In this paper, we present the development of a platform to collect data from cases diagnosed with mental disorders. It includes the use of a Machine Learning classification algorithm, k-NN with TF-IDF, to automatically identify the type of mental disorder suffered by a patient given his/her symptoms, when evaluated by a mental health professional. The platform called “Psycho Web” has a friendly web interface that will allow ergonomic interaction between the mental health professional and the system. The dataset used for the initial evaluation of our platform is composed of 114 instances in total, 56% of which were obtained from the taxonomy proposed by ICD-10. The rest of the instances correspond to real cases, whose symptoms and diagnoses were taken by professionals who voluntarily collaborated with the project. A raw application of the algorithm to the data available shows results with errors that go down to 5%.
|Title of host publication||Advances in Neuroergonomics and Cognitive Engineering - Proceedings of the AHFE 2019 International Conference on Neuroergonomics and Cognitive Engineering, and the AHFE International Conference on Industrial Cognitive Ergonomics and Engineering Psychology, 2019|
|Number of pages||12|
|State||Published - 1 Jan 2020|
|Event||AHFE International Conference on Neuroergonomics and Cognitive Engineering, 2019 and the AHFE International Conference on Industrial Cognitive Ergonomics and Engineering Psychology, 2019 - Washington D.C., United States|
Duration: 24 Jul 2019 → 28 Jul 2019
|Name||Advances in Intelligent Systems and Computing|
|Conference||AHFE International Conference on Neuroergonomics and Cognitive Engineering, 2019 and the AHFE International Conference on Industrial Cognitive Ergonomics and Engineering Psychology, 2019|
|Period||24/07/19 → 28/07/19|
Bibliographical noteFunding Information:
Acknowledgments. This work was supported by IDEIAGEOCA Research Group of Univer-sidad Politécnica Salesiana in Quito, Ecuador.
© Springer Nature Switzerland AG 2020.
- Diagnosis prediction
- Machine learning
- Mental disorders