Download Free Medical Machine Learning for the Healthcare Industry PowerPoint Presentation

Machine Learning for the Healthcare Industry PowerPoint Presentation

DOWNLOAD MEDICAL POWERPOINT PRESENTATION

About This Presentation

Description : Check out this medical presentation on Precision Medicine, which is titled "Machine Learning for the Healthcare Industry", to know about machine learning for the healthcare industry.

Tags : Precision Medicine, Machine Learning, Healthcare Industry

Published on : Jul 20, 2021 | Views : 2026 | Downloads : 4

Shareable Url :

Embed Code :

Comment

Transcript

Slide 1-

Machine Learning for the Healthcare Industry Daniel B. Neill H.J. Heinz III College Carnegie Mellon University E-mail: neill@cs.cmu.edu We gratefully acknowledge funding support from the National Science Foundation, grants IIS-0916345, IIS-0911032, and IIS-0953330, and the UPMC Technology Development Center.
Slide 2-

Daniel B. Neill (neill@cs.cmu.edu) Associate Professor of Information Systems, Heinz College, CMU Director, Event and Pattern Detection Laboratory Courtesy Associate Professor of Machine Learning and Robotics My research is focused at the intersection of two fields, machine learning and public policy, with two main goals: Develop new machine learning methods for better (more scalable and accurate) detection and prediction of events and other patterns in massive datasets. Apply these methods to improve the quality of public health, safety, and security. Patient Care (today’s talk) Disease Surveillance: Very early and accurate detection of emerging outbreaks. Law Enforcement: Detection, prediction, and prevention of “hot-spots” of violent crime.
Slide 3-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 4-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 5-

Improve accuracy of diagnosis, prognosis, and risk prediction. We have developed new methods for chronic disease risk prediction and visualization that give clinicians a comprehensive view of their patient population, risk levels, and risk factors, along with the estimated effects of potential interventions. Increased risk of heart attack  Link to paper
Slide 6-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 7-

Optimize hospital processes such as resource allocation and patient flow. By early and accurate prediction of each patient’s Diagnosis Related Group (DRG), we can better predict demand and allocate scarce hospital resources such as beds and operating rooms. Link to paper
Slide 8-

Optimize hospital processes such as resource allocation and patient flow. By early and accurate prediction of each patient’s Diagnosis Related Group (DRG), we can better predict demand and allocate scarce hospital resources such as beds and operating rooms. Better prediction of patients’ future diagnoses, risks, and care needs can enable more effective and efficient treatment and preventive care. Link to paper
Slide 9-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 10-

Automate detection of relevant findings in pathology, radiology, etc. Our pattern detection approaches have been successfully applied to detect regions of interest in digital pathology slides, and work surprisingly well to detect prostate cancer. Key advance 1: Very efficient, accurate search over subareas of an image. Key advance 2: Use hierarchy to search at multiple resolutions (coarse to fine). Link to paper
Slide 11-

Automate detection of relevant findings in pathology, radiology, etc. Our pattern detection approaches have been successfully applied to detect regions of interest in digital pathology slides, and work surprisingly well to detect prostate cancer. Key advance 1: Very efficient, accurate search over subareas of an image. Key advance 2: Use hierarchy to search at multiple resolutions (coarse to fine). Automatic detection of anomalies and patterns is especially valuable when the key to diagnosis is a tiny piece of the patient’s health data. Link to paper
Slide 12-

Automate detection of relevant findings in pathology, radiology, etc. Our pattern detection approaches have been successfully applied to detect regions of interest in digital pathology slides, and work surprisingly well to detect prostate cancer. Key advance 1: Very efficient, accurate search over subareas of an image. Key advance 2: Use hierarchy to search at multiple resolutions (coarse to fine). Detection is also valuable when key patterns of interest are discovered by integrating information across many patients, and might not be visible from a single patient’s data. Link to paper
Slide 13-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 14-

Discover new medical knowledge (clinical guidelines, best practices). We are currently working to analyze massive quantities of patient care data (EHR and health insurance claims) to discover anomalous patterns of care (APC) which significantly impact outcomes. Claims data: ~125K patients with diseases of the circulatory system APC-Scan Most significant detected pattern: Glucocorticoids are associated with dramatically increased hospitalizations and length of stay in the subpopulation of ~2K overweight, hypertensive males with endocrine secondary diagnoses. Regression on separate, held-out patient dataset: 51% increase in hospitalizations for this subpopulation; vs. 11% for entire patient population. Link to paper
Slide 15-

What can machine learning do for the healthcare industry? Improve accuracy of diagnosis, prognosis, and risk prediction. Optimize hospital processes such as resource allocation and patient flow. Identify patient subgroups for personalized and precision medicine. Improve quality of care and population health outcomes, while reducing healthcare costs. Reduce medication errors and adverse events. Discover new medical knowledge (clinical guidelines, best practices). Model and prevent spread of hospital acquired infections. Automate detection of relevant findings in pathology, radiology, etc.
Slide 16-

Questions? More details on EPD Lab website: http://epdlab.heinz.cmu.edu Or e-mail me at: neill@cs.cmu.edu