The secret of improving the management of population health can be in our pockets

The greatest priority of modern health care is perhaps to find ways to improve the health of the population, as measured by improving results and the reduction in overall costs, aligned with the objectives of value-based care.

But the effective management of population health is full of 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 about the capacity of our besieged health system to take up such an ambitious challenge in the midst of the hospital’s margins, paralyzing work shortages and a reduced public health infrastructure.

Waiting for something to change is no longer an option. It is widely recognized that technology must play a leading role in resolving the health challenges of the population by automating key parts of the process, stimulating efficiency and reducing costs, especially outside the hospital.

Fortunately, there is a device that is already in your pocket that can monitor vital signs of health, make cognitive assessments and encourage reconciliation / adhesion of medicines: your smartphone.

Ubiquity and advanced technology

Now used by more than 90% of Americans, smartphones are equipped with a variety of sophisticated sensors, such as GPS, gyroscope, accelerometer, magnetometer, proximity, ambient light, microphones and high resolution cameras.

When associated with progress in automatic learning models (AI), these sensors can measure almost all physiological metrics that you can get from remote patient monitoring (RPM), including vital signs, brain health and drug digitization.

The dream of data analyzer Handheld Star Trek Kniter has arrived, as researchers predicted it in a 2019 study: “The smartphone and its integrated sensors coupled with current communication information and technologies have opened a new opportunity window for profitable distance health services.” The authors have added: “Incredible improvements in processing and storage of data in modern smartphones can allow faster, real -time execution and on board complex predictive algorithms and / or artificial intelligence technologies (IA) using the high volume of raw data measured by smartphone sensors.”

Since then, AI health care models have made major progress. Google said last year, its Med-Gemini models had obtained 91.1% precision on the Medqa reference, surpassing the GPT-4 of the AI ​​opened in the understanding and analysis of the medical text, images and data in real time. Meanwhile, the explorer of articulated medical intelligence from Google (friend), a diagnostic chatbot of AI, recently paired or surpassed human clinicians in disease management consultations with several visits in a randomized study.

RPM limits

Cost reduction was the momentum behind the diet, which is based on a collection of connected health devices to monitor the vital key signs for patients most at risk of serious health crisis requiring hospitalization or readmission.

RPM can be part of the solution. In my old business, we have seen average overall care costs lower by more than 50% and a significant decrease in mortality when we have twinned patients at risk with our diet kits and our clinicians with our portal. The platform has maintained healthy patients at home and outside the hospital.

But the regime has a significant cost and offers limited opinions on the overall health of each patient. The devices are limited to the measurement of vital signs, to promote a reactionary approach to distance care and can cost up to $ 1,000 per patient, with continuous support and logistical expenses exceeding $ 50 per month. In addition, nurses who should focus on clinical tasks find themselves rather managing lost or defective devices.

Due to these high costs and these logistical complications, no one has been able to develop the scheme to meet the health needs of the population.

Proactive, not responsive

On the other hand, AI models can now listen to the smartphones recordings of a speaking user to detect light cognitive impairments, stress, anxiety, depression and even the first signs of dementia, Alzheimer and Parkinson. The models are now trained to recognize drugs with a simple photo with precision, announcing enormous drug management potential, membership and the many beneficial health effects.

All this leads to health management of the proactive rather than reactive population. It eliminates the high cost of devices and also widens the objective of what clinicians can observe.

Although these AI models can detect the millions of millions of data from almost instantly, they can also scrutinize the mockery of clinical data of “health signal” that they create to surface significant clinical information, using global knowledge of health care best practices to highlight the next best actions for improved results at lower costs. This is another significant advantage on the traditional diet, which relies on overloaded nurses to analyze the data and determine if the patients are stable or need an intervention.

Together, these new health signals can work together to find critical information. For example, imagine an elderly person who is likely to fall because his medication against depression has side effects of high heart rate and dizziness. A brain health signal could indicate that it no longer presents signs of depression and may no longer need the drug, which reduces its frequent falls and its emergency visits.

The implications

Together, these technological advances are very promising for the management of the health of the population.

• We can allow proactive and preventive care by eliminating obstacles to access, especially for patients who live in rural urban areas or low -served low income. Thanks to the continuous collection of passive data, technology can identify subtle physiological changes that could be indicative of more serious health problems, such as early diabetes, neurodegenerative diseases or heart disease. AI models can then relay them to clinicians to encourage previous intervention, potentially preventing more expensive complications or hospitalizations.
• We can customize large -scale health management while models analyze the rich sets of data from clinical actions associated with results for the health of the population to adapt information and recommendations to individual patients within a population.
• We can strengthen patient engagement and adherence to therapeutic patterns by reaching patients where they are already, without asking them to use separate devices, unless necessary or medically necessary.
• Finally, we can generate precious trains of real -scale evidence to help feed research, discovery of drugs and effective public health strategies.

The rapid progress of AI and smartphones technologies are promising for many stakeholders in the health system – providers, payers, pharmaceutical drug manufacturers and public health agencies – which must understand what is happening with the patient in real time.

We now have the possibility of achieving what the diet can deliver on an individual basis, and even more, on the level of the health of the population.

Photo: Janwillemkunnen, Getty Images

This message appears through the Medcity influencers program. Anyone can publish their point of view on business and innovation in health care on Medcity News through Medcity influencers. Click here to find out how.