The digital health space refers to the integration of technology and health care services to improve the overall quality of health care delivery. It encompasses a wide range of innovative and emerging technologies such as wearables, telehealth, artificial intelligence, mobile health, and electronic health records (EHRs). The digital health space offers numerous benefits such as improved patient outcomes, increased access to health care, reduced costs, and improved communication and collaboration between patients and health care providers. For example, patients can now monitor their vital signs such as blood pressure and glucose levels from home using wearable devices and share the data with their doctors in real-time. Telehealth technology allows patients to consult with their health care providers remotely without having to travel to the hospital, making health care more accessible, particularly in remote or rural areas. Artificial intelligence can be used to analyze vast amounts of patient data to identify patterns, predict outcomes, and provide personalized treatment recommendations. Overall, the digital health space is rapidly evolving, and the integration of technology in health

Monday, November 16, 2020

Effect of a Machine Learning–Derived Early Warning System for Intraoperative Hypotension vs Standard Care : Are we ready ?


Artificial intelligence, machine learning, and deep learning are topics being bandied about in clinical medicine.  We are aware of some early failures of studies in oncology by M.D. Anderson and IBMs Watson AI system. After working with Watson the Oncology Group at M.D. Anderson Clinic abandoned its use. Many of the reasons were due to logistics for using the "Oncology Expert" IBM model.  IBM maintains the program was successful.


Here are four things to know about why the project was put on hold.

1. One of the main challenges the audit cites is that the Oncology Expert Advisor's focus changed multiple times. The initial project focused on leukemia; however, it later shifted to lung cancer. Rob Merkel, general manager for oncology and genomics at IBM Watson Health, told the Wall Street Journal the focus changed because the project was in an "evaluation phase" at the time.

2. Another challenge for MD Anderson arose due to EHRs. The Oncology Expert Advisor was initially trained on MD Anderson's old EHR system, which was changed during the course of the project. The IBM product no longer works with MD Anderson's EHR system, and since its data has not yet been integrated with the new system, some of its information is outdated.

3. The Oncology Expert Advisor has not been piloted at additional hospitals, even though this step was included in a contract with PricewaterhouseCoopers. MD Anderson paid PwC $23 million to create a business plan for the system. Lynda Chin, the former chair of genomic medicine at MD Anderson, told the Wall Street Journal that partner hospitals showed a "lack of engagement or interest."

4. In total, the project cost MD Anderson more than $62.1 million. This figure includes payments made to external firms for planning, project management, and development for the Oncology Expert Advisor product, along with an initial MD Anderson and IBM contract of $2.4 million and $39 million in contract renewal fees.

MD Anderson is actively looking to other software contractors to potentially replace IBM's role in the project, having sent out a request for proposals that closed last month. The request specified that previous vendors could also submit proposals, but IBM declined to tell the Wall Street Journal whether it had submitted a bid.

"When it was appropriate to do so, the project was placed on hold," an MD Anderson spokesperson told Forbes in an article published last month. "As a public institution, we decided to go out to the marketplace for competitive bids to see where the industry has progressed."

These factors were wrought with logistical challenges, such as changes in focus on diseases, (from leukemia to lung cancer) and a change in EHR at MD Anderson.

Digital Health Space attributes the failure to naivete on the part of the vendor and the clinic. This was a first attempt to merge aspects of machine learning with the treatment of complex diseases with a myriad of possible combinations of anti-cancer drugs. The field itself has undergone the revolution of using powerful cellular poisons with severe side effects to precision medicine-based upon focused tools using molecular antibodies.

Predictive methods for reducing hypotensive episodes utilizing machine learning.

This study of hypotension and its role in morbidity in anesthesia was limited by the limitations of using intraarterial blood pressure monitoring. This method of monitoring blood pressure is usually limited to high-risk surgery, which excludes it from routine procedures in healthy patients.  It did provide accurate assessments and was an improvement over standard non-machine learning tools.

The HYPE Randomized Clinical Trial
























Effect of a Machine Learning–Derived Early Warning System for Intraoperative Hypotension vs Standard Care on Depth and Duration of Intraoperative Hypotension During Elective Noncardiac Surgery: The HYPE Randomized Clinical Trial | Anesthesiology | JAMA | JAMA Network

No comments:

Post a Comment