevant stereotypes, placing the burden of addressing microaggressions onto those who experience them, and offering only superficial empathy. We propose a new process for AI to foster more effective and culturally sensitive counterspeech. With these improvements, AI could help create safer, more inclusive spaces for people seeking support for stigmatized healthcare.
Relation Extraction with Instance-Adapted Predicate Descriptions.
Jiang Y, Kavuluru R
AMIA Annu Symp Proc · 2024 · PMID 41726493
Relation extraction (RE) is a standard information extraction task playing a major role in downstream applications such as knowledge discovery and question answering. Although decoder-only large language models are excel...
Relation extraction (RE) is a standard information extraction task playing a major role in downstream applications such as knowledge discovery and question answering. Although decoder-only large language models are excelling in generative tasks, smaller encoder models are still the go to architecture for RE. In this paper, we revisit fine-tuning such smaller models using a novel dual-encoder architecture with a joint contrastive and cross-entropy loss. Unlike previous methods that employ a fixed linear layer for predicate representations, our approach uses a second encoder to compute instance-specific predicate representations by infusing them with real entity spans from corresponding input instances. We conducted experiments on two biomedical RE datasets and two general domain datasets. Our approach achieved F score improvements ranging from 1% to 2% over state-of-the-art methods with a simple but elegant formulation. Ablation studies justify the importance of various components built into the proposed architecture.
Leveraging Large Language Models for Cancer Vaccine Adjuvant Name Extraction from Biomedical Literature.
Rehana H, Zheng J, Yeh FY … +7 more , Bansal B, Çam NB, Jemiyo C, McGregor B, Özgür A, He Y, Hur J
AMIA Annu Symp Proc · 2024 · PMID 41726492
This study explores cancer vaccine adjuvant name recognition using Large Language Models (LLMs), specifically Generative Pretrained Transformers (GPT), Large Language Model Meta AI (Llama), and Gemma. The models were tes...
This study explores cancer vaccine adjuvant name recognition using Large Language Models (LLMs), specifically Generative Pretrained Transformers (GPT), Large Language Model Meta AI (Llama), and Gemma. The models were tested in zero- and few-shot learning paradigms using AdjuvareDB and Vaccine Adjuvant Compendium (VAC) datasets. Prompts were designed to extract adjuvant names and assess the impact of contextual details. Notably, Llama-3.2 3B achieved a Recall of up to 68.7% (72.5% with manual validation) on the VAC dataset with four-shots, although its Precision and F1-score were lower. In contrast, GPT-4o, with additional contextual interventions, achieved a Precision of 65.9%, Recall of 79.7%, and F1-score of 69.8% on the AdjuvareDB dataset. Gemma-2 9B also demonstrated moderate few-shot gains, peaking at 63.6% F1-score. These LLMs outperformed BioBERT, a model widely used for biomedical text mining, highlighting the potential of general-purpose LLMs for automatic vaccine adjuvant name extraction and contributing to advancements in vaccine research.
An LLM-Powered Clinical Calculator Chatbot Backed by Verifiable Clinical Calculators and their Metadata.
Kumar N, Seifi F, Conte M … +1 more , Flynn AJ
AMIA Annu Symp Proc · 2024 · PMID 41726491
Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages (1) software implementations of verifia...
Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages (1) software implementations of verifiable clinical calculators via LLM tools, and (2) metadata about these calculators via retrieval augmented generation (RAG). We compare its accuracy to an unassisted LLM on four natural language conversation workloads. Our chatbot achieves 100% accuracy on queries interrogating calculator metadata content and shows a significant increase in clinical calculation accuracy vs. the off-the-shelf LLM when prompted with complete sentences (86.4% vs. 61.8%) or with medical shorthand (79.2% vs. 62.0%). It eliminates calculation errors when prompted with complete sentences (0% vs. 16.8%) and greatly reduces them when prompted with medical shorthand (2.4% vs. 18%). While our chatbot is not yet ready for clinical use, these results show progress in minimizing incorrect calculation results.
Leveraging multi-source data to resolve inconsistency across pharmacogenomic datasets in drug sensitivity prediction.
Li X, Das T, Bhattarai K … +8 more , Rajaganapathy S, Buchner VC, Wang Y, Su C, Sun L, Wang L, Cerhan JR, Zong N
AMIA Annu Symp Proc · 2024 · PMID 41726490
Researchers have developed pharmacogenomics datasets for various purposes, such as biomarker identification, yet drug response prediction models often underperform due to dataset inconsistencies. These variations arise f...
