A Machine Learning Model for Evaluating Imported Disease Screening Strategies in Immigrant Populations

View More View Less
  • 1 Group of Inverse Problems, Optimization and, Machine Learning, University of Oviedo, Asturias, Spain;
  • | 2 Department of Microbiology, Hospital Universitario Central de Asturias (HUCA), Oviedo, Spain;
  • | 3 Instituto de Investigación Sanitaria del Principado de Asturias, Oviedo, Spain;
  • | 4 Internal Medicine Department, Hospital de la Cruz Roja, Gijón, Spain;
  • | 5 Internal Medicine Department, Hospital Universitario Central de Asturias (HUCA), Oviedo, Spain;
  • | 6 Departamento de Biología Funcional, Área de Microbiología, University of Oviedo, Asturias, Spain;
  • | 7 Tropical Medicine Unit, Hospital Universitario Central de Asturias (HUCA), Oviedo, Spain;
  • | 8 Department of Medicine. University of Oviedo, Asturias, Spain

Given the high prevalence of imported diseases in immigrant populations, it has postulated the need to establish screening programs that allow their early diagnosis and treatment. We present a mathematical model based on machine learning methodologies to contribute to the design of screening programs in this population. We conducted a retrospective cross-sectional screening program of imported diseases in all immigrant patients who attended the Tropical Medicine Unit between January 2009 and December 2016. We designed a mathematical model based on machine learning methodologies to establish the set of most discriminatory prognostic variables to predict the onset of the: HIV infection, malaria, chronic hepatitis B and C, schistosomiasis, and Chagas in immigrant population. We analyzed 759 patients. HIV was predicted with an accuracy of 84.9% and the number of screenings to detect the first HIV-infected person was 26, as in the case of Chagas disease (with a predictive accuracy of 92.9%). For the other diseases the averages were 12 screenings to detect the first case of chronic hepatitis B (85.4%), or schistosomiasis (86.9%), 23 for hepatitis C (85.6%) or malaria (93.3%), and eight for syphilis (79.4%) and strongyloidiasis (88.4%). The use of machine learning methodologies allowed the prediction of the expected disease burden and made it possible to pinpoint with greater precision those immigrants who are likely to benefit from screening programs, thus contributing effectively to their development and design.

    • Supplemental Materials (PDF 158 KB)

Author Notes

Address correspondence to Azucena Rodríguez-Guardado, Internal Medicine Unit, Hospital Universitario Central de Asturias, Avenida de Roma s/n 33011, Oviedo, Spain. E-mail: azucenarodriguez@telecable.es

These authors contributed equally to this work.

Financial support: This research received no specific grant from any funding agency, commercial or not-for-profit sectors. The corresponding author had full access to all the data in the study and takes responsibility for the decision to submit for publication.

Disclosure: J. A. B. reports grants from Seegene Company, HAIN Company, and, Cepheid and nonfinancial support to Congress Attendance from Werfen Company (Seegene Company distribution in Spain) outside the submitted work; A. G-P reports nonfinancial support from Amgen, Daiichi Sankyo, MSD, Pfizer, Gilead, Boehringer Ingelheim, and, Esteve to Congress Attendance outside the submitted work; R-P reports nonfinancial support from DiaSorin Company to Congress Attendance Support outside the submitted work; F. V. reports personal fees and nonfinancial support from Werfen Company (Seegene Company distribution in Spain), BioMerieux, MSD, Roche, and, Pfizer; grants from Seegene, HAIN, and, Cepheid, outside the submitted work; A. R-G reports grants from Correvio, and non-financial support from Pzifer, MSD, and, Gilead, to Congress Attendance Support outside the submitted work; A. G-P reports nonfinancial support from Vitro S.A, to Congress Attendance Support outside the submitted work; J. L. F-M, E. de A-G, L. S., C. M., and, N. M-S have nothing to disclose.

Authors’ addresses: Juan L. Fernández-Martínez and Enrique de Andrés-Galiana, Group of Inverse Problems, Optimization and, Machine Learning, University of Oviedo, Calle San Francisco, Oviedo, Spain, E-mails: jlfmuniovi@gmail.com and ej.deandres@gmail.com. José A. Boga and Jonathan Fernández, Department of Microbiology, Hospital Universitario Central de Asturias, Oviedo, Spain, and Instituto de Investigación Sanitaria del Principado de Asturias, Oviedo, Spain, E-mails: joseantonio.boga@sespa.es and jofersua@hotmail.com. Luis Casado, Internal Medicine Department, Hospital de la Cruz Roja, Gijon, Spain, E-mail: legioxxi@yahoo. Candela Menéndez, Alicia García-Pérez, Noelia Moran-Suarez, and María Martinez-Sela, Internal Medicine Department, Hospital Universitario Central de Asturias, Oviedo, Spain, E-mails: candela1987@hotmail.com, apuali111@gmail.com, noemorsua@gmail.com, and minsela@gmail.com. Fernando Vázquez, Department of Microbiology, Hospital Universitario Central de Asturias (HUCA), Oviedo, Spain, and Departamento de Biología Funcional, Área de Microbiología, University of Oviedo, Asturias, Spain. Azucena Rodríguez-Guardado, Tropical Medicine Unit, Hospital Universitario Central de Asturias (HUCA), Oviedo, Spain, E-mail: azucenarodriguez@telecable.es.

Save