How AI can help the public health sector cope with future crises

From COVID-19 to monkey pox and intermittent polio anxiety, concerns about public health crises have increased significantly in recent years.

Living in a globally connected world amid climate change and a growing population has enabled the emergence of more frequent viruses and promoted their spread. An investigation study Last year it was estimated that the risk of outbreaks of new diseases will triple in the coming decades. Fortunately, there have been significant technological advances that can help minimize the impact of these global health problems.

As health crises have increased, so has the power and practice of artificial intelligence (AI) in support of public health. Several factors have played a role in this – including rapid software developments, improved connectivity, mobile communications and cloud computing – and have been boosted even more quickly by the pressing needs resulting from the emergence of COVID.

Consequently, the Centers for Disease Control and Prevention (CDC) have successfully used AI and machine learning (ML) technologies to accelerate their data management and analysis of different demographics and populations, enabling them to predict different COVID variants, vaccination distribution and tracking rates and much more.

Harnessing the wealth of data

The possibilities for these technologies in the public health sector do not stop with these applications or with COVID. They can be used by public health leaders to effectively inform community health and public policy decisions and for individual health care.

AI is already widely used in healthcare – from adopting the right data science platform, to going beyond descriptive analytics, to predictive analytics for more actionable insights. It is also evident in applications ranging from predicting the clinical outcomes of COVID patients to the discovery of new drugs to fight disease.

One of the key challenges is leveraging the vast amounts of information now available from a variety of sources to gain meaningful insights. The newer data management platforms enable public health agencies to aggregate, manage and analyze data in various formats. This includes unstructured data such as sensor data, case worker notes, and social media posts, most of which are not directly usable by previous platforms.

The collected data can then be segmented and assessed to get a clearer picture of the general health of the population. Predictive analyzes based on this data can identify emerging trends and risk factors for disease and suggest the allocation of limited health care resources.

AI can also be used to detect the emergence and spread of new diseases.

For example, Canadian company Blue Dot saw COVID before the World Health Organization. Their goal was to “spread knowledge faster than the diseases spread”. The company designed an application that uses ML and AI-powered natural language processing (NLP) to monitor a large number of online information sources to detect, locate and conceptualize the spread of infectious diseases.

They then went on to predict the spread of the disease to different parts of the world and then determine the possible consequences of the spread. Building on these capabilities, the US National Science Foundation (NSF) recently announced a research and collaboration grant program to predict and prevent the next infectious disease outbreak, making a significant contribution to public health efforts. .

AI and ML are increasingly being used for disease prevention and management. For example, an ML platform developed by scientists in Australia can: detect signs of depression in posts people post on social media.

NLP is quickly becoming a powerful public health tool. It supports analysis and data extraction from scientific literature, technical reports, medical records, social media, surveys, registries and other documents to support public health functions. Among other things, this technique was able to efficiently and accurately identify evidence of: problem opioid use through the rapid analysis of large amounts of electronic health records. NLP can also aid in disease prevention strategies through more efficient evaluation of the safety and effectiveness of interventions.

The use of these tools to scan medical records is also increasing. Researchers from the University of Pennsylvania and the University of Florida, for example, recently announced that they had been awarded a grant to use AI and ML to identify which patients are at risk of developing various inflammatory rheumatic diseases. The predictions will be derived from information already available through electronic health records and could significantly speed up diagnosis.

In addition, NLP is now used for: screen new drugs and has achieved 97% accuracy in identifying promising drug candidates. Researchers at the University of Central Florida devised a self-attention mechanism to learn which parts of a protein interact with the drug compounds, while achieving state-of-the-art prediction performance.

Hospitals are also finding new applications for AI technologies. Combining AI with whole genome sequencing leads to: faster detection outbreaks of infectious diseases in a hospital setting. In addition, hospital systems are now using AI to monitor their clinical workflows for: the onset of sepsis, allowing them to identify patients with sepsis or septic shock faster than standard methods. Rapid detection is critical to lowering the death rate in hospitals. Of the patients who die in hospitals, one in three has sepsis.

All in all, AI technologies can provide many of the advanced tools that public health organizations need now.

AI and disease diagnoses: earlier and more accurate

All these AI tools enable earlier and more accurate disease diagnoses than ever before. At the individual level, AI and ML algorithms are increasingly able to generate outputs for clinicians, leading to better diagnoses and better understanding of diseases.

A recent example is a new AI model for: diagnosis of cognitive impairment. The researchers hope this will lead to further improvements in the diagnosis of Alzheimer’s disease and other neurodegenerative disorders. AI-powered chatbots now provide valuable support and advice to patients suffering from anxiety or depression, allowing them to share their emotional issues without fear of being judged, while also giving advice.

Advances in AI and ML are increasing and reflecting the overall improvement rate for these technologies. This ranges from discovering medicines to robotics. Predictive analytics and NLP are particularly promising technologies that support evidence-based decision making in public health.

Thanks to these technologies, public health is getting better at identifying diseases and high-risk conditions in near real time. The hope is that this can lead to a reduction in disease across the population and to greater equity in access to and quality of health care.

Prasad Joshi is SVP and Head of Infosys Center for Emerging Technology Solutions (iCETS).