SAIGroup’s Post

Always great connecting with likeminded leaders in healthcare and discussing new trends. It is very encouraging to see the level of interest in healthcare in AI applications, while maintaining high ethical standards, great patient experience and robust data safety. Shout out to Matthew Sakumoto for the introduction. #HealthcareonLinkedin #AI #GenAI #ClinicalInformatics

Top 2 takeaways from my conversation this week with Anwar A. Jebran, MD, primary care physician and physician informaticist at Oak Street Health: 1) Loved his virtual visit AI copilot idea -- the solution would listen to the conversation and surface the relevant information or image on the video in real-time for both the patient and clinician to reference. Anyone working on this? 2) Found it interesting that data consolidation is still such a challenge -- the problem he references below is not unique, and I know a number of vendors are working on it. Anyone have a good experience with a solution? Full Q&A below 👇 — 🟩 Q: What applications of generative AI excite you the most? AI as a true copilot, particularly in the context of virtual visits. For example, if I’m discussing lab results with a patient, the AI can understand the context of the discussion and automatically and in real-time surface and display the relevant information on the screen. AI for diagnosis support. Given the length of many patients’ medical records today, I’m excited about the potential for AI-based solutions to surface potential diagnosis suspects I may have missed. 🟩 Q: Any areas where you see whitespace to deliver new solutions? I see an opportunity to consolidate various data sources better and make them usable at the point of care. For example, in value-based care and population health, you want access to different types of information and robust interoperability, including medical records, claims, SDoH data, prescription data, and more. However, this information is often delivered in a format that is incredibly difficult to parse today, and not easily digestible for physicians to take the next clinical steps. No one has cracked this yet as far as I’ve seen. 🟩 Q: Outside of generative AI, where do you see the greatest potential for technology to improve healthcare? I believe the hospital-at-home space has tremendous potential. During my fellowship, I spent two years working on implementing one of these programs and saw firsthand the potential to lower costs, drive better outcomes, and improve patient experience, particularly with lower acuity cases. The critical challenge is the reimbursement landscape: what will happen with the temporary CMS waiver (currently scheduled to expire at the end of the year) and how can these programs scale efficiently across non-Medicare payers? --- p.s. if you want to get these Q&As when they come out, sign up for our newsletter here: https://bit.ly/49z6AUW

A recent EHR Workload Trend report shows increased time spent in EHRs. It will be exciting to watch how AI affects this. #ehr #ai #healthcare The average time PCPs spent in the EHR per 8 hours of scheduled clinic appointments increased ( 28.4 minutes, 7.8%), as did time in orders ( 23.1 minutes, 58.9%), inbox ( 14.0 minutes, 24.4%), chart review ( 7.2 minutes, 13.0%), notes ( 2.9 minutes, 2.3%), outside scheduled hours on days with scheduled appointments ( 6.4 minutes, 8.2%), and on unscheduled days ( 13.6 minutes, 19.9%). Primary care physicians received more patient medical advice requests ( 5.4 messages, 55.5%) and prescription messages ( 2.3, 19.5%) per 8 hours of scheduled clinic appointments, but fewer patient calls (−2.8, −10.5%) and results messages (−0.3, −2.7%). While total time in the EHR continued to increase in the final study year ( 7.7 minutes, 2.0%), inbox time decreased slightly from the year prior (−2.2 minutes, −3.0%). Primary care physicians’ average aFTE decreased 5.2% from 0.66 to 0.63 over 4 years. https://lnkd.in/eu5fqZ_d

