The secret to improving population health management may be our pockets

Perhaps the biggest priority for modern healthcare is finding ways to improve population health, measured by improving outcomes and reducing overall costs, aligning with the goals of value-based care.

However, the challenges of effectively managing population health are challenges, including lack of access to care, health disparities, and the amount of work required to manage patients outside the four walls of the hospital.

We must also be honest, because the capacity of the healthcare system we are trapped in has taken on such ambitious challenges amid hospital margins shrinking, labor shortages and reduced public health infrastructure.

Something waiting for changes is no longer an option. It is widely recognized that technology must address population health challenges by automating critical parts of the process, increasing efficiency and reducing costs, especially outside hospitals.

Fortunately, there is a device in your pocket that can monitor healthy life, perform cognitive assessments and encourage drug reconciliation/compliance: your smartphone.

ubiquitous technology

Now, over 90% of Americans in smartphones use it, equipped with a variety of sophisticated sensors such as GPS, gyroscopes, accelerometers, magnetometers, proximity, ambient light, microphones, microphones, and high-resolution cameras.

When paired with advances in machine learning (AI) models, these sensors measure nearly every physiological metric you can get from remote patient monitoring (RPM) devices, including health, brain health, and drug scans.

As the researchers predicted in a 2019 study, the dream of handheld Star Trek 3 data analyzer has arrived: “Smartphones and their embedded sensors, as well as today’s information and communication technologies, open new windows of opportunity for cost-effective telehealth services.” The authors add, “Incredible improvements in processing and data storage capabilities in modern smartphones may enable complex prediction algorithms and/or artificial intelligence (AI) technologies to measure high volumes of raw data using smartphone sensors.”

Since then, significant advances have been made in the AI ​​healthcare model. Google said last year that its MED-GEMINI model achieved 91.1% accuracy on the MEDQA benchmark, outperforming GPT-4, which turned on AI in understanding and analyzing medical text, images and real-time data. Meanwhile, Google’s Diagnostic AI Chatbot (AMIE) matched or outperformed human clinicians in a randomized study in a multi-access disease management consultancy, Google’s Expression Medical Intelligence Explorer (AMIE).

RPM limitations

Reduced costs are the driving force behind RPM, which relies on a range of interrelated health devices to monitor the critical vitality of patients, as patients face the highest risk of a severe health crisis and need to be hospitalized or readmission.

RPM can be part of the solution. At my former company, the average overall cost of care dropped by more than 50% and the mortality rate was significantly reduced when we paired our high-risk patients with our RPM suite and clinicians with the portal. The platform enables patients to be healthy at home and outside the hospital.

But RPM is expensive and offers a limited view of the overall health of each patient. The equipment is limited to measuring vitality, facilitating a reactionary approach to care, which costs up to $1,000 per patient, while ongoing support and logistics costs exceed $50 per month. Additionally, nurses who should focus on clinical tasks will find themselves and instead manage missing or malfunctioning equipment.

Due to these high cost and logistical complications, no one has been able to expand RPM to meet population health needs.

Proactive, no response

In contrast, AI models can now listen to smartphone records of users’ speeches to detect mild cognitive impairment, stress, anxiety, depression, and even early signs of dementia, Alzheimer’s and Parkinson’s. Models are now being trained to accurately identify a simple photo that heralds the great potential of drug management, adherence, and many beneficial downstream health effects.

All of this leads to proactive rather than reactive population health management. It eliminates high equipment costs and also expands the lens that clinicians can observe.

While these AI models can detect patterns of millions of data points almost immediately, they can also highlight the transformation of clinical “health signal” data for their best practice health care by using the world’s best practice health care knowledge to highlight the transformation of their best practice health care clinical “health signal” data at lower cost improvement results. This is another important advantage over traditional RPM, which relies on overburdened nurses to parse data and determine whether patients are stable or require intervention.

Together, these new health signals can discover critical insights. For example, imagine an elderly person at risk of falling due to the side effects of depression medications with high heart rate and dizziness. Brain health signals may indicate that she no longer shows signs of depression and may no longer need medication, reducing her frequent falls and access to ED.

meaning

To sum up, these technological advances have great hope for population health management.

• We can take proactive and preventive care by removing barriers, especially for patients living in underserved rural or low-income urban areas. Through continuous, passive data collection, the technology can identify subtle physiological changes that may indicate more serious health problems such as early diabetes, neurodegenerative diseases, or heart disease. AI models can then pass these models to clinicians to encourage early intervention and potentially prevent more expensive complications or hospitalizations.
• When the model analyses rich clinical action datasets paired with population health outcomes to tailor individual patients in the population, we can personalize health management on a large scale.
• Unless there is an acute or medical necessity, we can enhance patient participation and compliance with treatment options by contacting patients that have arrived without their use of separate devices.
• Finally, we can generate valuable real-world evidence on a large scale to help promote research, drug discovery, and effective public health strategies.

Rapid advances in AI and smartphone technology are expected to see the progress of many stakeholders in the healthcare system (providers, payers, pharmaceutical drug manufacturers and public health agencies) in real-time.

Now we have the opportunity to achieve something that RPM can deliver individually on a scale of population health.

Photo: Janwillemkunnen, Getty Images

This article passed Mixed Influencer Programs. Anyone can post opinions on MedCity News’ healthcare business and innovation through MedCity Remacence. Click here to learn how.