Using Geographic Information Systems (GIS) in public health is becoming increasingly important as we seek to better understand and address the complex challenges facing our communities. In 2024, we can expect to see even more innovative applications of GIS in the public health field. Here are 8 of the key trends to watch for: 

#1 GeoAI

The expansion of artificial intelligence (AI) in geospatial analysis—GeoAI—is likely to be one of the most important trends for 2024.  Some authors include machine learning (ML) as part of AI, while others use AI primarily to refer to large language models.  

While AI has been adopted in clinical settings to assist with diagnosis, and ML is used widely for image analysis and pattern discernment, such as land use classification from imagery, applications in geospatial analysis are just beginning. 

In 2024, we will likely see AI used in geohealth to identify disease clusters and assist researchers in the “diagnosis” of these clusters to associate them with possible environmental exposures. As the ability to reason solidifies (think about induction, deduction, and abduction) we expect AI to enhance our abilities to generate and evaluate hypotheses regarding the environment, genetic predispositions, and human health outcomes.   

#2 Real-time data analysis and visualization 

GIS will increasingly be used to analyze and visualize real-time data, such as disease outbreaks, weather patterns, and air quality data. This will enable public health officials to make more informed decisions and take proactive action to protect public health.  

#3 Enhanced surveillance

An important problem in geohealth surveillance is the analysis and handling of near real-time data streams. How do we handle Big Data in geohealth

While non-spatial Big Data has been typified by the 3 V’s—Volume, Variety, and Velocity—we have 6 GV’s in geospatial Big Data: Volume, Variety, Velocity Veracity, Value, and Varied Support. This requires automated processes for identifying relevant data sources, data massaging, methods selection, and results interpretation, an expansive field for AI and ML.   

#4 Predictive analytics

GIS will be used to develop predictive models that can help us identify and predict potential health risks, such as outbreaks of infectious diseases or areas with high rates of chronic diseases. This data can then be used to target interventions and preventive measures.

One example is the use of geostatistical models to predict the locations of lead service lines, an important problem in the United States since lead exposure from drinking water causes impaired neurological development in children. Another example is the modeling of trichloroethylene (TCE) in groundwater, an enormous public health problem that is just coming to the forefront.

#5 Mobile applications

In 2024, GIS will be integrated into mobile applications that can be used by public health professionals, healthcare providers, and even the public to access and share data and information. Doing so will make it easier for everyone to stay informed about public health issues and take action to protect their health.  

#6 Data sharing and collaboration

GIS will facilitate the sharing and collaboration of data across different organizations and disciplines. This will enable us to develop a more comprehensive understanding of public health issues and develop more effective solutions.  

An example is the use of maps to rapidly communicate areas of high cancer mortality created by the public health wonks to those making policy decisions, such as congressmen. The ability of GIS to readily convey a complicated story in one or two maps is unrivaled.

#7 Personalized precision medicine

GIS will be used to develop personalized medicine approaches that take into account individual risk factors and environmental exposures. This will lead to more effective and targeted treatment and prevention strategies.  

#8 Geospatial Reasoning and AI

Geospatial reasoning requires AI that follows logical constructs, a heavy lift when we consider issues of AI hallucination, for example. But Q* (Qstar) recently solved basic math equations, a problem in mathematical logic that requires application of rules such as propositions, transitive properties, association and so on.

Is the next step then logical reasoning along the lines of Strong Inference (1), the ability to generate hypotheses, interpret results to create plausible sets of explanations, and perhaps find the underlying causes of disease?  Perhaps the biggest payoff, if attainable, is semi-automated hypothesis generation based on logical approaches, including induction, deduction, and abduction, that will accelerate both basic practice and in-depth research. 

The Future of Geospatial Analysis 

We are at an inflection point in geospatial analysis, much like the quantitative revolution that occurred in the 60’s and 70’s.  Whereas that revolution changed how we interact with and analyze geospatial data, this revolution will change how we handle enormous data streams and apply systematic ways of scientific reasoning to obtain transformational advances in knowledge.   

 

  1. Strong Inference: Certain systematic methods of scientific thinking may produce much more rapid progress than others. John R. Platt Authors Info & Affiliations Science 16 Oct 1964 Vol 146, Issue 3642 pp. 347 – 353 DOI: 10.1126/science.146.3642.347