Skip to main content
main-content
Top

Tip

Swipe om te navigeren naar een ander artikel

Gepubliceerd in: Journal of Autism and Developmental Disorders 5/2015

01-05-2015 | Original Paper

Applying Machine Learning to Facilitate Autism Diagnostics: Pitfalls and Promises

Auteurs: Daniel Bone, Matthew S. Goodwin, Matthew P. Black, Chi-Chun Lee, Kartik Audhkhasi, Shrikanth Narayanan

Gepubliceerd in: Journal of Autism and Developmental Disorders | Uitgave 5/2015

Log in om toegang te krijgen
share
DELEN

Deel dit onderdeel of sectie (kopieer de link)

  • Optie A:
    Klik op de rechtermuisknop op de link en selecteer de optie “linkadres kopiëren”
  • Optie B:
    Deel de link per e-mail

Abstract

Machine learning has immense potential to enhance diagnostic and intervention research in the behavioral sciences, and may be especially useful in investigations involving the highly prevalent and heterogeneous syndrome of autism spectrum disorder. However, use of machine learning in the absence of clinical domain expertise can be tenuous and lead to misinformed conclusions. To illustrate this concern, the current paper critically evaluates and attempts to reproduce results from two studies (Wall et al. in Transl Psychiatry 2(4):e100, 2012a; PloS One 7(8), 2012b) that claim to drastically reduce time to diagnose autism using machine learning. Our failure to generate comparable findings to those reported by Wall and colleagues using larger and more balanced data underscores several conceptual and methodological problems associated with these studies. We conclude with proposed best-practices when using machine learning in autism research, and highlight some especially promising areas for collaborative work at the intersection of computational and behavioral science.
Bijlagen
Alleen toegankelijk voor geautoriseerde gebruikers
Voetnoten
1
For instance, model over-fitting can occur when training data is included in testing sets, which can inflate confidence in a result that is not likely to replicate in independent samples. Cross-validation is a common solution.
 
2
The work of Wall et al. (2012a) has been extended in Duda et al. (2014). While some methodological issues are resolved, primary conceptual issues remain.
 
3
Analyses we conducted in this paper use these revised ADOS algorithms.
 
4
Apart from 4 Non-Spectrum subjects from the Boston Autism Consortium database.
 
5
Proper application of machine learning usually entails optimizing parameter settings for a chosen classifier. The peak performance of a classifier for a given dataset cannot be achieved without this step. Since optimizing parameter settings for maximal classification performance can lead to over-fitting, an independent test set is required; often a third set called the Development set is used or another layer of cross-validation is performed. In our experiments, we use default parameter settings in order to most closely replicate the methodology employed by Wall et al. (2012a).
 
6
Recall can be used interchangeably with either sensitivity or specificity, which differ only in naming convention of the “true” class.
 
7
It is advisable to test multiple algorithmic approaches to achieve optimal accuracy; however, since this increases potential for over-fitting and consequently inflating results, an independent, held-out dataset is valuable.
 
8
Note that sensitivity and specificity only differ in the naming convention of the “true” or “positive” class, and thus the term recall applies to any class.
 
