Matt Studney’s Post

Using natural language processing to analyze unstructured patient-reported outcomes data derived from electronic health records for cancer populations: a systematic review. #Research🔍 #StanfordQoLA🐨 #StanfordMed🏥 https://lnkd.in/gqEjmH-a

For corporate communications folks, especially those on investor relations teams, AI is adding additional pressure to the job as analysts are now hoping to apply AI to understand what's "not" being said by executives. The overlay of AI tools takes “Natural Language Processing” (NPL) to another level. As NPL looks to glean cues from the words executives use, the addition of AI looks to interpret hidden meanings from how they say things. Shifts in executive coaching techniques are sure to follow, to say the least. https://bit.ly/47uR6Ri

Deterministic NLP for supporting adverse event detection and processing. Interesting!! Thanks for sharing this very insightful interview Jane Reed & IQVIA! #drugsafety #pharma #ai

Check out this 2020 paper about using #NLP to identify patients with peripheral artery disease in Circulation: Cardiovascular Interventions, co-authored by Duke Spark Initiative for AI in Medical Imaging's Shelley Rusincovitch! Link here: https://lnkd.in/gSYr5vKq Here, the authors proposed a natural language processing approach that learns from completely unstructured clinical narrative data. Their method improved on the existing LASSO-based approach by over 0.08 AUC! Co-authors include E. Hope Weissler, Jikai Z., Steven Lippmann, Ph.D., Ricardo Henao, and W. Schuyler Jones. Thanks for reading; follow us for more biomedical AI research! #medicine #ai

The pharmaceutical industry is a vast landscape, with a deluge of data pouring in from research publications, clinical trials, and internal documents. Extracting valuable insights from this information can often feel like searching for a needle in a haystack. But fear not, there is a solution! Advanced text mining techniques, including cutting-edge natural language processing and machine learning algorithms, have the power to illuminate intricate patterns and relationships buried within complex, unstructured text data. This powerful combination of techniques empowers pharmaceutical companies to gain deep insights into their research areas, competitor landscapes, and potential drug targets, facilitating more informed decision-making and strategic planning. At the heart of this solution lies a sophisticated language model, which can be meticulously trained on a vast corpus of pharmaceutical literature and terminologies. This model enables accurate identification and extraction of key entities, such as drug names, therapeutic areas, clinical outcomes, and adverse events, from raw text data with remarkable precision. The impact of this solution is profound, streamlining research processes and accelerating the pace of innovation. Researchers can efficiently uncover relevant findings, clinical trial results, and emerging trends, allowing for targeted drug development efforts and a comprehensive understanding of competitor activities and market opportunities. As a genuine ally in the quest for pharmaceutical innovation, this solution empowers researchers and decision-makers alike, enabling them to stay at the forefront of discovery and drive positive impact in patient outcomes. With its proven track record of success, it serves as a testament to the transformative power of technology in advancing human health and well-being. #Pharmaceuticals #Technology #AI #NLP #MachineLearning #Data #TextMining #TextAnalytics #Healthcare #LifeScience #Success #Solution #PationeOutcome #MedicalAffairs #ClinicalTrials #Innovation

## If you are working in healthcare and in AI, then course like these are essentials. will help to navigate complexities of "Clinical datasets"! (Even GenAI will require this knowledge) 1- CLINICAL Named Entity Recognition - clinical entities have several variability than general entities and can be from fields like medication, disease, symptoms, ADE, anatomy, duration of medication, gene, lab test, route of administration. Framework like scispacy, CliNER, CLAMP, cTakes are good for Clinical NER. Practical uses. - extraction of entities such as genes/biomarkers, create knowledge base, pattern analysis, detection of medication names. 2. Clinical Entity Resolution - Extraction of entities are good, there are lot to be done in this space for example linkage of disparate clinical data sources, disambiguation, deduplication of clinical entities for data quality. And this is where clinical databases like UMLS, MeSH (Medical subject headings), RxNorm, Go (Gene Ontology), HPO (Human Phenotype Ontology) 3. Clinical Text Representation - clinical text like case note, family history, lab reports are some of most used documents in clinical world. They have abbreviation, notation and several domain nuances as well. Different CLINICAL Transformers can be put to use here like biobert, pubmedbert, bert-clinicalQA, clinical-longformer, clinical-bigbird, roberta-base-biomedical, Core clinical diagnosis prediction Some of transformers like bert-base-uncased-clinical-ner, biomedical-ner can be used to detect clinical entities as well. #generativeai #ai #ushealthcare #clinicalnlp ======================================================= Just finished the course “Advanced AI: NLP Techniques for Clinical Datasets” by Wuraola Oyewusi! Check it out: 

Revolutionizing #healthcare with #NLP ! HCPs, #pharmaceutical companies and #biotechnology firms, embracing the power of #naturallanguageprocessing technology, derive insights from unstructured data, drive efficiency and improve #patientoutcomes. Know more https://lnkd.in/gCkWRWMQ  #artificialintelligence 

Don’t miss Jane Reed’s talk today (4th Oct) at World Drug Safety Congress Europe, 5:10pm to learn how to “transform your drug safety processes with Natural Language Processing”. You can also meet us at #IQVIA booth 45 to learn how NLP can address the challenge of managing increasing volumes of safety-related data for your medical literature monitoring and safety assessment. https://lnkd.in/dmwAFP5D #DrugSafety #NaturalLanguageProcessing  

Excited to share my new Medium article! 🚀🧬 Delving into Explainable AI (XAI) and AI in medicine has been a captivating journey. I've explored on how NLP and XAI offer reasonable solutions. Stay tuned for insights into this fascinating blend of technology and medicine. 🤖🌍🩺 Special thanks to Bharathi Athinarayanan for his sessions on XAI #XAI #AIinMedicine #Ai https://lnkd.in/gX9N6hG7

This paper investigates the synergistic potential of Large Language Models (LLMs) and biomedical knowledge graphs in training semantic models for biomedical and clinical applications. These semantic models, adept at interpreting meaning and context rather than just processing data, can discern nuanced language use, such as understanding "feeling blue" as an expression of sadness. A key focus of this paper is addressing the scarcity of human-written definitions in biomedical thesauri. It demonstrates the effectiveness of LLMs in generating comprehensive definitions for a majority of biomedical concepts. The fusion of knowledge graph insights with LLMs' generalization capabilities is poised to improve healthcare applications, including clinical summarization, decision support, patient diagnosis, pharmacovigilance, and drug discovery. This approach also supports the creation of more interpretable AI systems in healthcare. #insightsonai.com https://lnkd.in/gzDEuHzK