How AI Can Improve Medical Diagnosis

How do medical specialists diagnose conditions? They look at our symptoms, use the knowledge they have gained in practice, apply tools and techniques, and figure out what they think is wrong with us. Then they take care of treating us. It sounds simple enough, but in reality it is often very complex.

Artificial intelligence has a long history of helping doctors diagnose and is proving to be a very useful tool in a wide range of medical disciplines. It is far from ubiquitous, but it is helping clinicians across a broad spectrum, with very positive results.

Quick diagnosis and efficient use of resources

A good way to understand the benefits that AI brings is in the context of real world examples.

The Moorfields Eye Hospital NHS Foundation Trust uses AI to diagnose eye disease and so far the system has made the right referral decisions for over 50 eye diseases with 94% accuracy. Clinical trials and regulatory approval are needed before the technology can be widely used, but the opportunity to help clinicians diagnose faster and prioritize people whose eyesight depends on urgent treatment is exciting for the patient. confidence.

Valerie Phillips, who works in MedTech at PA Consulting, gave some other examples used in the UK. “Kheiron Medical is deploying AI software and deep learning tools to help radiologists screen for breast cancer … [and] HeartFlow creates a personalized 3D model of a patient’s heart from their coronary CT scan and can assess the impact of a blockage on blood flow, ”she explains. IT pro.

Phillips adds, “By bringing together multiple sources of data, then the doctor doesn’t have to search for the information they need, which speeds up their diagnosis and decision-making. Likewise, automating manual tasks and allowing physicians to confirm, assess, quantify, track and report actions automatically makes them more efficient.

The technology is already well received by physicians. In a press release, Dr Philip Strike, interventional cardiologist at Queen Alexandra Hospital in Portsmouth, said HeartFlow “has transformed our paradigm for investigating chest pain. It has dramatically reduced the number of patients requiring invasive investigation. and enabled strategic targeting of treatment for patients who still require invasive angiography, saving time and money ”.

Associated resource

Diversity in the digital workplace

The future of work is a collaborative effort between humans and robots

Download now

AI and general medicine

AI is also used in a more general diagnostic environment, including by general practitioners. Doctorlink is an app-based system available on phone, tablet, and web browser that uses a symptom assessment tool. Firms using the service can also accept appointment bookings through it.

Dr Ravi Tomar, a general practitioner in London whose practice uses Doctorlink, tells us: “In the first year alone, one in five patients were referred to more appropriate forms of care, such as self-care or the local pharmacy. . – and patient phone calls to the office have been reduced by a third, reducing the time and resources of clinicians and administrative staff.

Tomar also says the system has improved the patient experience as well. “Prior to adopting Doctorlink’s health assessment platform in October 2018, we used a standard 8:00 am daily triage phone system for appointment bookings,” he explains. “Like so many other practices, this meant our books were full within hours and we had to turn patients away.”

Tomar understands, however, that people are wary of the idea of ​​AI replacing healthcare professionals. Therefore, people registered with his medical practice can join the system if they wish, but also still have access to more traditional methods. “Success isn’t about 100% adherence, it’s about proper use by the right patients,” he says. “I don’t see AI consultations replacing a patient’s time with their own doctor.”

However, AI in healthcare is still in its infancy and is currently being used relatively little. Healthcare professionals address both the clinical successes and the cultural and ethical aspects of using AI. Phillips sums up where the medical profession is and what remains to be done, telling us, “There needs to be careful consideration of the type of AI, the applications offered and the results provided, the triage, the diagnosis, the taking. decision making, second reading, specific clinical area, established clinical practice, risk assessment and regulatory environment. Only then can AI become a standard medical tool.

Featured Resources

Hybrid cloud for video surveillance

What is it and why you’ll want one

Free download

Are you ready for the hybrid workplace?

Invest in headsets and webcams to increase employee productivity

Insights on the digital transformation of CIOs for CIOs

Pilots, co-pilots and transformation engineers

Free download

Protect every edge to make hackers’ jobs harder, not yours

How to support and secure hybrid architectures

Free download


Source link