Literatuur
go back to reference Amaral, D., Dawson, G., & Geschwind, D. (Eds.). (2011). Autism spectrum disorders. Oxford: Oxford University Press. Amaral, D., Dawson, G., & Geschwind, D. (Eds.). (2011). Autism spectrum disorders. Oxford: Oxford University Press.
go back to reference American Psychiatric Association (Ed.). (2013). Diagnostic and statistical manual of mental disorders: DSM- 5. American Psychiatric Association. American Psychiatric Association (Ed.). (2013). Diagnostic and statistical manual of mental disorders: DSM- 5. American Psychiatric Association.
go back to reference Audhkhasi, K., & Narayanan, S. (2013). A globally-variant locally-constant model for fusion of labels from multiple diverse experts without using reference labels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(4), 769–783. CrossRefPubMed Audhkhasi, K., & Narayanan, S. (2013). A globally-variant locally-constant model for fusion of labels from multiple diverse experts without using reference labels. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(4), 769–783. CrossRefPubMed
go back to reference Baldi, P. (2001). Bioinformatics: The machine learning approach. Cambridge, MA: The MIT Press. Baldi, P. (2001). Bioinformatics: The machine learning approach. Cambridge, MA: The MIT Press.
go back to reference Black, M. P., Katsamanis, A., Baucom, B. R., Lee, C. C., Lammert, A. C., Christensen, A., et al. (2013). Toward automating a human behavioral coding system for married couples’ interactions using speech acoustic features. Speech Communication, 55(1), 1–21. CrossRef Black, M. P., Katsamanis, A., Baucom, B. R., Lee, C. C., Lammert, A. C., Christensen, A., et al. (2013). Toward automating a human behavioral coding system for married couples’ interactions using speech acoustic features. Speech Communication, 55(1), 1–21. CrossRef
go back to reference Bone, D., Black, M. P., Lee, C. C., Williams, M. E., Levitt, P., Lee, S., & Narayanan, S. (2012). Spontaneous-speech acoustic–prosodic features of children with autism and the interacting psychologist. In INTERSPEECH (pp. 1043–1046). Bone, D., Black, M. P., Lee, C. C., Williams, M. E., Levitt, P., Lee, S., & Narayanan, S. (2012). Spontaneous-speech acoustic–prosodic features of children with autism and the interacting psychologist. In INTERSPEECH (pp. 1043–1046).
go back to reference Bone, D., Black, M. P., Lee, C. C., Williams, M. E., Levitt, P., Lee, S., & Narayanan, S. (2014, in press). The Psychologist as an Interlocutor in Autism Spectrum Disorder Assessment: Insights from a Study of Spontaneous Prosody. Journal of Speech, Language, and Hearing Research. Bone, D., Black, M. P., Lee, C. C., Williams, M. E., Levitt, P., Lee, S., & Narayanan, S. (2014, in press). The Psychologist as an Interlocutor in Autism Spectrum Disorder Assessment: Insights from a Study of Spontaneous Prosody. Journal of Speech, Language, and Hearing Research.
go back to reference Bone, D., Lee, C. C., Chaspari, T., Black, M. P., Williams, M. E., Lee, S., Levitt, P. & Narayanan, S. (2013). Acoustic–prosodic, turn-taking, and language cues in child–psychologist interactions for varying social demand. In INTERSPEECH (pp. 2400–2404). Bone, D., Lee, C. C., Chaspari, T., Black, M. P., Williams, M. E., Lee, S., Levitt, P. & Narayanan, S. (2013). Acoustic–prosodic, turn-taking, and language cues in child–psychologist interactions for varying social demand. In INTERSPEECH (pp. 2400–2404).
go back to reference Chaspari, T., Bone, D., Gibson, J., Lee, C. C., & Narayanan, S. (2013). Using physiology and language cues for modeling verbal response latencies of children with ASD. In 2013 IEEE International Conference on acoustics, speech and signal processing (ICASSP) (pp. 3702–3706). Chaspari, T., Bone, D., Gibson, J., Lee, C. C., & Narayanan, S. (2013). Using physiology and language cues for modeling verbal response latencies of children with ASD. In 2013 IEEE International Conference on acoustics, speech and signal processing (ICASSP) (pp. 3702–3706).