The Role of Expert Systems in Healthcare: Improving Patient Care and Diagnosis https://ift.tt/vGonwf9 The Role of Expert Systems in Healthcare: Improving Patient Care and Diagnosis Introduction: In recent years, the healthcare industry has witnessed a significant transformation with the integration of advanced technologies. One such technology that has revolutionized the field is expert systems. Expert systems are computer-based programs that utilize artificial intelligence (AI) to mimic human expertise and provide accurate and reliable information for decision-making. In healthcare, these systems have played a crucial role in improving patient care and diagnosis. This article explores the various ways in which expert systems have contributed to enhancing healthcare outcomes and the challenges they face in implementation. Understanding Expert Systems in Healthcare: Expert systems in healthcare are designed to replicate the decision-making abilities of human experts in specific domains. These systems are built using a combination of knowledge representation, inference engines, and a user interface. The knowledge representation component stores the domain-specific knowledge, while the inference engine applies this knowledge to solve complex problems. The user interface allows healthcare professionals to interact with the system and obtain the necessary information. The Role of Expert Systems in Diagnosis: One of the primary applications of expert systems in healthcare is in the field of diagnosis. Expert systems can analyze patient symptoms, medical history, and laboratory results to provide accurate and timely diagnoses. These systems can process vast amounts of data and consider a wide range of factors that may not be immediately apparent to human experts. By leveraging AI algorithms, expert systems can identify patterns and correlations that may go unnoticed by healthcare professionals, leading to more accurate and efficient diagnoses. Expert systems can also assist in differential diagnosis, where multiple potential conditions are considered. By analyzing symptoms and comparing them against a vast database of medical knowledge, expert systems can generate a list of probable diagnoses, ranked by likelihood. This helps healthcare professionals in making informed decisions and reduces the risk of misdiagnosis. Improving Patient Care: Expert systems have also proven to be invaluable in improving patient care. These systems can provide evidence-based recommendations for treatment plans, medication dosages, and follow-up care. By considering patient-specific factors such as age, gender, medical history, and comorbidities, expert systems can generate personalized treatment plans that optimize outcomes. Furthermore, expert systems can assist in monitoring patient progress and alert healthcare professionals to any deviations from the expected trajectory. For example, in critical care settings, expert systems can continuously analyze p...

In 2019, I met a team that wanted to use AI to improve patient outcomes in emergency rooms. This week, Regard closed a $61m Series B. ---- Regard was early to AI-enabled healthcare. Just five years ago, using AI to process large amounts of healthcare data in an ER setting seemed daunting. EMR integrations, changing physician workflows, and hospital exec buy-in are all very hard. But we had a prepared mind. In 2017, we invested in the seed round of Viz.ai and had a front row seat to how Chris and team used AI to overhaul hospital imaging workflows to improve patient outcomes and increase hospital revenue. (fun fact: Susa Ventures partner Derick En'Wezoh, MD, MBA was on the founding team of Viz). So in 2019 we invested in the seed of Regard and partnered with Eli Ben-Joseph, Nate Wilson and Thomas Moulia to build a system that could quickly read the entire medical record of a patient to help emergency room physicians better care for their patients. It wasn't always up and to the right. The early years were hard. This is a complex product to build. Furthermore, selling into large hospitals and healthcare systems when you're a new startup is even more difficult. But after a few years, we started to close big contracts with leading healthcare systems in the US. Today, Regard has real momentum: 1. Live with Banner Health (one of Arizona’s largest health providers), Virginia-based Sentara Healthcare, New York’s Montefiore Medical Center and Cedars-Sinai Medical Center in Los Angeles 2. 4.5x'd revenue in 2023; similar projections in 2024 3. $1m ACVs 4. Added Mark Laret, former CEO of UCSF Health, to the Board 5. $61m Series B to hire the best minds in AI healthcare Our goals are to continue to improve patient outcomes, reduce physician burnout, and help hospitals find new revenue. AI will be critical to improving US healthcare, and Regard will be a key player. As always, all credit goes to the team on the awesome progress. https://lnkd.in/gnA-atGa

