FASDetect as a machine learning-based screening app for FASD in youth with ADHD

Lukas Ehrig; Ann-Christin Wagner; Heike Wolter; Christoph U Correll; Olga Geisel; Stefan Konigorski

doi:10.1038/s41746-023-00864-1

FASDetect as a machine learning-based screening app for FASD in youth with ADHD

NPJ Digit Med. 2023 Jul 19;6(1):130. doi: 10.1038/s41746-023-00864-1.

Authors

Lukas Ehrig^#^{1

2}, Ann-Christin Wagner^#², Heike Wolter², Christoph U Correll^{2

3

4}, Olga Geisel², Stefan Konigorski^{5

6

7

8}

Affiliations

¹ Digital Health Center, Hasso Plattner Institute for Digital Engineering, University of Potsdam, Potsdam, Germany.
² Department of Child and Adolescent Psychiatry, Charité Universitätsmedizin Berlin, Berlin, Germany.
³ The Zucker Hillside Hospital, Department of Psychiatry, Northwell Health, Glen Oaks, NY, USA.
⁴ Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Department of Psychiatry and Molecular Medicine, Hempstead, NY, USA.
⁵ Digital Health Center, Hasso Plattner Institute for Digital Engineering, University of Potsdam, Potsdam, Germany. stefan.konigorski@hpi.de.
⁶ Department of Child and Adolescent Psychiatry, Charité Universitätsmedizin Berlin, Berlin, Germany. stefan.konigorski@hpi.de.
⁷ Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, USA. stefan.konigorski@hpi.de.
⁸ Department of Statistics, Harvard University, Cambridge, MA, USA. stefan.konigorski@hpi.de.

^# Contributed equally.

Abstract

Fetal alcohol-spectrum disorder (FASD) is underdiagnosed and often misdiagnosed as attention-deficit/hyperactivity disorder (ADHD). Here, we develop a screening tool for FASD in youth with ADHD symptoms. To develop the prediction model, medical record data from a German University outpatient unit are assessed including 275 patients aged 0-19 years old with FASD with or without ADHD and 170 patients with ADHD without FASD aged 0-19 years old. We train 6 machine learning models based on 13 selected variables and evaluate their performance. Random forest models yield the best prediction models with a cross-validated AUC of 0.92 (95% confidence interval [0.84, 0.99]). Follow-up analyses indicate that a random forest model with 6 variables - body length and head circumference at birth, IQ, socially intrusive behaviour, poor memory and sleep disturbance - yields equivalent predictive accuracy. We implement the prediction model in a web-based app called FASDetect - a user-friendly, clinically scalable FASD risk calculator that is freely available at https://fasdetect.dhc-lab.hpi.de .