go back to reference Constantino, J. N., LaVesser, P. D., Zhang, Y., Abbacchi, A. M., Gray, T., & Todd, R. D. (2007). Rapid quantitative assessment of autistic social impairment by classroom teachers. Journal of the American Academy of Child and Adolescent Psychiatry, 46(12), 1668–1676. CrossRefPubMed Constantino, J. N., LaVesser, P. D., Zhang, Y., Abbacchi, A. M., Gray, T., & Todd, R. D. (2007). Rapid quantitative assessment of autistic social impairment by classroom teachers. Journal of the American Academy of Child and Adolescent Psychiatry, 46(12), 1668–1676. CrossRefPubMed
go back to reference Dawson, G., Webb, S., Schellenberg, G. D., Dager, S., Friedman, S., Aylward, E., et al. (2002). Defining the broader phenotype of autism: Genetic, brain, and behavioral perspectives. Development and Psychopathology, 14(3), 581–611. CrossRefPubMed Dawson, G., Webb, S., Schellenberg, G. D., Dager, S., Friedman, S., Aylward, E., et al. (2002). Defining the broader phenotype of autism: Genetic, brain, and behavioral perspectives. Development and Psychopathology, 14(3), 581–611. CrossRefPubMed
go back to reference Duda, M., Kosmicki, J. A., & Wall, D. P. (2014). Testing the accuracy of an observation-based classifier for rapid detection of autism risk. Translational Psychiatry, 4(8), e424. CrossRefPubMedCentralPubMed Duda, M., Kosmicki, J. A., & Wall, D. P. (2014). Testing the accuracy of an observation-based classifier for rapid detection of autism risk. Translational Psychiatry, 4(8), e424. CrossRefPubMedCentralPubMed
go back to reference Freund, Y., & Mason, L. (1999). The alternating decision tree learning algorithm. In ICML (Vol. 99, pp. 124–133). Freund, Y., & Mason, L. (1999). The alternating decision tree learning algorithm. In ICML (Vol. 99, pp. 124–133).
go back to reference Geschwind, D. H., Sowinski, J., Lord, C., Iversen, P., Shestack, J., Jones, P., et al. (2001). The autism genetic resource exchange: A resource for the study of autism and related neuropsychiatric conditions. American Journal of Human Genetics, 69(2), 463. CrossRefPubMedCentralPubMed Geschwind, D. H., Sowinski, J., Lord, C., Iversen, P., Shestack, J., Jones, P., et al. (2001). The autism genetic resource exchange: A resource for the study of autism and related neuropsychiatric conditions. American Journal of Human Genetics, 69(2), 463. CrossRefPubMedCentralPubMed
go back to reference Gotham, K., Risi, S., Pickles, A., & Lord, C. (2007). The autism diagnostic observation schedule: Revised algorithms for improved diagnostic validity. Journal of Autism and Developmental Disorders, 37(4), 613–627. CrossRefPubMed Gotham, K., Risi, S., Pickles, A., & Lord, C. (2007). The autism diagnostic observation schedule: Revised algorithms for improved diagnostic validity. Journal of Autism and Developmental Disorders, 37(4), 613–627. CrossRefPubMed
go back to reference Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1), 10–18. CrossRef Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11(1), 10–18. CrossRef
go back to reference Hu, V. W., & Steinberg, M. E. (2009). Novel clustering of items from the Autism Diagnostic Interview-Revised to define phenotypes within autism spectrum disorders. Autism Research, 2(2), 67–77. CrossRefPubMedCentralPubMed Hu, V. W., & Steinberg, M. E. (2009). Novel clustering of items from the Autism Diagnostic Interview-Revised to define phenotypes within autism spectrum disorders. Autism Research, 2(2), 67–77. CrossRefPubMedCentralPubMed
go back to reference Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI (Vol. 14, No. 2, pp. 1137–1145). Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI (Vol. 14, No. 2, pp. 1137–1145).
