Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment
Background: Autism spectrum disorder (ASD) diagnosis traditionally relies on behavioral assessments, which can be subjective and often lead to delayed identification. Recent advances in metabolomics and machine learning offer promising alternatives for more objective and precise diagnostic approache...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Metabolites |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-1989/15/5/332 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850126507865800704 |
|---|---|
| author | Shula Shazman Julie Carmel Maxim Itkin Sergey Malitsky Monia Shalan Eyal Soreq Evan Elliott Maya Lebow Yael Kuperman |
| author_facet | Shula Shazman Julie Carmel Maxim Itkin Sergey Malitsky Monia Shalan Eyal Soreq Evan Elliott Maya Lebow Yael Kuperman |
| author_sort | Shula Shazman |
| collection | DOAJ |
| description | Background: Autism spectrum disorder (ASD) diagnosis traditionally relies on behavioral assessments, which can be subjective and often lead to delayed identification. Recent advances in metabolomics and machine learning offer promising alternatives for more objective and precise diagnostic approaches. Methods: First-morning urine samples were collected from 52 children (32 with ASD and 20 neurotypical controls), aged 5.04 ± 1.87 and 5.50 ± 1.74 years, respectively. Using liquid chromatography-mass spectrometry (LC-MS), 293 metabolites were identified and categorized into 189 endogenous and 104 exogenous metabolites. Various machine learning classifiers (random forest, logistic regression, random tree, and naïve Bayes) were applied to differentiate ASD and control groups through 10-fold cross-validation. Results: The random forest classifier achieved 85% accuracy and an area under the curve (AUC) of 0.9 using all 293 metabolites. Classification based solely on endogenous metabolites yielded 85% accuracy and an AUC of 0.86, whereas using exogenous metabolites alone resulted in lower performance (71% accuracy and an AUC of 0.72). Conclusion: This study demonstrates the potential of urine metabolomic profiling, particularly endogenous metabolites, as a complementary diagnostic tool for ASD. The high classification accuracy highlights the feasibility of developing assistive diagnostic methods based on metabolite profiles, although further research is needed to link these profiles to specific behavioral characteristics and ASD subtypes. |
| format | Article |
| id | doaj-art-9884e80b483d4b9c822c49fb647a9cfa |
| institution | OA Journals |
| issn | 2218-1989 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metabolites |
| spelling | doaj-art-9884e80b483d4b9c822c49fb647a9cfa2025-08-20T02:33:55ZengMDPI AGMetabolites2218-19892025-05-0115533210.3390/metabo15050332Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision TreatmentShula Shazman0Julie Carmel1Maxim Itkin2Sergey Malitsky3Monia Shalan4Eyal Soreq5Evan Elliott6Maya Lebow7Yael Kuperman8Department of Mathematics and Computer Science, The Open University of Israel, Raanana 4353701, IsraelAzrieli Faculty of Medicine, Bar Ilan University, Safed 1311502, IsraelMetabolic Profiling Unit, Life Sciences Core Facilities, Weizmann Institute of Science, Rehovot 7610001, IsraelMetabolic Profiling Unit, Life Sciences Core Facilities, Weizmann Institute of Science, Rehovot 7610001, IsraelZiv Medical Center, Safed 1311502, IsraelDepartment of Brain Science, Faculty of Medicine, Imperial College London, London SW3 6LY, UKAzrieli Faculty of Medicine, Bar Ilan University, Safed 1311502, IsraelANeustart, Ltd., Rishon LeZion 7526088, IsraelANeustart, Ltd., Rishon LeZion 7526088, IsraelBackground: Autism spectrum disorder (ASD) diagnosis traditionally relies on behavioral assessments, which can be subjective and often lead to delayed identification. Recent advances in metabolomics and machine learning offer promising alternatives for more objective and precise diagnostic approaches. Methods: First-morning urine samples were collected from 52 children (32 with ASD and 20 neurotypical controls), aged 5.04 ± 1.87 and 5.50 ± 1.74 years, respectively. Using liquid chromatography-mass spectrometry (LC-MS), 293 metabolites were identified and categorized into 189 endogenous and 104 exogenous metabolites. Various machine learning classifiers (random forest, logistic regression, random tree, and naïve Bayes) were applied to differentiate ASD and control groups through 10-fold cross-validation. Results: The random forest classifier achieved 85% accuracy and an area under the curve (AUC) of 0.9 using all 293 metabolites. Classification based solely on endogenous metabolites yielded 85% accuracy and an AUC of 0.86, whereas using exogenous metabolites alone resulted in lower performance (71% accuracy and an AUC of 0.72). Conclusion: This study demonstrates the potential of urine metabolomic profiling, particularly endogenous metabolites, as a complementary diagnostic tool for ASD. The high classification accuracy highlights the feasibility of developing assistive diagnostic methods based on metabolite profiles, although further research is needed to link these profiles to specific behavioral characteristics and ASD subtypes.https://www.mdpi.com/2218-1989/15/5/332autism spectrum disordermetabolomicsurine metabolitesmachine learningdiagnostic biomarkersrandom forest |
| spellingShingle | Shula Shazman Julie Carmel Maxim Itkin Sergey Malitsky Monia Shalan Eyal Soreq Evan Elliott Maya Lebow Yael Kuperman Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment Metabolites autism spectrum disorder metabolomics urine metabolites machine learning diagnostic biomarkers random forest |
| title | Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment |
| title_full | Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment |
| title_fullStr | Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment |
| title_full_unstemmed | Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment |
| title_short | Urine Metabolomic Profiling and Machine Learning in Autism Spectrum Disorder Diagnosis: Toward Precision Treatment |
| title_sort | urine metabolomic profiling and machine learning in autism spectrum disorder diagnosis toward precision treatment |
| topic | autism spectrum disorder metabolomics urine metabolites machine learning diagnostic biomarkers random forest |
| url | https://www.mdpi.com/2218-1989/15/5/332 |
| work_keys_str_mv | AT shulashazman urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT juliecarmel urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT maximitkin urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT sergeymalitsky urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT moniashalan urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT eyalsoreq urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT evanelliott urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT mayalebow urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment AT yaelkuperman urinemetabolomicprofilingandmachinelearninginautismspectrumdisorderdiagnosistowardprecisiontreatment |