Format

Send to

Choose Destination
Sci Rep. 2018 Oct 4;8(1):14840. doi: 10.1038/s41598-018-33110-w.

Potential identification of vitamin B6 responsiveness in autism spectrum disorder utilizing phenotype variables and machine learning methods.

Author information

1
Tohoku Medical Megabank Organization (ToMMo), Tohoku University, Sendai, Miyagi, Japan.
2
Department of Molecular Epidemiology, Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan.
3
Department of Pharmaceutical Sciences, Tohoku University Hospital, Sendai, Miyagi, Japan.
4
Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Chuo-ku, Tokyo, Japan.
5
Department of Hygiene and Public Health, School of Medicine, Teikyo University, Tokyo, Japan.
6
Division of Public Health, Hygiene and Epidemiology, Tohoku Medical and Pharmaceutical University, Sendai, Miyagi, Japan.
7
Department of Pediatrics, Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan.
8
Department of Education, Art and Science, Yamagata University, Yamagata, Yamagata, Japan.
9
Department of Pediatrics, Saka General Hospital, Shiogama, Miyagi, Japan.
10
Kakuta Child & Allergy Clinic, Tagajo, Miyagi, Japan.
11
Department of Pediatrics, NTT Medical Center Tokyo, Shinagawa-ku, Tokyo, Japan.
12
Bunkyo Education Center, Bunkyo-ku, Tokyo, Japan.
13
Fujimoto Shinjuku Hospital, Shinjuku-ku, Tokyo, Japan.
14
Department of Psychiatry, Miyagi Psychiatric Center, Natori, Miyagi, Japan.
15
Miyagi Disaster Mental Health Care Center, Sendai, Miyagi, Japan.
16
Yasuhara Children's Clinic, Neyagawa, Osaka, Japan.
17
Department of Developmental Disorders, National Institute of Mental Health, National Center of Neurology and Psychiatry, Kodaira, Tokyo, Japan.
18
Tokyo Metropolitan Tobu Medical Center for Children with Developmental Disabilities, Koto-ku, Tokyo, Japan.
19
Tohoku Medical Megabank Organization (ToMMo), Tohoku University, Sendai, Miyagi, Japan. kuriyama@med.tohoku.ac.jp.
20
Department of Molecular Epidemiology, Graduate School of Medicine, Tohoku University, Sendai, Miyagi, Japan. kuriyama@med.tohoku.ac.jp.
21
Department of Disaster Public Health, International Research Institute of Disaster Science, Tohoku University, Sendai, Miyagi, Japan. kuriyama@med.tohoku.ac.jp.

Abstract

We investigated whether machine learning methods could potentially identify a subgroup of persons with autism spectrum disorder (ASD) who show vitamin B6 responsiveness by selected phenotype variables. We analyzed the existing data from our intervention study with 17 persons. First, we focused on signs and biomarkers that have been identified as candidates for vitamin B6 responsiveness indicators. Second, we conducted hypothesis testing among these selected variables and their combinations. Finally, we further investigated the results by conducting cluster analyses with two different algorithms, affinity propagation and k-medoids. Statistically significant variables for vitamin B6 responsiveness, including combination of hypersensitivity to sound and clumsiness, and plasma glutamine level, were included. As an a priori variable, the Pervasive Developmental Disorders Autism Society Japan Rating Scale (PARS) scores was also included. The affinity propagation analysis showed good classification of three potential vitamin B6-responsive persons with ASD. The k-medoids analysis also showed good classification. To our knowledge, this is the first study to attempt to identify subgroup of persons with ASD who show specific treatment responsiveness using selected phenotype variables. We applied machine learning methods to further investigate these variables' ability to identify this subgroup of ASD, even when only a small sample size was available.

PMID:
30287864
PMCID:
PMC6172273
DOI:
10.1038/s41598-018-33110-w
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center