go back to reference Lai, M. C., Lombardo, M. V., Chakrabarti, B., & Baron-Cohen, S. (2013). Subgrouping the autism “spectrum”: Reflections on DSM-5. PLoS Biology, 11(4). Lai, M. C., Lombardo, M. V., Chakrabarti, B., & Baron-Cohen, S. (2013). Subgrouping the autism “spectrum”: Reflections on DSM-5. PLoS Biology, 11(4).
go back to reference Lee, H., Marvin, A. R., Watson, T., Piggot, J., Law, J. K., Law, P. A., et al. (2010). Accuracy of phenotyping of autistic children based on internet implemented parent report. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics, 153(6), 1119–1126. Lee, H., Marvin, A. R., Watson, T., Piggot, J., Law, J. K., Law, P. A., et al. (2010). Accuracy of phenotyping of autistic children based on internet implemented parent report. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics, 153(6), 1119–1126.
go back to reference Levitt, P., & Campbell, D. B. (2009). The genetic and neurobiologic compass points toward common signaling dysfunctions in autism spectrum disorders. The Journal of Clinical Investigation, 119(4), 747. CrossRefPubMedCentralPubMed Levitt, P., & Campbell, D. B. (2009). The genetic and neurobiologic compass points toward common signaling dysfunctions in autism spectrum disorders. The Journal of Clinical Investigation, 119(4), 747. CrossRefPubMedCentralPubMed
go back to reference Lord, C., & Jones, R. M. (2012). Annual Research Review: Re-thinking the classification of autism spectrum disorders. Journal of Child Psychology and Psychiatry, 53(5), 490–509. CrossRefPubMedCentralPubMed Lord, C., & Jones, R. M. (2012). Annual Research Review: Re-thinking the classification of autism spectrum disorders. Journal of Child Psychology and Psychiatry, 53(5), 490–509. CrossRefPubMedCentralPubMed
go back to reference Lord, C., Risi, S., Lambrecht, L., Cook, E. H, Jr, Leventhal, B. L., DiLavore, P. C., et al. (2000). The Autism Diagnostic Observation Schedule—Generic: A standard measure of social and communication deficits associated with the spectrum of autism. Journal of Autism and Developmental Disorders, 30(3), 205–223. CrossRefPubMed Lord, C., Risi, S., Lambrecht, L., Cook, E. H, Jr, Leventhal, B. L., DiLavore, P. C., et al. (2000). The Autism Diagnostic Observation Schedule—Generic: A standard measure of social and communication deficits associated with the spectrum of autism. Journal of Autism and Developmental Disorders, 30(3), 205–223. CrossRefPubMed
go back to reference Lord, C., Rutter, M., & Le Couteur, A. (1994). Autism diagnostic interview-revised: A revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders. Journal of Autism and Developmental Disorders, 24(5), 659–685. CrossRefPubMed Lord, C., Rutter, M., & Le Couteur, A. (1994). Autism diagnostic interview-revised: A revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders. Journal of Autism and Developmental Disorders, 24(5), 659–685. CrossRefPubMed
go back to reference Narayanan, S., & Georgiou, P. G. (2013). Behavioral signal processing: Deriving human behavioral informatics from speech and language. Proceedings of the IEEE, 101(5), 1203–1233. CrossRefPubMedCentralPubMed Narayanan, S., & Georgiou, P. G. (2013). Behavioral signal processing: Deriving human behavioral informatics from speech and language. Proceedings of the IEEE, 101(5), 1203–1233. CrossRefPubMedCentralPubMed
go back to reference Picard, R. W. (2000). Affective computing. Cambridge, MA: MIT press. Picard, R. W. (2000). Affective computing. Cambridge, MA: MIT press.
