Chathuri Daluwatte, PhD

👉🏼 Enhancing readability of USFDA patient communications through large language models: a proof-of-concept study 🤓 Kannan Sridharan 👇🏻 https://lnkd.in/e3sXi3Yn 🔍 Focus on data insights: - Large language models (LLMs) significantly improved the readability of USFDA patient communications. - Original materials were challenging to read, with high grade levels for drug safety communications (DSCs) and medication guides (MGs). - LLM outputs simplified the materials to more accessible reading levels without compromising technical accuracy or key messages. 💡 Main outcomes and implications: - LLMs can enhance the readability of complex health-related information, benefiting patients with average reading abilities. - Simplifying patient communications through LLMs can improve patient understanding and engagement with important drug safety information. - Future research should explore extending these findings to other languages and patient groups in real-world healthcare settings. 📚 Field significance: - Health communication - Patient education - Language models in healthcare 🗄️: [#healthcommunication #patienteducation #languagemodels]

👉🏼 Criteria2Query 3.0: Leveraging generative large language models for clinical trial eligibility query generation 🤓 Jimyung Park 👇🏻 https://lnkd.in/eEvH3Xhi 🔍 Focus on data insights: - GPT-4 achieved an F1-score of 0.891 in concept extraction. - 29 errors were detected in SQL generation, with logic errors being the most common. - Reasoning evaluations showed high coherence but relatively lower readability. 💡 Main outcomes and implications: - GPT-4 significantly improves the accuracy of extracting clinical trial eligibility criteria concepts in C2Q 3.0. - Continued research is warranted to ensure the reliability of large language models. 📚 Field significance: - Automation of patient identification in clinical research. - Advancements in leveraging large language models for query generation. 🗄️: #clinicalresearch #GPT-4 #datainsights #automation

👉🏼 Text summarization with ChatGPT for drug labeling documents 🤓 Lan Ying 👇🏻 https://lnkd.in/eSTq3YX2 🔍 Focus on data insights: - ChatGPT-generated summaries closely resembled those produced by human experts - Greater similarity observed in summarizing drug safety information 💡 Main outcomes and implications: - ChatGPT's potential to accelerate work in critical areas, including drug safety 📚 Field significance: - Automation of text summarization using large language models like ChatGPT - Enhancing efficiency and accuracy in summarizing drug labeling documents 🗄️: [#drugdiscovery #textsummarization #ChatGPT #datainsights]

Explore the powerful potential of large language models in healthcare! This insightful article delves into how LLMs like Flan-T5 are identifying social determinants of health (SDoH) from electronic health records. Learn how AI advancements can help uncover critical insights and minimize algorithmic bias in healthcare. 📌 Learn More: https://lnkd.in/gdWcAzu2 #SDOH #EHR #Healthcare #AIinhealthcare #LLMs #NLP #Naturallanguageprocessing #DigitalHealth

👉🏼 Text summarization with ChatGPT for drug labeling documents 🤓 Lan Ying 👇🏻 https://lnkd.in/e-tvY6Pc 🔍 Focus on data insights: - ChatGPT-generated summaries closely resembled those produced by human experts - Greater similarity observed in summarizing drug safety information 💡 Main outcomes and implications: - ChatGPT's potential to accelerate work in critical areas, including drug safety 📚 Field significance: - Automation of text summarization using large language models like ChatGPT - Improved efficiency and accuracy in summarizing drug labeling documents 🗄️: [#drugdiscovery #textsummarization #ChatGPT #datainsights]

👉🏼 Clinical and Surgical Applications of Large Language Models: A Systematic Review 🤓 Sophia M Pressman 👇🏻 https://lnkd.in/enYZQYHc 🔍 Focus on data insights: - LLMs have the potential to enhance healthcare delivery through assisting in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. - In surgical settings, LLMs can aid surgeons with documentation, surgical planning, and intraoperative guidance. 💡 Main outcomes and implications: - LLMs can be valuable tools to complement the expertise of healthcare professionals in clinical and surgical settings. - Addressing limitations and concerns related to accuracy and biases is crucial for the effective utilization of LLMs. 📚 Field significance: - Advancements in LLM technology have significant implications for improving healthcare practices and patient outcomes. - Understanding the role of LLMs in clinical and surgical applications is essential for maximizing their benefits while mitigating potential risks. 🗄️: [#LargeLanguageModels #HealthcareDelivery #ClinicalApplications #SurgicalApplications]