The Role of Expert Systems in Healthcare: Improving Patient Care and Diagnosis Introduction: In recent years, the healthcare industry has witnessed a significant transformation with the integration of advanced technologies. One such technology that has revolutionized the field is expert systems. Expert systems are computer-based programs that utilize artificial intelligence (AI) to mimic human expertise and provide accurate and reliable information for decision-making. In healthcare, these systems have played a crucial role in improving patient care and diagnosis. This article explores the various ways in which expert systems have contributed to enhancing healthcare outcomes and the challenges they face in implementation. Understanding Expert Systems in Healthcare: Expert systems in healthcare are designed to replicate the decision-making abilities of human experts in specific domains. These systems are built using a combination of knowledge representation, inference engines, and a user interface. The knowledge representation component stores the domain-specific knowledge, while the inference engine applies this knowledge to solve complex problems. The user interface allows healthcare professionals to interact with the system and obtain the necessary information. The Role of Expert Systems in Diagnosis: One of the primary applications of expert systems in healthcare is in the field of diagnosis. Expert systems can analyze patient symptoms, medical history, and laboratory results to provide accurate and timely diagnoses. These systems can process vast amounts of data and consider a wide range of factors that may not be immediately apparent to human experts. By leveraging AI algorithms, expert systems can identify patterns and correlations that may go unnoticed by healthcare professionals, leading to more accurate and efficient diagnoses. Expert systems can also assist in differential diagnosis, where multiple potential conditions are considered. By analyzing symptoms and comparing them against a vast database of medical knowledge, expert systems can generate a list of probable diagnoses, ranked by likelihood. This helps healthcare professionals in making informed decisions and reduces the risk of misdiagnosis. Improving Patient Care: Expert systems have also proven to be invaluable in improving patient care. These systems can provide evidence-based recommendations for treatment plans, medication dosages, and follow-up care. By considering patient-specific factors such as age, gender, medical history, and comorbidities, expert systems can generate personalized treatment plans that optimize outcomes. Furthermore, expert systems can assist in monitoring patient progress and alert healthcare professionals to any deviations from the expected trajectory. For example, in critical care settings, expert systems can continuously analyze patient vital signs and alert healthcare professionals to any signs of deterioration. This early warning syste

Not more, but fewer and more relevant alerts by a Clinical Decision Support System (CDSS) make such a system more valuable for healthcare providers and patients. CDSS is a computer-based program that helps healthcare providers make decisions and improve patient care by analyzing data from electronic health records (EHRs).  CDSSs can help providers make more informed decisions by providing relevant, up-to-date, and patient-specific information at the point of care. Alert Overload and Information Fatigue: Constant barrage of alerts: Traditional CDSS systems can bombard healthcare providers with numerous alerts, many of which may be irrelevant to the specific patient situation. This can lead to alert fatigue, where providers become desensitized to the alerts and miss truly critical warnings. Decision Paralysis: Information overload can make it challenging for providers to prioritize and make informed decisions, potentially leading to delayed or incorrect diagnoses or treatment plans. The Power of Targeted Alerts: Focus on High-Impact Situations: A well-designed CDSS should prioritize generating alerts for critical situations where immediate intervention can significantly impact patient outcomes. This could include drug interactions, potential allergies, or abnormal test results. Actionable Insights: Alerts should be actionable, providing clear recommendations or next steps for the provider to consider, saving them valuable time and cognitive load. Customization Options: The ability to customize alert settings based on patient demographics, medical history, and specific care needs allows for a more targeted and relevant approach. Benefits of Fewer, More Relevant Alerts: Improved Provider Efficiency: Reduced alert fatigue allows providers to focus on patient care and make well-informed decisions with less cognitive strain. Enhanced Patient Safety: Actionable alerts for critical situations can lead to earlier intervention and improved patient outcomes. Increased Provider Satisfaction: A CDSS that is seen as a helpful tool rather than a source of information overload can improve provider satisfaction and trust in the system. The Road to Better CDSS Design: Machine Learning and AI: Utilizing machine learning algorithms can help CDSS systems analyze patient data and generate alerts. Focus on Usability: The design of the CDSS interface should be user-friendly and intuitive, allowing providers to easily access and interpret alerts within their workflow. Clinician Input and Feedback: Involving healthcare providers in the development and implementation of CDSS is crucial. Their feedback can help ensure the system generates alerts that are truly valuable and actionable in real-world clinical practice. By prioritizing fewer, more relevant alerts, CDSS systems can become invaluable tools for healthcare providers. This can lead to improved efficiency, better patient care, and ultimately, a more effective healthcare system.

