Reuben R Shamir1, Trygve Dolber1, Angela M Noecker1, Benjamin L Walter2, Cameron C McIntyre3. 1. Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA. 2. Department of Neurology, Case Western Reserve University, Cleveland, OH, USA; Neurological Institute, University Hospitals Case Medical Center, Cleveland, OH, USA. 3. Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA; Department of Neurology, Case Western Reserve University, Cleveland, OH, USA. Electronic address: ccm4@case.edu.
Abstract
BACKGROUND: Deep brain stimulation (DBS) of the subthalamic region is an established therapy for advanced Parkinson's disease (PD). However, patients often require time-intensive post-operative management to balance their coupled stimulation and medication treatments. Given the large and complex parameter space associated with this task, we propose that clinical decision support systems (CDSS) based on machine learning algorithms could assist in treatment optimization. OBJECTIVE: Develop a proof-of-concept implementation of a CDSS that incorporates patient-specific details on both stimulation and medication. METHODS: Clinical data from 10 patients, and 89 post-DBS surgery visits, were used to create a prototype CDSS. The system was designed to provide three key functions: (1) information retrieval; (2) visualization of treatment, and; (3) recommendation on expected effective stimulation and drug dosages, based on three machine learning methods that included support vector machines, Naïve Bayes, and random forest. RESULTS: Measures of medication dosages, time factors, and symptom-specific pre-operative response to levodopa were significantly correlated with post-operative outcomes (P < 0.05) and their effect on outcomes was of similar magnitude to that of DBS. Using those results, the combined machine learning algorithms were able to accurately predict 86% (12/14) of the motor improvement scores at one year after surgery. CONCLUSIONS: Using patient-specific details, an appropriately parameterized CDSS could help select theoretically optimal DBS parameter settings and medication dosages that have potential to improve the clinical management of PD patients.
BACKGROUND: Deep brain stimulation (DBS) of the subthalamic region is an established therapy for advanced Parkinson's disease (PD). However, patients often require time-intensive post-operative management to balance their coupled stimulation and medication treatments. Given the large and complex parameter space associated with this task, we propose that clinical decision support systems (CDSS) based on machine learning algorithms could assist in treatment optimization. OBJECTIVE: Develop a proof-of-concept implementation of a CDSS that incorporates patient-specific details on both stimulation and medication. METHODS: Clinical data from 10 patients, and 89 post-DBS surgery visits, were used to create a prototype CDSS. The system was designed to provide three key functions: (1) information retrieval; (2) visualization of treatment, and; (3) recommendation on expected effective stimulation and drug dosages, based on three machine learning methods that included support vector machines, Naïve Bayes, and random forest. RESULTS: Measures of medication dosages, time factors, and symptom-specific pre-operative response to levodopa were significantly correlated with post-operative outcomes (P < 0.05) and their effect on outcomes was of similar magnitude to that of DBS. Using those results, the combined machine learning algorithms were able to accurately predict 86% (12/14) of the motor improvement scores at one year after surgery. CONCLUSIONS: Using patient-specific details, an appropriately parameterized CDSS could help select theoretically optimal DBS parameter settings and medication dosages that have potential to improve the clinical management of PDpatients.
Authors: Ashutosh Chaturvedi; Christopher R Butson; Scott F Lempka; Scott E Cooper; Cameron C McIntyre Journal: Brain Stimul Date: 2010-04 Impact factor: 8.955
Authors: W M M Schuepbach; J Rau; K Knudsen; J Volkmann; P Krack; L Timmermann; T D Hälbig; H Hesekamp; S M Navarro; N Meier; D Falk; M Mehdorn; S Paschen; M Maarouf; M T Barbe; G R Fink; A Kupsch; D Gruber; G-H Schneider; E Seigneuret; A Kistner; P Chaynes; F Ory-Magne; C Brefel Courbon; J Vesper; A Schnitzler; L Wojtecki; J-L Houeto; B Bataille; D Maltête; P Damier; S Raoul; F Sixel-Doering; D Hellwig; A Gharabaghi; R Krüger; M O Pinsker; F Amtage; J-M Régis; T Witjas; S Thobois; P Mertens; M Kloss; A Hartmann; W H Oertel; B Post; H Speelman; Y Agid; C Schade-Brittinger; G Deuschl Journal: N Engl J Med Date: 2013-02-14 Impact factor: 91.245
Authors: Svjetlana Miocinovic; Scott F Lempka; Gary S Russo; Christopher B Maks; Christopher R Butson; Ken E Sakaie; Jerrold L Vitek; Cameron C McIntyre Journal: Exp Neurol Date: 2008-12-11 Impact factor: 5.330
Authors: Jean-François Daneault; Benoit Carignan; Carl Éric Codère; Abbas F Sadikot; Christian Duval Journal: Front Hum Neurosci Date: 2013-01-18 Impact factor: 3.169
Authors: Jorge Leite; Leon Morales-Quezada; Sandra Carvalho; Aurore Thibaut; Deniz Doruk; Chiun-Fan Chen; Steven C Schachter; Alexander Rotenberg; Felipe Fregni Journal: Int J Neural Syst Date: 2017-04-11 Impact factor: 5.866
Authors: Lucas L Dwiel; Jibran Y Khokhar; Michael A Connerney; Alan I Green; Wilder T Doucette Journal: PLoS Comput Biol Date: 2019-04-22 Impact factor: 4.475
Authors: Lieneke van den Heuvel; Ray R Dorsey; Barbara Prainsack; Bart Post; Anne M Stiggelbout; Marjan J Meinders; Bastiaan R Bloem Journal: J Parkinsons Dis Date: 2020 Impact factor: 5.568
Authors: Dustin A Heldman; Christopher L Pulliam; Enrique Urrea Mendoza; Maureen Gartner; Joseph P Giuffrida; Erwin B Montgomery; Alberto J Espay; Fredy J Revilla Journal: Neuromodulation Date: 2015-12-01
Authors: Lacramioara Perju-Dumbrava; Maria Barsan; Daniel Corneliu Leucuta; Luminita C Popa; Cristina Pop; Nicoleta Tohanean; Stefan L Popa Journal: Exp Ther Med Date: 2021-12-17 Impact factor: 2.447