Automatic Detection of Genetic Diseases in Pediatric Age Using Pupillometry

Inherited retinal diseases cause severe visual deficits in children. They are classified in outer and inner retina diseases, and often cause blindness in childhood. The diagnosis for this type of illness is challenging, given the wide range of clinical and genetic causes (with over 200 causative genes). It is routinely based on a complex pattern of clinical tests, including invasive ones, not always appropriate for infants or young children. A different approach is thus needed, that exploits Chromatic Pupillometry, a technique increasingly used to assess outer and inner retina functions. This paper presents a novel Clinical Decision Support System (CDSS), based on Machine Learning using Chromatic Pupillometry in order to support diagnosis of Inherited retinal diseases in pediatric subjects. An approach that combines hardware and software is proposed: a dedicated medical equipment (pupillometer) is used with a purposely designed custom machine learning decision support system. Two distinct Support Vector Machines (SVMs), one for each eye, classify the features extracted from the pupillometric data. The designed CDSS has been used for diagnosis of Retinitis Pigmentosa in pediatric subjects. The results, obtained by combining the two SVMs in an ensemble model, show satisfactory performance of the system, that achieved 0.846 accuracy, 0.937 sensitivity and 0.786 specificity. This is the first study that applies machine learning to pupillometric data in order to diagnose a genetic disease in pediatric age.

[1]  Dursun Delen,et al.  A data analytics approach to building a clinical decision support system for diabetic retinopathy: Developing and deploying a model ensemble , 2017, Decis. Support Syst..

[2]  Ernesto Iadanza,et al.  A convolutional neural network approach to detect congestive heart failure , 2020, Biomed. Signal Process. Control..

[3]  Yogesan Kanagasingam,et al.  Evaluation of Cholinergic Deficiency in Preclinical Alzheimer's Disease Using Pupillometry , 2017, Journal of ophthalmology.

[4]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[5]  Vitor Yano,et al.  Extraction and application of dynamic pupillometry features for biometric authentication , 2015 .

[6]  Oscar Camacho Nieto,et al.  A machine learning approach to medical image classification: Detecting age-related macular degeneration in fundus images , 2017, Comput. Electr. Eng..

[7]  Ernesto Iadanza,et al.  A multi-layer monitoring system for clinical management of Congestive Heart Failure , 2015, BMC Medical Informatics and Decision Making.

[8]  Gabriele Guidi,et al.  Case Study: IBM Watson Analytics Cloud Platform as Analytics-as-a-Service System for Heart Failure Early Detection , 2016, Future Internet.

[9]  Daniel Riccio,et al.  Learning-based approach to segment pigment signs in fundus images for Retinitis Pigmentosa analysis , 2018, Neurocomputing.

[10]  Aki Kawasaki,et al.  Chromatic pupillometry in patients with retinitis pigmentosa. , 2011, Ophthalmology.

[11]  A. J. Roman,et al.  Quantifying rod photoreceptor-mediated vision in retinal degenerations: dark-adapted thresholds as outcome measures. , 2005, Experimental eye research.

[12]  Sejong Oh,et al.  Development of machine learning models for diagnosis of glaucoma , 2017, PloS one.

[13]  Aki Kawasaki,et al.  Characterization of pupil responses to blue and red light stimuli in autosomal dominant retinitis pigmentosa due to NR2E3 mutation. , 2012, Investigative ophthalmology & visual science.

[14]  Donald C Hood,et al.  Toward a clinical protocol for assessing rod, cone, and melanopsin contributions to the human pupil response. , 2011, Investigative ophthalmology & visual science.

[15]  C. Pang,et al.  Genotype–phenotype correlation and mutation spectrum in a large cohort of patients with inherited retinal dystrophy revealed by next-generation sequencing , 2014, Genetics in Medicine.

[16]  Pupil responses derived from outer and inner retinal photoreception are normal in patients with hereditary optic neuropathy. , 2014, Experimental eye research.

[17]  Akshi Kumar,et al.  Machine Learning from Theory to Algorithms: An Overview , 2018, Journal of Physics: Conference Series.

[18]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[19]  Taimur Hassan,et al.  Fully Automated Robust System to Detect Retinal Edema, Central Serous Chorioretinopathy, and Age Related Macular Degeneration from Optical Coherence Tomography Images , 2017, BioMed research international.

[20]  Rishab Gargeya,et al.  Automated Identification of Diabetic Retinopathy Using Deep Learning. , 2017, Ophthalmology.

[21]  Elisabeth Strohmayr,et al.  Chromatic pupillometry dissects function of the three different light-sensitive retinal cell populations in RPE65 deficiency. , 2012, Investigative ophthalmology & visual science.

[22]  David A Mackey,et al.  Current state and future prospects of artificial intelligence in ophthalmology: a review , 2018, Clinical & experimental ophthalmology.

[23]  Yoshua Bengio,et al.  An empirical evaluation of deep architectures on problems with many factors of variation , 2007, ICML '07.

[24]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[25]  Jafar A. Alzubi,et al.  Optimal Classifier Ensemble Design Based on Cooperative Game Theory , 2015 .

[26]  Ernesto Iadanza,et al.  Toward a Novel Medical Device Based on Chromatic Pupillometry for Screening and Monitoring of Inherited Ocular Disease: A Pilot Study , 2018, IFMBE Proceedings.

[27]  Aki Kawasaki,et al.  Chromatic pupil responses: preferential activation of the melanopsin-mediated versus outer photoreceptor-mediated pupil light reflex. , 2009, Ophthalmology.

[28]  Aki Kawasaki,et al.  Pupillometric quantification of residual rod and cone activity in leber congenital amaurosis. , 2012, Archives of ophthalmology.

[29]  Sara Tedmori,et al.  Consensus-based combining method for classifier ensembles , 2018, Int. Arab J. Inf. Technol..

[30]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[31]  R. Kapoor,et al.  The current state of artificial intelligence in ophthalmology. , 2019, Survey of ophthalmology.

[32]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[33]  Ernesto Iadanza,et al.  A collaborative RESTful cloud-based tool for management of chromatic pupillometry in a clinical trial , 2020 .

[34]  David Huang,et al.  Choriocapillaris evaluation in choroideremia using optical coherence tomography angiography. , 2017, Biomedical optics express.

[35]  Kim Fung Tsang,et al.  An Accurate ECG-Based Transportation Safety Drowsiness Detection Scheme , 2016, IEEE Transactions on Industrial Informatics.

[36]  Ernesto Iadanza,et al.  ORÁO: RESTful Cloud-Based Ophthalmologic Medical Record for Chromatic Pupillometry , 2019 .

[37]  Mohamad O Mhajna,et al.  Chromatic Multifocal Pupillometer for Objective Perimetry and Diagnosis of Patients with Retinitis Pigmentosa. , 2016, Ophthalmology.

[38]  Ashish Khanna,et al.  Boosted neural network ensemble classification for lung cancer disease diagnosis , 2019, Appl. Soft Comput..

[39]  Paul Sajda,et al.  Machine learning for detection and diagnosis of disease. , 2006, Annual review of biomedical engineering.

[40]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[41]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[42]  Ernesto Iadanza,et al.  An automatic system supporting clinical decision for chronic obstructive pulmonary disease , 2019, Health and Technology.

[43]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[44]  Jeong-Min Hwang,et al.  Efficacy of digital pupillometry for diagnosis of Horner syndrome , 2017, PloS one.