MACHINE LEARNING & ARTIFICIAL INTELLIGENCE TOOLS IMPROVE ACCESS WITH FINANCIAL INSTRUMENTS FUNDED BY SAVINGS

Machine Learning and Artificial Intelligence tools can identify patients, estimate the costs to the system, quantify the savings from life saving medications and support investment from financial instruments to loan the health system funds to provide.

Many children's diseases can be prevented by a vaccine.  Today, hundreds of thousands of children die or are hospitalized with a preventable children's disease.  Machine learning and artificial intelligence has and can again be applied to identify such disease; RSV, Pneumococcal, Varicella and Prematurity were explored in this instance. 

RSV affects ~100% of children by age 2 and 2% of these babies require hospitalization which kills 60,000 babies annually.  In the USA, only preterm infants are reimbursed for the RSV vaccine and not all receive.  The lives saved and avoiding hospitalization are priceless and in the millions of dollars saved for a preventable vaccine.

Pneumococcal has an instance of 24:10,000 children and 8% of these 24 children die; approximately 2:10,000.  The children lives lost is priceless and the savings is in the millions in which pneumococcal is a devastating illness.  These lives could be saved and avoiding hospitalization if all children were vaccines to prevent or eradicate at some future point pneumococcal illness.

Varicella, chicken pox, in Latin America is not included as the regimen for children whereas it is in many other regions.  Varicella in Mexico alone causes 300,000 hospitalization as estimated from prior studies and publically available secretariat de salud real world database killing approximately 5,300 children annually.  Vaccinating the children population in latin america starting with Mexico and Brazil where measureable public real world data exists can support expanding regional vaccination administration.  What these governments needs is funding from financial services to procure and administer the vaccine within the health system.