Cartesian genetic programming for diagnosis of Parkinson disease through handwriting analysis: Performance vs. interpretability issues

Parziale, Antonio; Senatore, Rosa; Cioppa, Antonio Della; Marcelli, Angelo

doi:10.1016/j.artmed.2020.101984

Cited by 45 publications

(17 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parziale et al [31] addressed a recurrent issue in most published works, clinical interpretability. More specifically, authors frequently use handcrafted features poorly linked to physiological processes and employ less interpretable machine learning models (so-called black boxes).…”

Section: Related Workmentioning

confidence: 99%

Exploiting Spectral and Cepstral Handwriting Features on Diagnosing Parkinson’s Disease

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Exploiting Spectral and Cepstral Handwriting Features on Diagnosing Parkinson’s Disease

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Some other works also use vision sensors [ 14 , 17 , 18 ]. Alternatively, some methods for evaluating PD rely on tablets [ 23 , 24 ] or scanner devices [ 25 ] for handwriting analysis, or microphones for analysing speech [ 26 , 27 ].…”

Section: Related Workmentioning

confidence: 99%

“…The learning algorithms mainly use raw data or extracted features along with classification methods, such as artificial neural networks (ANN) [ 12 , 13 , 16 , 20 , 21 , 24 ], random forests (RF) [ 14 , 15 , 19 , 23 , 26 ], support vector machines (SVM) [ 22 , 23 ], and k -nearest neighbours (KNN) [ 26 ], among others. For example, in [ 20 , 21 ], restricted Boltzmann machines are trained using features extracted from wrist-worn accelerometer data in a home environment to predict PD state.…”

Section: Related Workmentioning

confidence: 99%

Multimodal Classification of Parkinson’s Disease in Home Environments with Resiliency to Missing Modalities

Heidarivincheh

McConville

Morgan

et al. 2021

Sensors

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a chronic neurodegenerative condition that affects a patient’s everyday life. Authors have proposed that a machine learning and sensor-based approach that continuously monitors patients in naturalistic settings can provide constant evaluation of PD and objectively analyse its progression. In this paper, we make progress toward such PD evaluation by presenting a multimodal deep learning approach for discriminating between people with PD and without PD. Specifically, our proposed architecture, named MCPD-Net, uses two data modalities, acquired from vision and accelerometer sensors in a home environment to train variational autoencoder (VAE) models. These are modality-specific VAEs that predict effective representations of human movements to be fused and given to a classification module. During our end-to-end training, we minimise the difference between the latent spaces corresponding to the two data modalities. This makes our method capable of dealing with missing modalities during inference. We show that our proposed multimodal method outperforms unimodal and other multimodal approaches by an average increase in F1-score of 0.25 and 0.09, respectively, on a data set with real patients. We also show that our method still outperforms other approaches by an average increase in F1-score of 0.17 when a modality is missing during inference, demonstrating the benefit of training on multiple modalities.

show abstract

“…Previous studies have designed batteries to detect features such as variability of spiral width, overall shape, spiral smoothness, pen velocity, and pen pressure. Advancements in digital spiral drawing, computerized feature analysis, drawing task design, and complex machine learning techniques established greater diagnostic ability, achieving impressive classification accuracies ranging from 79.78% to 97.52% [28][29][30][31][32][33][34][35] and area under the receiver operating characteristic curve (AUC) values ranging from 0.82 to 0.992 [33,[36][37][38]. Research has continued to refine, augment, and standardize Archimedean spiral drawing assessments, exploring novel informative features for PD detection [39][40][41][42].…”

Section: Archimedean Spiral Drawings For Diagnosis Of Parkinson's Diseasementioning

confidence: 99%

Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings

et al. 2021

View full text Add to dashboard Cite

Conventional means of Parkinson’s Disease (PD) screening rely on qualitative tests typically administered by trained neurologists. Tablet technologies that enable data collection during handwriting and drawing tasks may provide low-cost, portable, and instantaneous quantitative methods for high-throughput PD screening. However, past efforts to use data from tablet-based drawing processes to distinguish between PD and control populations have demonstrated only moderate classification ability. Focusing on digitized drawings of Archimedean spirals, the present study utilized data from the open-access ParkinsonHW dataset to improve existing PD drawing diagnostic pipelines. Random forest classifiers were constructed using previously documented features and highly-predictive, newly-proposed features that leverage the many unique mathematical characteristics of the Archimedean spiral. This approach yielded an AUC of 0.999 on the particular dataset we tested on, and more importantly identified interpretable features with good promise for generalization across diverse patient cohorts. It demonstrated the potency of mathematical relationships inherent to the drawing shape and the usefulness of sparse feature sets and simple models, which further enhance interpretability, in the face of limited sample size. The results of this study also inform suggestions for future drawing task design and data analytics (feature extraction, shape selection, task diversity, drawing templates, and data sharing).

show abstract

Cartesian genetic programming for diagnosis of Parkinson disease through handwriting analysis: Performance vs. interpretability issues

Cited by 45 publications

References 39 publications

Exploiting Spectral and Cepstral Handwriting Features on Diagnosing Parkinson’s Disease

Exploiting Spectral and Cepstral Handwriting Features on Diagnosing Parkinson’s Disease

Multimodal Classification of Parkinson’s Disease in Home Environments with Resiliency to Missing Modalities

Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings

Contact Info

Product

Resources

About