BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250308T222926Z UID:AC2EB3CA-C1CB-4581-A0B4-3970038D6A32 DTSTART;TZID=America/Los_Angeles:20250307T120000 DTEND;TZID=America/Los_Angeles:20250307T140000 DESCRIPTION:Welcome to the 2nd lecture!\n\nWe went over the following in th e last lecture:\n\n- Learned the basics of AI and ML\n- How is AI/ML relat ed to biological networks\n- How an AI system is trained and what does it mean\n- Why\, how\, and where AI/ML helps\n\nAI is generally applied to th e detection or presence of a certain disease. The manner in which it can b e used to solve differs on the problem construction. In some cases\, the t raining is done on actual images\, or images are constructed from the data itself\, or time series analysis are done etc. Also\, depending upon the problem\, it may be useful to consider what type of network should be used : CNN\, DNN\, RNN\, LSTM etc.\n\nWe will start with an understanding of so me biological signals that are necessary to solve a certain detection or e stimation problem.\n\nWe will review the following examples:\n\n- Imaging – detection of abnormalities in a CT scan\, MRI\, or X-ray\,\n- Detectio n of Atrial Fibrillation using:\n- Time series analysis\n- Image analysis\ n\n- Drug discovery\,\n- Help in diagnosis of a disease (automated doctor? )\, and\n- LLM in medicine\n\nHow AI is used to develop an algorithm is di fferent from how the medical devices were made in the past. AI generally r equires large databases and also may or may not work on known features or aspects of a disease. In some cases\, the data scientist expects AI to fig ure out such features. This poses a challenge to the regulating authoritie s that the detection of a disease is done without knowing how it was done. We will review how and what FDA is doing about it.\n\nIf time permits\, w e will go over some cautions around data analysis.\n\nSpeaker(s): Dr Md Us man\n\nAgenda: \n- 12:10 to 12:20 PM : Introduction by Gora Datta\, FHL7\n - 12:20 to 1::55 PM: Expert Lecture by Dr Md Usman\n- Understand some exam ples of using AI\,\n- Know when to use AI for health measurements\,\n- Reg ulations around AI by the FDA.\n\n- 1:55 to 2 PM : Wrap Up\n\nRoom: Shark Cove\, Bldg: Bealle Applied Innovation\, 5270 California Ave\, Irvine\, Ca lifornia\, United States\, 92617\, Virtual: https://events.vtools.ieee.org /m/472277 LOCATION:Room: Shark Cove\, Bldg: Bealle Applied Innovation\, 5270 Californ ia Ave\, Irvine\, California\, United States\, 92617\, Virtual: https://ev ents.vtools.ieee.org/m/472277 ORGANIZER:goradatta@ieee.org SEQUENCE:14 SUMMARY:MEDICAL DEVICES PART II- Public Health and FDA Regulations URL;VALUE=URI:https://events.vtools.ieee.org/m/472277 X-ALT-DESC:Description: <br /><p>Welcome to the 2<sup>nd</sup>&nbsp\;lectur e!</p>\n<p>We went over the following in the last lecture:</p>\n<ul>\n<li> Learned the basics of AI and ML</li>\n<li>How is AI/ML related to biologic al networks</li>\n<li>How an AI system is trained and what does it mean</l i>\n<li>Why\, how\, and where AI/ML helps</li>\n</ul>\n<p>AI is generally applied to the detection or presence of a certain disease. The manner in w hich it can be used to solve differs on the problem construction. In some cases\, the training is done on actual images\, or images are constructed from the data itself\, or time series analysis are done etc. Also\, depend ing upon the problem\, it may be useful to consider what type of network s hould be used: CNN\, DNN\, RNN\, LSTM etc.</p>\n<p>We will start with an u nderstanding of some biological signals that are necessary to solve a cert ain detection or estimation problem.</p>\n<p>We will review the following examples:</p>\n<ol>\n<li>Imaging &ndash\; detection of abnormalities in a CT scan\, MRI\, or X-ray\,</li>\n<li>Detection of Atrial Fibrillation usin g:\n<ol>\n<li>Time series analysis</li>\n<li>Image analysis</li>\n</ol>\n< /li>\n<li>Drug discovery\,</li>\n<li>Help in diagnosis of a disease (autom ated doctor?)\, and</li>\n<li>LLM in medicine</li>\n</ol>\n<p>How AI is us ed to develop an algorithm is different from how the medical devices were made in the past. AI generally requires large databases and also may or ma y not work on known features or aspects of a disease. In some cases\, the data scientist expects AI to figure out such features. This poses a challe nge to the regulating authorities that the detection of a disease is done without knowing how it was done. We will review how and what FDA is doing about it.</p>\n<p>If time permits\, we will go over some cautions around d ata analysis.</p><br /><br />Agenda: <br /><ul>\n<li>12:10 to 12:20 PM : I ntroduction by Gora Datta\, FHL7</li>\n<li aria-level="1">12:20 to 1::55 P M: Expert Lecture by Dr Md Usman\n<ul>\n<li>Understand some examples of us ing AI\,</li>\n<li>Know when to use AI for health measurements\,</li>\n<li >Regulations around AI by the FDA.</li>\n</ul>\n</li>\n<li aria-level="1"> 1:55 to 2 PM : Wrap Up</li>\n</ul> END:VEVENT END:VCALENDAR