go back to reference Rehg, J. M., Abowd, G. D., Rozga, A., Romero, M., Clements, M. A., Sclaroff, S., & Ye, Z. (2013). Decoding children’s social behavior. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on (pp. 3414–3421). IEEE. Rehg, J. M., Abowd, G. D., Rozga, A., Romero, M., Clements, M. A., Sclaroff, S., & Ye, Z. (2013). Decoding children’s social behavior. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on (pp. 3414–3421). IEEE.
go back to reference Rehg, J. M., Rozga, A., Abowd, G. D., & Goodwin, M. S. (2014). Behavioral imaging and autism. Pervasive Computing, IEEE, 13(2), 84–87. CrossRef Rehg, J. M., Rozga, A., Abowd, G. D., & Goodwin, M. S. (2014). Behavioral imaging and autism. Pervasive Computing, IEEE, 13(2), 84–87. CrossRef
go back to reference Rosenberg, A. (2012). Classifying skewed data: Importance weighting to optimize average recall. In INTERSPEECH (pp. 2242–2245). Rosenberg, A. (2012). Classifying skewed data: Importance weighting to optimize average recall. In INTERSPEECH (pp. 2242–2245).
go back to reference Schuller, B., Steidl, S., & Batliner, A. (2009, September). The INTERSPEECH 2009 emotion challenge. In INTERSPEECH (pp. 312–315). Schuller, B., Steidl, S., & Batliner, A. (2009, September). The INTERSPEECH 2009 emotion challenge. In INTERSPEECH (pp. 312–315).
go back to reference Schuller, B., Steidl, S., Batliner, A., Schiel, F., & Krajewski, J. (2011, August). The INTERSPEECH 2011 Speaker State Challenge. In INTERSPEECH (pp. 3201–3204). Schuller, B., Steidl, S., Batliner, A., Schiel, F., & Krajewski, J. (2011, August). The INTERSPEECH 2011 Speaker State Challenge. In INTERSPEECH (pp. 3201–3204).
go back to reference Wall, D. P., Dally, R., Luyster, R., Jung, J. Y., & DeLuca, T. F. (2012b). Use of artificial intelligence to shorten the behavioral diagnosis of autism. PloS One, 7(8). Wall, D. P., Dally, R., Luyster, R., Jung, J. Y., & DeLuca, T. F. (2012b). Use of artificial intelligence to shorten the behavioral diagnosis of autism. PloS One, 7(8).
go back to reference Wall, D. P., Kosmicki, J. A., DeLuca, T., Harstad, E. B., & Fusaro, V. A. (2012a). Use of machine learning to shorten observation-based screening and diagnosis of autism. Translational Psychiatry, 2(4), e100. CrossRefPubMedCentralPubMed Wall, D. P., Kosmicki, J. A., DeLuca, T., Harstad, E. B., & Fusaro, V. A. (2012a). Use of machine learning to shorten observation-based screening and diagnosis of autism. Translational Psychiatry, 2(4), e100. CrossRefPubMedCentralPubMed
go back to reference Wei, L., Yang, Y., Nishikawa, R. M., & Jiang, Y. (2005). A study on several machine learning methods for classification of malignant and benign clustered microcalcifications. IEEE Transactions on Medical Imaging, 24(3), 371–380. CrossRefPubMed Wei, L., Yang, Y., Nishikawa, R. M., & Jiang, Y. (2005). A study on several machine learning methods for classification of malignant and benign clustered microcalcifications. IEEE Transactions on Medical Imaging, 24(3), 371–380. CrossRefPubMed
go back to reference Ye, Z., Li, Y., Fathi, A., Han, Y., Rozga, A., Abowd, G. D., & Rehg, J. M. (2012). Detecting eye contact using wearable eye-tracking glasses. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing (pp. 699–704). ACM. Ye, Z., Li, Y., Fathi, A., Han, Y., Rozga, A., Abowd, G. D., & Rehg, J. M. (2012). Detecting eye contact using wearable eye-tracking glasses. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing (pp. 699–704). ACM.
Metagegevens
Titel
Applying Machine Learning to Facilitate Autism Diagnostics: Pitfalls and Promises
Auteurs
Daniel Bone
Matthew S. Goodwin
Matthew P. Black
Chi-Chun Lee
Kartik Audhkhasi
Shrikanth Narayanan
Publicatiedatum
01-05-2015
Uitgeverij
Springer US
Gepubliceerd in
Journal of Autism and Developmental Disorders / Uitgave 5/2015
Print ISSN: 0162-3257
Elektronisch ISSN: 1573-3432
DOI
https://doi.org/10.1007/s10803-014-2268-6

Andere artikelen Uitgave 5/2015

Journal of Autism and Developmental Disorders 5/2015 Naar de uitgave