Michele Matarazzo1,2,3,4, Teresa Arroyo-Gallego5,6,7, Paloma Montero2,8, Verónica Puertas-Martín2, Ian Butterworth9, Carlos S Mendoza9, María J Ledesma-Carbayo5, María José Catalán8, José Antonio Molina2, Félix Bermejo-Pareja2, Juan Carlos Martínez-Castrillo10, Lydia López-Manzanares11, Araceli Alonso-Cánovas10, Jaime Herreros Rodríguez12, Ignacio Obeso1,3, Pablo Martínez-Martín3,13, José Carlos Martínez-Ávila14, Agustín Gómez de la Cámara14, Martha Gray6,9, José A Obeso1,3, Luca Giancardo6,15, Álvaro Sánchez-Ferro1,2,3,6. 1. HM-CINAC, Hospital Universitario HM Puerta del Sur, Móstoles and Medical School, CEU-San Pablo University, Madrid, Spain. 2. Neurology Department, Instituto de Investigación del Hospital 12 de Octubre, Madrid, Spain. 3. Centro de Investigación Biomédica en Red, Enfermedades Neurodegenerativas, Madrid, Spain. 4. Pacific Parkinson's Research Centre, University of British Columbia, Vancouver, British Columbia, Canada. 5. Biomedical Image Technologies, Universidad Politécnica de Madrid and CIBERBBN, Madrid, Spain. 6. Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA. 7. nQ Medical Inc., Cambridge, Massachusetts, USA. 8. Movement Disorders Unit, Hospital Clínico San Carlos, Madrid, Spain. 9. Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA. 10. Movement Disorders Unit, Hospital Ramón y Cajal, Madrid, Spain. 11. Movement Disorders Unit, Hospital de la Princesa, Madrid, Spain. 12. Neurology Department, Hospital Infanta Leonor, Madrid, Spain. 13. Area of Applied Epidemiology, National Centre of Epidemiology, Carlos III Institute of Health, Madrid, Spain. 14. Clinical Research Unit, Instituto de Investigación Hospital 12 de Octubre, Consorcio de Investigación Biomédica en Red de Epidemiología y Salud Pública, Hospital Universitario 12 de Octubre, Madrid, Spain. 15. Center for Precision Health, School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, USA.
Abstract
OBJECTIVE: The recent advances in technology are opening a new opportunity to remotely evaluate motor features in people with Parkinson's disease (PD). We hypothesized that typing on an electronic device, a habitual behavior facilitated by the nigrostriatal dopaminergic pathway, could allow for objectively and nonobtrusively monitoring parkinsonian features and response to medication in an at-home setting. METHODS: We enrolled 31 participants recently diagnosed with PD who were due to start dopaminergic treatment and 30 age-matched controls. We remotely monitored their typing pattern during a 6-month (24 weeks) follow-up period before and while dopaminergic medications were being titrated. The typing data were used to develop a novel algorithm based on recursive neural networks and detect participants' responses to medication. The latter were defined by the Unified Parkinson's Disease Rating Scale-III (UPDRS-III) minimal clinically important difference. Furthermore, we tested the accuracy of the algorithm to predict the final response to medication as early as 21 weeks prior to the final 6-month clinical outcome. RESULTS: The score on the novel algorithm based on recursive neural networks had an overall moderate kappa agreement and fair area under the receiver operating characteristic (ROC) curve with the time-coincident UPDRS-III minimal clinically important difference. The participants classified as responders at the final visit (based on the UPDRS-III minimal clinically important difference) had higher scores on the novel algorithm based on recursive neural networks when compared with the participants with stable UPDRS-III, from the third week of the study onward. CONCLUSIONS: This preliminary study suggests that remotely gathered unsupervised typing data allows for the accurate detection and prediction of drug response in PD.
OBJECTIVE: The recent advances in technology are opening a new opportunity to remotely evaluate motor features in people with Parkinson's disease (PD). We hypothesized that typing on an electronic device, a habitual behavior facilitated by the nigrostriatal dopaminergic pathway, could allow for objectively and nonobtrusively monitoring parkinsonian features and response to medication in an at-home setting. METHODS: We enrolled 31 participants recently diagnosed with PD who were due to start dopaminergic treatment and 30 age-matched controls. We remotely monitored their typing pattern during a 6-month (24 weeks) follow-up period before and while dopaminergic medications were being titrated. The typing data were used to develop a novel algorithm based on recursive neural networks and detect participants' responses to medication. The latter were defined by the Unified Parkinson's Disease Rating Scale-III (UPDRS-III) minimal clinically important difference. Furthermore, we tested the accuracy of the algorithm to predict the final response to medication as early as 21 weeks prior to the final 6-month clinical outcome. RESULTS: The score on the novel algorithm based on recursive neural networks had an overall moderate kappa agreement and fair area under the receiver operating characteristic (ROC) curve with the time-coincident UPDRS-III minimal clinically important difference. The participants classified as responders at the final visit (based on the UPDRS-III minimal clinically important difference) had higher scores on the novel algorithm based on recursive neural networks when compared with the participants with stable UPDRS-III, from the third week of the study onward. CONCLUSIONS: This preliminary study suggests that remotely gathered unsupervised typing data allows for the accurate detection and prediction of drug response in PD.
Authors: Kevin B Wilkins; Matthew N Petrucci; Yasmine Kehnemouyi; Anca Velisar; Katie Han; Gerrit Orthlieb; Megan H Trager; Johanna J O'Day; Sudeep Aditham; Helen Bronte-Stewart Journal: J Parkinsons Dis Date: 2022 Impact factor: 5.520
Authors: Krzysztof Z Gajos; Katharina Reinecke; Mary Donovan; Christopher D Stephen; Albert Y Hung; Jeremy D Schmahmann; Anoopum S Gupta Journal: Mov Disord Date: 2019-11-07 Impact factor: 10.338