Researchers have developed pharmacogenomics datasets for various purposes, such as biomarker identification, yet drug response prediction models often underperform due to dataset inconsistencies. These variations arise from inter-tumoral heterogeneity, experimental conditions, and cell subtype complexity, limiting model generalizability. To address this, we propose a computational model based on Aggregated Learning (AL) to enhance drug response prediction by learning from inconsistencies across multiple datasets. Our model minimizes discrepancies by training on overlapping inconsistent data points from three pharmacogenomic datasets-CCLE, GDSC2, and gCSI. Compared to four baseline methods-Selecting Better (SB), Result Average (RA), Combining Data (CD), and Model Average (MA)-our approach achieved superior performance with lower Mean Absolute Error (MAE) scores: 0.090 (CCLE-GDSC), 0.096 (CCLE-gCSI), and 0.081 (GDSC-gCSI). These results demonstrate that addressing inconsistencies enhances prediction accuracy and generalizability, making our model a promising solution for robust drug response predictions.
Enhancing Health Research Results Dissemination for American Indian and Alaska Native Communities through Indigenous Community-Centered Design.
Dirks LG, BearBow V, Pratt W
AMIA Annu Symp Proc · 2024 · PMID 41726489
American Indian and Alaska Native (AI/AN) communities not only face significant health disparities but are often underrepresented in health research dissemination. Existing communication tools may fail to effectively rea...
American Indian and Alaska Native (AI/AN) communities not only face significant health disparities but are often underrepresented in health research dissemination. Existing communication tools may fail to effectively reach these communities in culturally relevant and accessible ways, limiting their ability to benefit from critical health research. We co-designed and evaluated a prototype for health research results dissemination for AI/AN communities. We created and evaluated the prototype drawing from previous co-design workshops with AI/AN people. 38 participants completed an evaluation providing feedback for further iteration and highlighting key features such as search functionality, ease of use, visual and interactive elements, and content accessibility. Participants emphasized the importance of community connection, educational resources, and personalized experiences. We feature an alternative design approach we call Indigenous Community-Centered Design to create more accessible and engaging health research communication tools for AI/AN communities, fostering stronger connections and more accurate research representation.
Prospective Validation of a Suicide Event Risk Model in Transgender Patients.
Becker RA, Walsh CG
AMIA Annu Symp Proc · 2024 · PMID 41726488
Suicide risk prediction models offer a promising avenue for early intervention, but their effectiveness in underrepresented populations remain uncertain. This study evaluated VSAIL's, a real-world, externally validated,...
Suicide risk prediction models offer a promising avenue for early intervention, but their effectiveness in underrepresented populations remain uncertain. This study evaluated VSAIL's, a real-world, externally validated, and deployed suicide risk prediction model, performance in predicting suicide risk among transgender individuals. Transgender individuals were identified from electronic health record data and transgender status was verified via manual chart review. Results indicated modest discriminative ability (AUROC=0.777, AUPRC=0.115), however, a high rate of false negatives (77%), and significant miscalibration (Brier=0.023, Spiegelhalter's z-statistic p<0.001) reduced clinical utility. Findings underscore the importance of targeted subgroup validation and highlight limitations of general population-trained models in accurately identifying suicide risk among transgender patients. They also suggest the need for ongoing algorithm monitoring and subgroup-aware modeling strategies to improve predictive equity in marginalized populations.
Understanding Stigmatizing Language Lexicons: A Comparative Analysis in Clinical Contexts.
Zhou Y, Hu D, Lyu T … +4 more , Dhillon J, Beck AL, Sadigh G, Zheng K
AMIA Annu Symp Proc · 2024 · PMID 41726487
Stigmatizing language results in healthcare inequities, yet there is no universally accepted or standardized lexicon defining which words, terms, or phrases constitute stigmatizing language in healthcare. We conducted a...
Stigmatizing language results in healthcare inequities, yet there is no universally accepted or standardized lexicon defining which words, terms, or phrases constitute stigmatizing language in healthcare. We conducted a systematic search of the literature to identify existing stigmatizing language lexicons and then analyzed them comparatively to examine: 1) similarities and discrepancies between these lexicons, and 2) the distribution of positive, negative, or neutral terms based on an established sentiment dataset. Our search identified four lexicons. The analysis results revealed moderate semantic similarity among them, and that most stigmatizing terms are related to judgmental expressions by clinicians to describe perceived negative behaviors. Sentiment analysis showed a predominant proportion of negatively classified terms, though variations exist across lexicons. Our findings underscore the need for a standardized lexicon and highlight challenges in defining stigmatizing language in clinical texts.