The Role of Expert Systems in Healthcare: Improving Patient Care and Diagnosis Introduction: In recent years, the healthcare industry has witnessed a significant transformation with the integration of advanced technologies. One such technology that has revolutionized the field is expert systems. Expert systems are computer-based programs that utilize artificial intelligence (AI) to mimic human expertise and provide accurate and reliable information for decision-making. In healthcare, these systems have played a crucial role in improving patient care and diagnosis. This article explores the various ways in which expert systems have contributed to enhancing healthcare outcomes and the challenges they face in implementation. Understanding Expert Systems in Healthcare: Expert systems in healthcare are designed to replicate the decision-making abilities of human experts in specific domains. These systems are built using a combination of knowledge representation, inference engines, and a user interface. The knowledge representation component stores the domain-specific knowledge, while the inference engine applies this knowledge to solve complex problems. The user interface allows healthcare professionals to interact with the system and obtain the necessary information. The Role of Expert Systems in Diagnosis: One of the primary applications of expert systems in healthcare is in the field of diagnosis. Expert systems can analyze patient symptoms, medical history, and laboratory results to provide accurate and timely diagnoses. These systems can process vast amounts of data and consider a wide range of factors that may not be immediately apparent to human experts. By leveraging AI algorithms, expert systems can identify patterns and correlations that may go unnoticed by healthcare professionals, leading to more accurate and efficient diagnoses. Expert systems can also assist in differential diagnosis, where multiple potential conditions are considered. By analyzing symptoms and comparing them against a vast database of medical knowledge, expert systems can generate a list of probable diagnoses, ranked by likelihood. This helps healthcare professionals in making informed decisions and reduces the risk of misdiagnosis. Improving Patient Care: Expert systems have also proven to be invaluable in improving patient care. These systems can provide evidence-based recommendations for treatment plans, medication dosages, and follow-up care. By considering patient-specific factors such as age, gender, medical history, and comorbidities, expert systems can generate personalized treatment plans that optimize outcomes. Furthermore, expert systems can assist in monitoring patient progress and alert healthcare professionals to any deviations from the expected trajectory. For example, in critical care settings, expert systems can continuously analyze patient vital signs and alert healthcare professionals to any signs of deterioration. This early warning syste

If you’re curious about the ins and outs of the American Medical Association’s CPT Editorial Panel’s upcoming review of the 15 codes used for remote monitoring of patients, Medical Economics gives an in-depth explanation around the potential for new billing codes that could give physicians more flexibility — and reimbursement — for RPM programs. Proposed code changes could lead to payment for more of the time physicians spend caring for their patients. In his congressional testimony last month, Cadence’s founder and CEO Chris Altchek shared that our experience with Medicare beneficiaries and PCPs “has made clear that RPM is key to the future of primary care.” Cadence’s customer base is 95% primary care physicians who want to improve how they manage patients’ chronic conditions outside of office visits. The industry agrees that more flexible payment for these visits is important for patient access. Christopher J Adamec, vice president of the Alliance for Connected Care, a coalition of telehealth and RPM organizations added: “[Reimbursement for] a window of 11 to 20 minutes may not sound like much, but the time adds up—so much that the 20-minute threshold for reimbursement results in approximately 30% of care being uncompensated.” Read the full article here for more information on what this means and the decisions coming down the pipe: https://lnkd.in/dvWVzhW8