http://mohammedkhalilia.com/tags/clinical-nlp/Clinical NLPHugoBlox Kit (https://hugoblox.com)en-usThu, 11 Jan 2018 00:00:00 +0000http://mohammedkhalilia.com/media/icon_hu_e7e672982174d01f.pnghttp://mohammedkhalilia.com/tags/clinical-nlp/http://mohammedkhalilia.com/projects/compmed/Thu, 11 Jan 2018 00:00:00 +0000http://mohammedkhalilia.com/projects/compmed/<p>Amazon Comprehend Medical is a HIPAA-eligible natural language processing (NLP) service that uses machine learning that has been pre-trained to understand and extract health data from medical text, such as prescriptions, procedures, or diagnoses, medication brand and generic names, dosage, strength, duration, date/time and other traits such as negation. The service also extracts private health information (PHI) including medical record numbers, patient names, age, address, location, race and ethnicity, etc.</p> <h4 id="example">Example</h4> <p>Input is clinical text that includes patient private information and clinical notes. <figure > <div class="flex justify-center "> <div class="w-full" > <img alt="alt" srcset="http://mohammedkhalilia.com/projects/compmed/example_text_hu_69a421e4a12700bb.webp 320w, http://mohammedkhalilia.com/projects/compmed/example_text_hu_7bebbee87898a706.webp 480w, http://mohammedkhalilia.com/projects/compmed/example_text_hu_7936baf082404ec3.webp 760w" sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px" src="http://mohammedkhalilia.com/projects/compmed/example_text_hu_69a421e4a12700bb.webp" width="760" height="456" loading="lazy" data-zoomable /></div> </div></figure> </p> <p>The output includes the entities, relationships between entities and attributes. <figure > <div class="flex justify-center "> <div class="w-full" > <img alt="alt" srcset="http://mohammedkhalilia.com/projects/compmed/example_entities_hu_8aa77338d18540c7.webp 320w, http://mohammedkhalilia.com/projects/compmed/example_entities_hu_1c29567dc18b0612.webp 480w, http://mohammedkhalilia.com/projects/compmed/example_entities_hu_54da6a6799cc9ce.webp 760w" sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px" src="http://mohammedkhalilia.com/projects/compmed/example_entities_hu_8aa77338d18540c7.webp" width="760" height="650" loading="lazy" data-zoomable /></div> </div></figure> </p>