Download as PDF, PPTX
Uploaded byXavier Amatriain
AI for COVID-19 - Q42020 update
The document discusses the integration of AI technology in healthcare to enhance accessibility, quality, and efficiency, particularly in light of the COVID-19 pandemic. It emphasizes a collaborative approach where AI aids human providers, utilizing data feedback loops for continuous learning and improvement in medical diagnostics. The content also outlines AI-driven innovations in medical conversations, diagnosis through expert systems, and addressing healthcare challenges through tailored AI applications.
More Related Content
Similar to AI for COVID-19 - Q42020 update
AI for COVID-19 - Q42020 update
- 1. AI for COVID-19:An online virtual care approach (Q42020 update) Xavier Amatriain (@xamat) https://curai.com 11/06/2020
- 2.
- 3. ● >50% worldwith no access to essential health services ○ ~30% of US adults under-insured ● ~15 min. to capture information, diagnose, recommend treatment ● 30% of the medical errors causing ~400k deaths a year are due to misdiagnosis Healthcare access, quality, and scalability shortage of 120,000 physicians by 2030
- 4. Towards an AIpowered learning health system ● Mobile-First Care, always on, accessible, affordable ● AI + human providers in the loop for quality care ● Always-Learning system ● AI to operate in-the-wild (EHR) FEEDBACK DATA MODEL AI-augmented medical conversations
- 5. How does thislook like?
- 6.
- 7. Breakthroughs in AI& healthcare
- 8.
- 9. Research areas atCurai ● Medical Reasoning and Diagnosis ○ Learning from the Experts: combining expert systems and deep learning ● NLP ○ Medical dialogue summarization ○ Transfer Learning for Similar Questions ○ Medical entity recognition: An active learning approach ● Multimodal healthcare AI ○ Few-shot dermatology image classification
- 10. General principles 1. ExtensibleAI a. Data feedback loops b. Incrementally/iteratively learn from “physician-in-the-loop” 2. Domain Priors + Data 3. AI in the wild a. Uncertainty in prediction b. Enables fall-back to “physician-in-the-loop”
- 11. ToC ● ● ○ ● ○ ○ 11 To appear atEMNLP-Findings 2020
- 12. Local to globalsummarization DOCTOR: what color is the phlegm? PATIENT: dark green dark green DOCTOR: do you have chest pain while coughing? PATIENT: yes and breathing . pretty much all the time DOCTOR: just clarifying. is your chest pain constant? or is it on & off ? PATIENT: pretty constant it is constant pain it does not turn off. Summaries dark green phlegm chest pain while coughing and breathing all the time constant chest pain ● Local structures in the conversation / Local summaries to global summaries
- 13. Designing the Model ●Hybrid model between abstractive and extractive summarization ○ Copy more (maintain integrity of domain) ○ Focus on medical concepts ○ Get negations and affirmations right ● Extension of the Pointer Generator Network (Abigail See et al. 2017) ○ Loss Contributions: Penalized generation to focus on copying ○ Architecture Contributions: Negations and medical concepts in attention mechanism and final probability distributions. ○ Formulated new evaluation criteria: Automated and doctor metrics
- 14. Results Copied from DoctorCopied from Patient Generated Proposed ModelFine-tuned pointer generator network
- 15. Using GPT-3 toSupplement Training Data Snippet Trained on Human Trained on GPT-3 Trained on Human + GPT-3 DR: Have you ever been tested for any underlying health conditions such as diabetes, hypothyroidism or polycystic ovarian syndrome? PT: No PT: I have been told I have prediabetes Has not been tested for any underlying health conditions. Hasn't tested for any underlying health conditions such as diabetes, hypothyroidism or polycystic ovarian syndrome Has not been tested for any underlying health conditions. Has been told has prediabetes. DR: Do you have pus appearing discharge from the site? PT: Yes. If the bubbles pop it leaks out a watery substance Has pus appearing from the sire. Pus appearing from the site Pus discharge from the site. If bubbles pop it leaks out a substance.
- 16.
- 17. Our approach toCOVID-19
- 18.
- 19. AI + Providersin the loop + Daily follow up
- 20. Feedback data fromCOVID-assessment female middle-age cough headache nose discharge cigarette smoking hospital personnel Moderate COVID-19 risk female middle-age cough headache chest pain difficulty breathing nose discharge cigarette smoking hospital personnel foreign travel history High COVID-19 risk Positive examples for COVID-19
- 21. ToC ● ● ○ ● ○ ○ 21 To appear atNeurIPS’ 2020 ML4H workshop
- 22. ML + Expertsystems for Dx models female middle aged fever cough Influenza 16.9 bacterial pneumonia 16.9 acute sinusitis 10.9 asthma 10.9 common cold 10.9 influenza 0.753 bacterial pneumonia 0.205 asthma 0.017 acute sinusitis 0.008 pulmonary tuberculosis 0.007 Inputs DDx with expert system DDx with ML model Expert system Clinical case simulator Clinical cases DDx ML model Common cold UTI Acute bronchitis Female Middle-aged Chronic cough Nasal congestion Other data (e.g. EHR)
- 23. COVID-aware modeling Expert system Clinical case simulator Clinicalcases with DDx ML model Common cold UTI Acute bronchitis Female Middle-aged Chronic cough Nasal congestion COVID-19 assessment data COVID-19 COVID-19 female middle-age cough headache nose discharge cigarette smoking hospital personnel
- 24. Examples Inputs DDx beforeCOVID DDx after COVID female middle aged fever cough healthcare worker influenza bacterial pneumonia asthma COVID-19 influenza bacterial pneumonia female middle aged fever cough nasal congestion influenza adenovirus infection bacterial pneumonia influenza COVID-19 adenovirus infection
- 25. ToC ● ● ○ ● ○ ○ 25 Proceedings of the2020 ACM SIGKDD
- 26. Question similarity forCOVID FAQs ● Transfer learning ● Double-finetuned BERT model ● Handle data sparsity ● Medical domain knowledge through an intermediate QA binary task Does A answer Q? Q A Pretrained BERT BERT Q1 similar to Q2? Q1 Q2 BERT
- 27. COVID-19: Automated FAQMatching ● ● User Questions Matching Questions in our FAQ (Answer not shown here for brevity) When do COVID symptoms start after exposure? How long is it between when a person is exposed to the virus and when they start showing symptoms? Currently I’m experiencing a cough and slight chest pain. Should I just stay at home? At what point will I know I have to go to the ER? When should you go to the emergency room? 27
- 28.
- 29. Conclusions ● Healthcare needsto scale quickly, and this has become obvious in a global pandemic like the one we are facing ● The only way to scale healthcare while improving quality and accessibility is through technology and AI ● AI cannot be simply “dropped” in the middle of old workflows and processes ○ It needs to be integrated in end-to-end medical care benefitting both patients and providers https://curai.com/work