Nick Tarazona, MD’s Post

Data is at the heart of fighting cancer as it’s central to finding effective ways to prevent, diagnose, and treat the disease. The challenge, however, is that much of the data in healthcare is unstructured, such as clinical notes, surgical and lab reports, clinical trial data, and discharge notes. A prominent US-based healthcare provider recognized the importance of unstructured data for all cancer-related activities. Given the volume and complexity of the work, they knew they needed assistance from a company that had Natural Language Processing expertise, experience with the applied tooling, as well as a deep understanding of medical terminology. They turned to the US team of Klarrio. 💭Klarrio’s solution: To enable the client to find and extract the information needed for their research in large volumes of unstructured data, Klarrio’s initial task was to assess an existing set of annotators to improve their accuracy. Klarrio had the added objective of making the maintenance of the annotators more efficient. To perform the work, Klarrio devised a process for redeveloping the annotators, which included the following:  • Developing and applying tooling to determine the rules and dictionary dependencies for each annotator. This led to the elimination of unused rules, restructuring existing dictionaries, and generating new dictionaries.     • Introducing reusable models to make maintenance of the annotators more efficient  • Establishing Gold Standard document samples for each of the annotators and assessing the annotators against them for accuracy. This approach was applied to assess and improve additional existing annotators as well as the development of new annotators. ✅Result: improved accuracy & a cleaner system. To find out more about this project, visit the link in the comments section ⬇ #healthcare #data #medical #medicalrecords #dataengineering #dataengineer #opensource #dataanalytics #cancerresearch #languageprocessing

It’s good to read about all the developments taking place with Artificial Intelligence and healthcare and the utilization of LLM and the challenges with its adoption. Happy to be apart of organizations, such as CHAI (Coalition for Health AI) who are providing guidance for model developers. #transparency #llm #ethicalai #CHAI Brenton Hill, JD, MHA Shauna M. Overgaard, Ph.D. Nicoleta Economou Christine Swisher, PhD

👉🏼 Capability of GPT-4V(ision) in the Japanese National Medical Licensing Examination: Evaluation Study 🤓 Takahiro Nakao 👇🏻 https://lnkd.in/eanx_vjg 🔍 Focus on data insights: - GPT-4V's accuracy was 68% when presented with images and 72% when presented without images. - The accuracies with and those without images were different for clinical and general question categories. 💡 Main outcomes and implications: - The additional information from images did not significantly improve the performance of GPT-4V in the Japanese National Medical Licensing Examination. 📚 Field significance: - Evaluating the image recognition capability of GPT-4V in the medical field. - Understanding how visual information affects the performance of large language models in answering questions. 🗄️: [#GPT-4V, #medical field, #image recognition, #data insights]

👉🏼 A Novel Approach for Mixed-Methods Research Using Large Language Models: A Report Using Patients' Perspectives on Barriers to Arthroplasty 🤓 Insa Mannstadt https://lnkd.in/ev69pF4m 🔍 Focus on data insights: - ChatGPT-4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. - The survey questions generated by ChatGPT-4 were less precise than those developed by human investigators. 💡 Main outcomes and implications: - The study proposes integrating Large Language Models (LLMs) and human investigators as a supplementary tool for preliminary thematic analysis of qualitative data and survey generation. - By utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may conduct more efficient mixed-methods research to better understand patient perspectives. 📚 Field significance: - Efficient mixed-methods research using LLMs and human investigators can provide valuable insights into patient perceptions and improve understanding in healthcare research. 🗄️: [#mixedmethods #healthcare #patientperspectives #LLMs]

Using RAG (Retrieval Augmented Generation) with Large Language Models (LLMs) to get answers to your health related questions needs careful implementation and using right data sources, yet this may not be best solution to get the most accurate answer. Learn more from this article: https://lnkd.in/g-BvfHex

🔗 **Large Language Models in Healthcare: Are We There Yet?** Challenges persist as large language models (LLMs) show promise in healthcare. Stanford HAI’s recent review highlights key insights and areas needing improvement. - Only 5% of studies use real patient care data, highlighting the need for real-world testing. - LLM evaluations focus on medical exams and diagnostics, with less emphasis on administrative tasks that could reduce physician burnout. - Dimensions like accuracy, bias, and robustness need standardization. Systematic, real-world evaluation is essential to harness LLMs' full potential in healthcare, enhancing both physician efficiency and patient outcomes. For more insights, explore the full article [here](https://lnkd.in/eNDkFsrZ?

