Public health has traditionally been understood as a mission-driven industry that could not be profitable but, rather, one that utilizes a non-profit structure. The understanding of public health as a low-profit or non-profit field also came with the expectation that public health was siloed from modern tech advancements. This reputation is changing. Public health solutions can and are furthering goals of promoting health equity and bridging access to healthcare for the world’s most disadvantaged groups, all while driving revenue and leveraging the most up-to-date technologies of our generation, such as artificial intelligence (AI).
AI and Machine Learning in healthcare: advanced tools for early detection
AI has the potential to revolutionize healthcare by using sophisticated algorithms and data analytics. By studying patterns in user-generated health information, AI can detect concerning signs of deteriorating health ahead of time and alert users or medical professionals — a breakthrough that could drastically reduce risks associated with severe conditions like heart disease. With convenient access to wearable technology, such as smartwatches equipped with heart rate monitors, AI can make more accurate predictions about stroke/heart attack probabilities for its users.
RELATED: The Future of Digital Health
One example is a new AI-driven company, HeHealth, which built a solution for the early detection of Monkeypox and other sexually transmitted infections. Due to the recent increased number of cases, the World Health Organization (WHO) declared the disease a public health emergency. As a result of this emergency, patients are looking for additional detection methods, such as home-based testing solutions. HeHealth can help patients determine whether they have symptomatic Monkeypox infection with up to 87% accuracy with this digital test.
Skinive is another example that provides an innovative solution for the detection and risk assessment of skin diseases. By leveraging advanced AI algorithms based on a vast dermatological dataset, the Skinive app cleverly harnesses the power of smartphone cameras to enable thousands of users to monitor their skin health from anywhere effectively — be it their homes or healthcare clinics. Moreover, its versatility extends beyond just individual users; it can also seamlessly integrate with other digital health and beauty apps.
Another example of a startup using AI to advance public health solutions and prevent the spread of infectious diseases is Hyfe AI. Hyfe is a remote monitoring tool that collects data from a smartphone or any wearable, analyzing the number of coughs and the sound of a user's cough. The data gathered using Hyfe’s proprietary AI can provide more accurate data than a single doctor’s visit. Hyfe’s AI algorithm compares each user’s cough data against 250 million cough-like sounds from 83 countries across all continents. Such quick and extensive analysis could not be achieved without AI, allowing Hyfe to screen hundreds and thousands of people at a meager cost per patient across several respiratory disease areas.
Further, machine learning (ML) and AI tools are used to monitor crowd surveillance to predict infectious disease spread using online sources like social media data. ML analysis was used to detect the spread of influenza, arrange for vaccine implementation in influenza hotspots, and draw conclusions on factors related to low vaccine uptake.
While AI is being leveraged to identify, predict, and remedy contracting disease, these predictive learnings are also used to create policies to address health inequities at a population level and directly impact the health insurance industry.
Are you a corporate partner looking to connect with new healthcare technologies? At Plug and Play, we fast-trackinnovation in the healthcare industry. Connect with our most disruptive startups.
Public health solutions through AI
AI in health insurance
AI and ML are used in health insurance to identify at-risk patients and reduce costs in healthcare. ML can reduce healthcare costs to the system in many ways, such as higher quality medical imaging that leads to faster diagnoses, improved health outcomes, and streamlining patient data in electronic health records (EHRs). This improved patient data collection has directly impacted health policy and health insurance processes.
Predictive analytics tools provide a more personalized assessment of a patient’s disease risk and the necessary medical procedures. Implementing “precision public health” practices makes the care experience more straightforward and reduces unnecessary costs. In a context where precision and personalized care become the standard expectation, we will see more tools built to help patients choose the best insurance for their needs, budget, and personal preferences. Putting the patient in a firmer decision-making seat is part of a consumer-driven healthcare trend.
Additionally, the health insurance purchasing process requires insurers to know specific personal details about a patient, such as their family history and the nature of their home life. Previous approaches to capturing this sensitive information involved a verbal phone call from a health insurance representative. AI voice or text conversations can make it easier to capture this information, reducing administrative burdens, timelines, and costs during the underwriting process.
Of course, there are ways in which AI is used to deter public health efforts. One example is Medicare Advantage plans using predictive AI to deny care to patients, which can delay treatment by an additional 2.5 years for patients experiencing a serious illness.
Prevention of chronic disease at its earliest stages
AI can identify patients with harmful health behaviors and those at the highest risk of developing certain chronic diseases. For example, sentiment analysis strategies of Twitter data were used to identify hookah smokers so that the World Health Organization could send targeted campaigns warning against the health repercussions of smoking. These targeted ad interventions use AI to allow public health institutions to be more effective and efficient in reaching those at the highest risk.
Further, innovative technologies like Gabbi are driving public health prevention efforts. Gabbi is driven to reduce the statistic that 90% of women do not know their risk for breast cancer and prevent late-stage breast cancer diagnoses. Users log onto the Gabbi app to take a risk assessment and get an action plan to understand their risk and focus on early prevention for breast cancer. Patients engage with the Gabbi platform entirely from the comfort of their smartphones, so women do not need to wait for infrequent visits to the physician’s office for their subsequent examination.
How AI and Machine Learning in healthcare have shifted public health solutions
There is massive potential for AI to improve our healthcare system and promote equitable healthcare access for some of the most marginalized groups in the US and the world. Although there are some hesitations from healthcare stakeholders, particularly in the public sector, on the use of AI and ML tools given the sensitive nature of patient data, ultimately, such technologies have been able to:
- identify disease earlier than a physician & reduce time to diagnoses for patients
- provide clinical decision-making insights for more personalized treatments
- respond to pandemics at an instant rate
The health insurance industry is rapidly evolving to support AI’s ability to ingest and give insights into massive data sets. Every public health institution should establish its own AI implementation strategies to advance public health solutions further.