The intersection of telehealth and AI: How can they reinforce each other?
Telemedicine has taken a quantum leap during the pandemic as more providers and patients embraced the delivery of healthcare services remotely.
Today, artificial intelligence-based telemedicine tools are emerging that diagnose patients remotely and direct them to the right care environment; they are designed to increase access to health care services and help providers make informed decisions, ensuring timely and appropriate care.
As providers increasingly develop virtual care options across the care continuum, AI-powered patient triage and medical diagnostics can potentially create the right channels of care that not only bridge the gap in health disparities and promote access, but also create a better patient experience and better health. outcomes.
Piotr Orzechowski is CEO of Infermedica, an AI health company focused on improving preliminary symptom analysis and digital triage. We interviewed him to discuss the intersection of telemedicine and AI.
Q. What is the area of telemedicine that you think Al is particularly suited for?
A. Artificial intelligence offers significant potential in improving telemedicine services. A primary area of application is helping patients identify the appropriate level of care.
Our studies show that approximately 75% of patients are unsure about the appropriate care they need, leading to inefficient use of emergency rooms for minor problems or neglect of serious symptoms. The role of AI is crucial in guiding patients, advising on when telemedicine is appropriate and suggesting alternative care options when necessary.
AI also significantly improves telemedicine adoption. A survey with one of our clients showed that 33% of patients who initially planned an in-person doctor visit opted for teleconsultation first. The role of AI in guiding patient decisions. This helps determine when telehealth is appropriate and when a physical examination or further testing is needed, optimizing the efficiency of patient care.
Finally, AI helps healthcare providers manage extensive documentation tasks. In telemedicine environments, AI can communicate with patients prior to the consultation, gathering initial information and details about their main concerns.
This is especially relevant given the findings from the “I'm Crying, But No One Cares”: Burnout and Depression Report for Physicians 2023, which showed that more than 50% of physicians experience burnout. AI's support in these areas can alleviate some of the workload and provide significant relief for healthcare professionals.
Q. You suggest that Al Tools can diagnose patients remotely and quickly direct them to the right care environment. Please describe how this would work.
A. Although our AI is not licensed to diagnose, it plays a crucial role in influencing patient decisions. According to our data, as many as 77% of patients are likely to change their original intent after undergoing online triage.
AI tools help streamline the triage process, also making it more user-friendly. It begins by collecting basic information such as demographics and risk factors, followed by questions about the patient's primary symptoms, which cover a wide age range from newborns to adults.
Using the initial data, the AI system raises a series of questions that mimic the diagnostic approach of human doctors, focusing on aspects such as severity, duration, exacerbating factors and related symptoms. Normally, after 10 to 20 questions, the AI reaches a sufficient confidence level to provide a reliable triage suggestion.
The output is a results page outlining the recommended course of action, which can range from self-care guidelines to recommending a consultation with healthcare professionals or referral to emergency care. These recommendations also suggest the most appropriate consultation format, such as in-person or remote. We also offer educational articles to guide patients through interim care and home management.
It is critical to note that our AI tool does not diagnose or dictate the patient's final decision. It serves as an educational tool, allowing patients to make informed choices about their health care. We are convinced that AI should support, not force, patient decision-making.
Q: Do you think Al tools are qualified to make this kind of diagnosis nowadays?
A. Currently, AI tools are not authorized to diagnose patients. Despite the remarkable progress in generative AI, we must remain cautious about its practical application in healthcare. Our blood pressure cuffs are certified medical devices, and it's worth noting that while AI tools have significant capabilities, they are not subject to the same stringent regulations.
It is critical to establish a robust regulatory framework to provide guidance and set standards for AI-enabled diagnostics in the future. This includes addressing key challenges such as ensuring maximum transparency in AI decision-making processes and addressing issues related to bias and inaccuracies.
I believe the ideal path forward is to position AI tools as optimal support for both patients and healthcare providers. This includes helping patients make informed self-care decisions and freeing healthcare professionals from repetitive tasks.
Q. What are the results of integrating Al into telemedicine in this way? For example, how would this help improve care and increase patient and caregiver satisfaction?
A. We work with the best telemedicine organizations worldwide, from health insurers to ministries of health. Our systems have assessed more than 15 million patients worldwide.
For example, Solv's symptom checker, launched in October 2022, doubled the number of bookings within the network and achieved an 80% satisfaction score. Notably, 14% of users who did not initially seek care booked appointments, reducing potential health risks and costs.
Diagnostikare, which is transforming digital healthcare in Mexico, integrated our symptom checker API, improving patient care efficiency by 39%. This tool quickly connects patients to physicians, shortens visits by 7.5 minutes and improves readiness.
Our solution also led to 39% of new patients choosing single-payer telemedicine, with 28% of those patients choosing teleconsultation over emergency room visits. The standardized triage process also received high ratings from call center operators.
The HIMSS AI in Healthcare Forum will take place December 14-15, 2023 in San Diego, California. More information and registration.
Follow Bill's HIT coverage on LinkedIn: Bill Siwicki
Email him: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.