BACKGROUND: There are currently no neuroanatomical biomarkers of anorexia nervosa (AN) available to make clinical inferences at an individual subject level. We present results of a multivariate machine learning (ML) approach utilizing structural neuroanatomical scan data to differentiate AN patients from matched healthy controls at an individual subject level. METHOD: Structural neuroimaging scans were acquired from 15 female patients with AN (age = 20, s.d. = 4 years) and 15 demographically matched female controls (age = 22, s.d. = 3 years). Neuroanatomical volumes were extracted using the FreeSurfer software and input into the Least Absolute Shrinkage and Selection Operator (LASSO) multivariate ML algorithm. LASSO was 'trained' to identify 'novel' individual subjects as either AN patients or healthy controls. Furthermore, the model estimated the probability that an individual subject belonged to the AN group based on an individual scan. RESULTS: The model correctly predicted 25 out of 30 subjects, translating into 83.3% accuracy (sensitivity 86.7%, specificity 80.0%) (p < 0.001; χ 2 test). Six neuroanatomical regions (cerebellum white matter, choroid plexus, putamen, accumbens, the diencephalon and the third ventricle) were found to be relevant in distinguishing individual AN patients from healthy controls. The predicted probabilities showed a linear relationship with drive for thinness clinical scores (r = 0.52, p < 0.005) and with body mass index (BMI) (r = -0.45, p = 0.01). CONCLUSIONS: The model achieved a good predictive accuracy and drive for thinness showed a strong neuroanatomical signature. These results indicate that neuroimaging scans coupled with ML techniques have the potential to provide information at an individual subject level that might be relevant to clinical outcomes.
BACKGROUND: There are currently no neuroanatomical biomarkers of anorexia nervosa (AN) available to make clinical inferences at an individual subject level. We present results of a multivariate machine learning (ML) approach utilizing structural neuroanatomical scan data to differentiate AN patients from matched healthy controls at an individual subject level. METHOD: Structural neuroimaging scans were acquired from 15 female patients with AN (age = 20, s.d. = 4 years) and 15 demographically matched female controls (age = 22, s.d. = 3 years). Neuroanatomical volumes were extracted using the FreeSurfer software and input into the Least Absolute Shrinkage and Selection Operator (LASSO) multivariate ML algorithm. LASSO was 'trained' to identify 'novel' individual subjects as either AN patients or healthy controls. Furthermore, the model estimated the probability that an individual subject belonged to the AN group based on an individual scan. RESULTS: The model correctly predicted 25 out of 30 subjects, translating into 83.3% accuracy (sensitivity 86.7%, specificity 80.0%) (p < 0.001; χ 2 test). Six neuroanatomical regions (cerebellum white matter, choroid plexus, putamen, accumbens, the diencephalon and the third ventricle) were found to be relevant in distinguishing individual AN patients from healthy controls. The predicted probabilities showed a linear relationship with drive for thinness clinical scores (r = 0.52, p < 0.005) and with body mass index (BMI) (r = -0.45, p = 0.01). CONCLUSIONS: The model achieved a good predictive accuracy and drive for thinness showed a strong neuroanatomical signature. These results indicate that neuroimaging scans coupled with ML techniques have the potential to provide information at an individual subject level that might be relevant to clinical outcomes.
Entities:
Keywords:
Anorexia; drive for thinness; machine learning; magnetic resonance imaging
Authors: Gerit Pfuhl; Joseph A King; Daniel Geisler; Benjamin Roschinski; Franziska Ritschel; Maria Seidel; Fabio Bernardoni; Dirk K Müller; Tonya White; Veit Roessner; Stefan Ehrlich Journal: Hum Brain Mapp Date: 2016-11 Impact factor: 5.038
Authors: Lindsay M Squeglia; Tali M Ball; Joanna Jacobus; Ty Brumback; Benjamin S McKenna; Tam T Nguyen-Louie; Scott F Sorg; Martin P Paulus; Susan F Tapert Journal: Am J Psychiatry Date: 2016-08-19 Impact factor: 18.112
Authors: Mon-Ju Wu; Benson Mwangi; Isabelle E Bauer; Ives C Passos; Marsal Sanches; Giovana B Zunta-Soares; Thomas D Meyer; Khader M Hasan; Jair C Soares Journal: Neuroimage Date: 2016-02-13 Impact factor: 6.556
Authors: Luca Lavagnino; Benson Mwangi; Bo Cao; Megan E Shott; Jair C Soares; Guido K W Frank Journal: Int J Eat Disord Date: 2018-02-07 Impact factor: 4.861
Authors: Stefania Tognin; Hendrika H van Hell; Kate Merritt; Inge Winter-van Rossum; Matthijs G Bossong; Matthew J Kempton; Gemma Modinos; Paolo Fusar-Poli; Andrea Mechelli; Paola Dazzan; Arija Maat; Lieuwe de Haan; Benedicto Crespo-Facorro; Birte Glenthøj; Stephen M Lawrie; Colm McDonald; Oliver Gruber; Therese van Amelsvoort; Celso Arango; Tilo Kircher; Barnaby Nelson; Silvana Galderisi; Rodrigo Bressan; Jun S Kwon; Mark Weiser; Romina Mizrahi; Gabriele Sachs; Anke Maatz; René Kahn; Phillip McGuire Journal: Schizophr Bull Date: 2020-02-26 Impact factor: 9.306
Authors: José María Mateos-Pérez; Mahsa Dadar; María Lacalle-Aurioles; Yasser Iturria-Medina; Yashar Zeighami; Alan C Evans Journal: Neuroimage Clin Date: 2018-08-10 Impact factor: 4.881