Relational Database-Based Resource-Provenance Visualization Engine: with an application to BICAN data.
Li X, Huang Y, Ng L … +8 more , Smith KA, Chou WC, Abeysinghe R, Tong L, Lin S, Cui L, Tao S, Zhang GQ
AMIA Annu Symp Proc · 2024 · PMID 41726486
Provenance tracking ensures data integrity, security, and accountability in healthcare and biomedical research. As biomedical data grows in complexity, comprehensive tracking mechanisms are needed to maintain reproducibi...
Provenance tracking ensures data integrity, security, and accountability in healthcare and biomedical research. As biomedical data grows in complexity, comprehensive tracking mechanisms are needed to maintain reproducibility, transparency, and compliance with regulatory standards, such as GDPR. Traditional log-based and ontology-based approaches capture and standardize data lineage, while cryptographic and blockchain-based methods enhance security and verifiability. However, challenges remain in scalability, security, and usability. To address these, we introduce the Resource-Provenance Visualization Engine (RPVE), an advanced system integrating data lineage tracking and interactive visualization. RPVE employs the Randomized N-gram Hashing Identifier (NHash ID) to establish precise data links within the BRAIN Initiative Cell Atlas Network (BICAN) and features an interactive Sankey visualization engine for seamless data exploration. The system enhances provenance tracking by improving data retrieval efficiency, ensuring reliable verification processes, and maintaining data integrity.
Earlier ICU Transfer after CONCERN Early Warning System Score Escalation Reduced Sepsis-related Mortality: Results from a Multi-site Pragmatic Cluster Randomized Controlled Trial.
Lee RY, Cato KD, Dykes PC … +6 more , Lowenthal G, Cho S, Jia H, Daramola T, Tuteja S, Rossetti SC
AMIA Annu Symp Proc · 2024 · PMID 41726485
Early recognition and timely escalation of care are critical for improving sepsis outcomes. This post-hoc analysis of a multi-site clinical trial examined whether the timing of ICU transfer following CONCERN Early Warnin...
Early recognition and timely escalation of care are critical for improving sepsis outcomes. This post-hoc analysis of a multi-site clinical trial examined whether the timing of ICU transfer following CONCERN Early Warning System (EWS) score escalation was associated with in-hospital mortality among patients later diagnosed with sepsis. Among 54 patients with CONCERN score changes prior to unanticipated ICU transfer, shorter score-change-to-ICU-transfer time intervals were significantly associated with lower odds of in-hospital death. A 36-hour threshold emerged as a potential inflection point; all patients transferred after this time interval died in the hospital. No significant differences were observed in the ICU-arrival-to-sepsis time interval between early and late transfers. These findings highlight the importance of acting promptly on early warning systems and suggest that CONCERN EWS may offer a meaningful lead time for intervention improving outcomes for sepsis patients.
Automating Patient Safety Workflows: The Development and Implementation of LLaMPS, a Secure Large Language Model Application.
Schaeferle GM, Zhou M, Patel S … +10 more , Kuanar S, Lamers J, Abbas M, Devkaran S, Nienow J, Nagel JJ, Ramar K, Enayati M, Dowdy SC, Ngufor C
AMIA Annu Symp Proc · 2024 · PMID 41726484
Despite significant advancements in Generative Artificial Intelligence (GenAI), practical adoption in healthcare, particularly patient safety, remains challenging due to concerns regarding data privacy, model transparenc...
Despite significant advancements in Generative Artificial Intelligence (GenAI), practical adoption in healthcare, particularly patient safety, remains challenging due to concerns regarding data privacy, model transparency, clinical relevance and user engagement. We present LLaMPS (Large Language Model for Patient Safety), a locally deployed GenAI platform designed to enhance patient safety event management and reporting. LLaMPS integrates automated incident classification, harm-level prediction, intelligent search, and an interactive chatbot. The system employs a Retrieval-Augmented Generation (RAG) approach, leveraging secure, institutionally hosted large language models (LLMs) and a vector database to ensure data privacy and regulatory compliance. Developed iteratively with direct input from clinicians and patient safety experts, LLaMPS demonstrates high classification accuracy and improved user satisfaction, underscoring the potential of locally controlled AI solutions to enhance patient safety workflows.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe