Parkinson’s Disease Diagnosis: Towards Grammar-based Explainable Artificial Intelligence

Machine Learning (ML) approaches are vastly used for supporting humans in decision-making processes. However, the poor explainability associated to their behavior hampers their application in fields were the impact of the decision is critical, as it is the case for medical application, since physicians cannot simply use the predictions of the model but they must trust the results it provides. This work focuses on the automatic detection of Parkinson’s disease (PD), whose impact on both the individual’s quality of life and social well-being is constantly increasing with the aging of the population. To this end, we propose an explainable approach based on Genetic Programming, called Grammar Evolution (GE). This technique uses context-free grammar to describe the language of the programs to be generated and evolved. In this case, the generated programs are the explicit classification rules for the diagnosis of the subjects. The results of the experiments obtained on the publicly available HandPD data set show GE’s high expressive power and performance comparable to those of several ML models that have been proposed in the literature.

[1]  Noorbakhsh Amiri Golilarz,et al.  Reliable Parkinson’s Disease Detection by Analyzing Handwritten Drawings: Construction of an Unbiased Cascaded Learning System Based on Feature Selection and Adaptive Boosting Model , 2019, IEEE Access.

[2]  Clayton R. Pereira,et al.  Deep Learning-Aided Parkinson's Disease Diagnosis from Handwritten Dynamics , 2016, 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI).

[3]  Clayton R. Pereira,et al.  A new computer vision-based approach to aid the diagnosis of Parkinson's disease , 2016, Comput. Methods Programs Biomed..

[4]  G E Stelmach,et al.  Micrographia in Parkinson's disease. , 1995, Neuroreport.

[5]  G. Stelmach,et al.  Parkinsons disease and the control of size and speed in handwriting , 1999, Neuropsychologia.

[6]  Angelo Marcelli,et al.  A Decision Tree for Automatic Diagnosis of Parkinson's Disease from Offline Drawing Samples: Experiments and Findings , 2019, ICIAP.

[7]  Michael O'Neill,et al.  PonyGE2: grammatical evolution in Python , 2017, GECCO.

[8]  Una-May O'Reilly,et al.  Genetic Programming II: Automatic Discovery of Reusable Programs. , 1994, Artificial Life.

[9]  Gennaro Vessio,et al.  Dynamic Handwriting Analysis for Neurodegenerative Disease Assessment: A Literary Review , 2019, Applied Sciences.

[10]  Angelo Marcelli,et al.  Automatic Diagnosis of Neurodegenerative Diseases: An Evolutionary Approach for Facing the Interpretability Problem , 2019, Inf..

[11]  John McCarthy,et al.  Recursive functions of symbolic expressions and their computation by machine, Part I , 1959, Commun. ACM.

[12]  Allen Newell,et al.  Human Problem Solving. , 1973 .

[13]  Xia Hu,et al.  Techniques for interpretable machine learning , 2018, Commun. ACM.

[14]  Thomas Wichmann,et al.  Circuits and circuit disorders of the basal ganglia. , 2007, Archives of neurology.

[15]  Angelo Marcelli,et al.  A Neural Scheme for Procedural Motor Learning of Handwriting , 2012, 2012 International Conference on Frontiers in Handwriting Recognition.

[16]  Angelo Marcelli,et al.  A paradigm for emulating the early learning stage of handwriting: Performance comparison between healthy controls and Parkinson's disease patients in drawing loop shapes. , 2019, Human movement science.

[17]  G. Stelmach,et al.  Control of stroke size, peak acceleration, and stroke duration in Parkinsonian handwriting , 1991 .

[18]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[19]  Clayton R. Pereira,et al.  Parkinson Disease Identification Using Residual Networks and Optimum-Path Forest , 2018, 2018 IEEE 12th International Symposium on Applied Computational Intelligence and Informatics (SACI).

[20]  Angelo Marcelli,et al.  Automatic Diagnosis of Parkinson Disease through Handwriting Analysis: A Cartesian Genetic Programming Approach , 2019, 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS).

[21]  Arun Sharma,et al.  Diagnosis of Parkinson’s disease using modified grey wolf optimization , 2019, Cognitive Systems Research.

[22]  Anthony Brabazon,et al.  An investigation into automatically defined function representations in Grammatical Evolution , 2009 .

[23]  Conor Ryan,et al.  Grammatical evolution , 2007, GECCO '07.

[24]  Friedrich L. Bauer,et al.  Revised report on the algorithm language ALGOL 60 , 1963, CACM.

[25]  Clayton R. Pereira,et al.  A Step Towards the Automated Diagnosis of Parkinson's Disease: Analyzing Handwriting Movements , 2015, 2015 IEEE 28th International Symposium on Computer-Based Medical Systems.

[26]  G. Stelmach,et al.  Hypometria and bradykinesia during drawing movements in individuals with Parkinson’s disease , 2009, Experimental Brain Research.