🏥 Revolutionizing Healthcare with EPTECHAI: The Synergy of Language Model (LLM) and Machine Learning (ML) In the dynamic landscape of healthcare, EPTECHAI stands as a beacon of innovation, leveraging advanced technologies to transform patient care, streamline operations, and drive medical breakthroughs. Let's delve into how EPTECHAI harnesses the power of Language Models (LLM) and Machine Learning (ML) to provide cutting-edge solutions in healthcare. 🌐 Understanding the Language of Healthcare: EPTECHAI's Language Models are designed to comprehend the intricacies of medical language, from clinical notes to research papers. This capability enables us to build solutions that facilitate efficient data management, seamless communication among healthcare professionals, and accurate documentation. 🤖 Machine Learning for Predictive Healthcare: EPTECHAI's Machine Learning algorithms are tailored for predictive analytics in healthcare. Through the analysis of vast datasets, we empower healthcare providers to anticipate patient needs, identify potential health risks, and optimize treatment plans. This proactive approach enhances patient outcomes and reduces the burden on healthcare systems. 💡 EPTECHAI Healthcare Solutions: Clinical Documentation Optimization: Streamline and automate the documentation process, ensuring accuracy and compliance with medical standards. Predictive Diagnostics: Leverage ML algorithms to enhance diagnostic accuracy and identify potential health issues at an early stage. Operational Efficiency: Improve hospital workflows, resource allocation, and patient scheduling through data-driven insights. Patient Engagement: Develop personalized and interactive interfaces powered by LLM for enhanced patient communication and engagement. Research Acceleration: Facilitate medical research by extracting valuable insights from a vast array of medical literature using Language Models. 🌈 Realizing the Future of Healthcare: EPTECHAI envisions a future where healthcare is not just reactive but predictive and personalized. By integrating LLM and ML, we empower healthcare professionals to make informed decisions, enhance patient care, and drive medical innovation. 👩⚕️ Partner with EPTECHAI for a Healthier Tomorrow! #HealthTechInnovation #EPTECHAIHealthcare #MLinHealthcare #FutureOfHealthcare

Generative AI impact is getting real - and this is the latest illustration, for a highly complex process (clinical trials) in a highly regulated industry (biopharma). Very proud and excited to share the paper published by my BCG X colleagues Chris Meier Nigel Markey Casper van Langen Ilyass El Mansouri Gaëtan Rensonnet that shows how you can leverage Generative AI (including RAG but also semi autonomous agent-based approaches leveraging our opensource AgentKit toolkit) to write large and complex documents such as clinical trial protocols. This saves meaningful (months, not days) time for teams, translated into faster time to market for biopharmas - and ultimately hundreds of millions in revenues. More here: https://lnkd.in/es2jDQyy

You still have a few more days to submit a paper to our CHI 2024 workshop on LLMs as Research Tools! Here's the complete Call for Papers: Broadly accessible large language models (LLMs) stand to fundamentally reshape the HCI community’s suite of methods for working with data. To date, LLM tools have already been used to facilitate qualitative coding, perform thematic analysis, and even mediate interviews or simulate user data. However, we lack a broader understanding of: - How LLM-based methods are being used to work with data in HCI - What empirical evaluation strategies are acceptable to the community for establishing validity of data work conducted with LLMs - How to critically and ethically use LLM methods in HCI research. The goal of this workshop is to gather a community of researchers interested in these topics to map current approaches as a community, documenting the challenges encountered, and norm-set in this rapidly evolving field. For this hybrid CHI 2024 workshop, we invite junior and senior academics, researchers, and practitioners to submit extended abstracts or short papers. Interested participants should submit a 2-4 page (not including references) proposal via this link using the CHI Extended Abstracts format. We invite submissions including empirical works-in-progress, research or research proposals, and provocations, critical approaches, or position papers. Broadly, paper topics should relate to the use of LLMs to work with data in HCI, epistemic validity and methodological evaluations, and/or critical and ethical perspectives on the use of LLM methods in HCI research. One participant from each submission must register for the workshop and at least one day of the conference. Submissions will be published on the workshop website. Submission deadline: Feb 22, 2024 Website: https://lnkd.in/g6i3BxG3 #chi2024 #llm #llms #hci #ai

Mining companies are already testing the potential of artificial intelligence to discover new sources of high-demand Metals. For instance, an Australian mining firm has been working with Microsoft to develop an AI system that could help to improve copper recovery at the world's largest copper mine. Codelco, a Chilean mining company, is using artificial intelligence to squeeze out more copper from its aging mines. McKinsey reports that a custom-built artificial intelligence (AI) model, loaded with three years' worth of operating data from the mill, could increase copper production by 10 percent or more. The mining industry is responding to an increasingly urgent problem of copper shortage by exploring new ways of extracting copper. For instance, a startup called Jetti Resources has developed a solution that involves rock-eating microbes releasing trapped copper. In conclusion, AI can be applied to copper mining industries to improve copper recovery, increase production, and discover new sources of high-demand metals. The use of AI in copper mining can bring several benefits, including: Improved copper recovery: AI can help mining companies to increase extraction rates and improve copper recovery from aging mines. Process optimization and decision-making: AI can enable the analysis and optimization of mining processes, leading to better decision-making and increased efficiency. Environmental impact reduction: AI can work to reduce environmental impact and risk on location by analyzing data quickly and efficiently. Risk evaluation and alert: AI can evaluate and alert to possible risks at a mine site, creating a more efficient and safer environment for human workforces. Better worker safety: AI can help to improve worker safety by reducing the need for human intervention in hazardous areas. Cost reduction: AI can help mining companies to process large amounts of data at the edge of their networks, closer to where the data is being generated, leading to cost reduction. In conclusion, AI can bring several benefits to copper mining, including improved copper recovery, process optimization and decision-making, environmental impact reduction, risk evaluation and alert, better worker safety, and cost reduction #India #Innovation #Management #HumanResources #DigitalMarketing #Technology #Creativity #Future #Entrepreneurship #Careers #Markets #Marketing #SocialMedia #SocialNetworking #Economy