👉🏼 Symptom-BERT: Enhancing Cancer Symptom Detection in EHR Clinical Notes 🤓 Nahid Zeinali 👇🏻 https://lnkd.in/eDWQRGQZ 🔍 Focus on data insights: - The study utilized a pre-trained language model to identify cancer symptoms in clinical notes. - Symptom-BERT demonstrated high efficacy in detecting cancer symptoms with impressive F1-score and AUC metrics. - Physical symptoms like Pruritus were identified with higher performance compared to psychological symptoms such as Anxiety. 💡 Main outcomes and implications: - Specialized pre-training on domain-specific data significantly boosted the performance of language models for medical applications. - The exceptional efficacy of Symptom-BERT in detecting cancer symptoms signifies a groundbreaking advancement in patient-centered AI technologies. - This advancement offers a promising avenue to enhance symptom management and improve patient self-care outcomes. 📚 Field significance: - Advanced language models like Symptom-BERT can revolutionize the detection and management of cancer symptoms in clinical settings. - Leveraging data insights from clinical notes can lead to more accurate and personalized symptom prediction algorithms, enhancing patient care and outcomes. 🗄️: [#cancer #symptoms #EHR #clinicalnotes #AI #patientcare]

👉🏼 Appropriateness of ChatGPT in Answering Heart Failure Related Questions 🤓 Ryan C King 👇🏻 https://lnkd.in/e2e82tuB 🔍 Focus on data insights: - GPT-4 provided 100% correct responses to heart failure-related questions. - GPT-4 displayed a higher proportion of comprehensive knowledge compared to GPT-3.5. - Both models showed high reproducibility in their responses. 💡 Main outcomes and implications: - ChatGPT, specifically GPT-4, can accurately and reliably answer heart failure-related questions. - ChatGPT may be a valuable resource for providing health-related information and education to patients with heart failure. - Further validation and testing are needed to ensure patient safety and equity across all demographics. 📚 Field significance: - Potential use of ChatGPT as a supplemental resource for patients with heart failure. - Importance of rigorous testing and validation for ChatGPT in healthcare settings. 🗄️: #datainsights #healthcare #heartfailure #ChatGPT

#LLMs are the transformers in #healthcare. LLMs have democratized data; through open access to huge amounts of information. They are becoming tools used in healthcare to improve patient care. But is this improvement being studied carefully enough? measured? reported (when there is an error or when it does not work safely, effectively, ethically and without bias)? They can serve as a better communication tool between patient and clinician, patient and healthcare system (is this what patients and clinicians want? I think yes). ...and not to be overlooked, LLMs and RPAs are being used as a tools between the clinician/hospital/healthcare system and payors for things such as prior authorizations and denials. The chatbot wars have begun (but what are the wars over? patients, care, or $$). Effective evaluation and implementation seems to be lagging behind the creation of LLMs in the healthcare space. I think LLMs have great potential in healthcare, but caution is necessary because patient's lives and health are at risk which is different than LLMs or RPAs application in many other industries. I hear how LLMs embedded within our #EHRs and #ambient #intelligence will decrease physician documentation burden by creating daily progress notes and other documentation for us, ...but has anyone considered that this documentation is part of the necessary cognitive process of patient care? For me, it is. Before I create my notes, I am gathering data from multiple sources (vital signs, labs, radiology studies, bedside examinations of critically ill patients, conversations with bedside nurses, consultants, colleagues, respiratory therapists, OT/PT, neonatal nurse practitioners, residents, students, social workers, parents...) and then I develop a care plan while going through a complex mental processing of these many data elements and then pull it together using 25 years of medical experience/knowledge/wisdom. The note provides me time and space to connect these many data dots into a comprehensive plan. Effective ICU plans require adaptation as data changes, sometimes in minutes and hours. I am not sure how much a LLM or AI can help me with this. I do know one thing for certain--- no one creating these models has asked me how they can help me improve my cognitive processes involved in patient care and that's what I want. Has anyone asked you? Therein lies a huge problem. A one sized fits all application of AI in healthcare is doomed for failure. What works in an adult ICU will likely not work in the Neonatal ICU. Don't get me wrong. I am excited about the potential of LLMs, ML, DL, computer vision and other AI tools in making our healthcare better for our patients and families. CAUTION as I am a guardian as a pediatric healthcare leader. #UsingWhatWeHaveBetter https://lnkd.in/dYFiwyMv

👉🏼 Redefining Health Care Data Interoperability: Empirical Exploration of Large Language Models in Information Exchange 🤓 Dukyong Yoon 👇🏻 https://lnkd.in/eeJTXmMa 🔍 Focus on data insights: - Advanced language models, such as Large Language Models (LLMs), can significantly enhance health care data interoperability. - LLMs demonstrate high accuracy and efficiency in transforming and exchanging medical data. - The study showcases the potential of LLMs in overcoming challenges related to nonstandardized or unstructured medical records. 💡 Main outcomes and implications: - LLMs show a high conversion accuracy in transforming laboratory results and diagnostic codes. - LLMs offer enhanced consistency in diagnostic code conversion compared to traditional mapping approaches. - LLMs exhibit a positive predictive value in extracting specific information from unstructured clinical records. 📚 Field significance: - The findings suggest that LLMs have the potential to revolutionize health care data exchange by streamlining information transfer and improving interoperability. - LLMs could reduce the complexity associated with standardizing medical terms and data structures, leading to more efficient data sharing in the healthcare industry. 🗄️: #HealthCare #DataInteroperability #LanguageModels #MedicalDataExchange