Optimizing Patient-Specific Medication Regimen Policies Using Wearable Sensors in Parkinson’s Disease

References

• Aich S, Youn J, Chakraborty S, Pradhan P, Park J, Park S, Park J (2020) A supervised machine learning approach to detect the on/off state in Parkinson’s disease using wearable based gait signals. Diagnostics (Basel) 10(6):421.Crossref, Google Scholar
• Al-Khafajiy M, Baker T, Chalmers C, Asim M, Kolivand H, Fahim M, Waraich A (2019) Remote health monitoring of elderly through wearable sensors. Multimedia Tools Appl. 78(17):24681–24706.Crossref, Google Scholar
• Antonini A, Odin P (2009) Pros and cons of apomorphine and L-dopa continuous infusion in advanced Parkinson’s disease. Parkinsonism Related Disorders 15(S4):S97–S100.Crossref, Google Scholar
• Barbato G, Barini E, Genta G, Levi R (2011) Features and performance of some outlier detection methods. J. Appl. Statist. 38(10):2133–2149.Crossref, Google Scholar
• Baucum M, Khojandi A, Vasudevan R (2021) Improving deep reinforcement learning with transitional variational autoencoders: A healthcare application. IEEE J. Biomedical Health Informatics 25(6):2273–2280.Crossref, Google Scholar
• Belić M, Bobić V, Badža M, Šolaja N, Đurić-Jovičić M, Kostić V (2019) Artificial intelligence for assisting diagnostics and assessment of Parkinson’s disease—a review. Clinical Neurology Neurosurgery 184:105442.Crossref, Google Scholar
• Brooks D (2008) Optimizing levodopa therapy for Parkinson’s disease with levodopa/carbidopa/entacapone: Implications from a clinical and patient perspective. Neuropsychiatric Disease Treatment 4(1):39–47.Crossref, Google Scholar
• Coleman C, Limone B, Sobieraj D, Lee S, Roberts M, Kaur R, Alam T (2012) Dosing frequency and medication adherence in chronic disease. J. Managed Care Pharmacy 18(7):527–539.Crossref, Google Scholar
• Daneault J, Carignan B, Sadikot A, Panisset M, Duval C (2013) Drug-induced dyskinesia in Parkinson’s disease. Should success in clinical management be a function of improvement of motor repertoire rather than amplitude of dyskinesia? BMC Medicine 11(1):76.Crossref, Google Scholar
• Daskalaki E, Diem P, Mougiakakou S (2013) Personalized tuning of a reinforcement learning control algorithm for glucose regulation. 2013 35th Annual Internat. Conf. IEEE Engrg. Medicine Biology Soc. (EMBC) (IEEE, Piscataway, NJ), 3487–3490.Google Scholar
• Favela J, Cruz-Sandoval D, Morales-Tellez A, Lopez-Nava I (2020) Monitoring behavioral symptoms of dementia using activity trackers. J. Biomedical Informatics 109:103520.Crossref, Google Scholar
• Fox I, Lee J, Pop-Busui R, Wiens J (2020) Deep reinforcement learning for closed-loop blood glucose control. Machine Learn. Healthcare Conf. (PMLR), 508–536.Google Scholar
• Gao C, Sun H, Wang T, Tang M, Bohnen NI, Müller MLTM, Herman T, et al. (2018) Model-based and model-free machine learning techniques for diagnostic prediction and classification of clinical outcomes in Parkinson’s disease. Sci. Rep. 8(1):7129.Crossref, Google Scholar
• Gottesman O, Johansson F, Komorowski M, Faisal A, Sontag D, Doshi-Velez F, Celi LA (2019) Guidelines for reinforcement learning in healthcare. Nature Medicine 25(1):16–18.Crossref, Google Scholar
• Griffiths R, Kotschet K, Arfon S, Xu Z, Johnson W, Drago J, Evans A, Kempste P, Raghav S, Horne M (2012) Automated assessment of bradykinesia and dyskinesia in Parkinson’s disease. J. Parkinson’s Disease 2(1):47–55.Crossref, Google Scholar
• Hauser RA, Hsu A, Kell S, Espay AJ, Sethi K, Stacy M, Ondo W, O’Connell M, Gupta S; IPX066 ADVANCE-PD investigators (2013) Extended-release carbidopa-levodopa (IPX066) compared with immediate-release carbidopa-levodopa in patients with Parkinson’s disease and motor fluctuations: A phase 3 randomised, double-blind trial. Lancet Neurology 12(4):346–356.Crossref, Google Scholar
• Horne M, Kotschet K, McGregor S (2016) The clinical validation of objective measurement of movement in Parkinson’s disease. CNS 2(1):15–22.Google Scholar
• Hsu A, Yao H, Gupta S, Modi N (2015) Comparison of the pharmacokinetics of an oral extended-release capsule formulation of carbidopa-levodopa (IPX066) with immediate-release carbidopa-levodopa (Sinemet), sustained-release carbidopa-levodopa (Sinemet CR), and carbidopa-levodopa-entacapone (Stalevo). J. Clinical Pharmacology 55(9):995–1003.Crossref, Google Scholar
• Kang S, Kang J, Ko K, Park S, Mariani S, Weng J (2017) Validity of a commercial wearable sleep tracker in adult insomnia disorder patients and good sleepers. J. Psychosomatic Res. 97:38–44.Crossref, Google Scholar
• Khojandi A, Shylo O, Mannini L, Kopell B, Ramdhani R (2017) Stratifying Parkinson’s patients with STN-DBS into high-frequency or 60 Hz-frequency modulation using a computational model. Neuromodulation 20(5):450–455.Crossref, Google Scholar
• Kim Y, Suescun J, Schiess M, Jiang X (2021) Computational medication regimen for Parkinson’s disease using reinforcement learning. Sci. Rep. 11(1):9313.Crossref, Google Scholar
• Kuoppamäki M, Korpela K, Marttila R, Kaasinen V, Hartikainen P, Lyytinen J, Kaakkola S, Hänninen J, Löyttyniemi E, Kailajärvi M (2009) Comparison of pharmacokinetic profile of levodopa throughout the day between levodopa/carbidopa/entacapone and levodopa/carbidopa when administered four or five times daily. Eur. J. Clinical Pharmacology 65(5):443–455.Crossref, Google Scholar
• Lee S, Daneault J, Golabchi F, Patel S, Paganoni S, Shih L, Bonato P (2015) A novel method for assessing the severity of levodopa-induced dyskinesia using wearable sensors. 2015 37th Annual Internat. Conf. IEEE Engrg. Medicine Biology Soc. (EMBC) (IEEE, Piscataway, NJ), 8087–8090.Google Scholar
• Marek K, Chowdhury S, Siderowf A, Lasch S, Coffey C, Caspell-Garcia C, Simuni T, et al. (2018) The Parkinson’s progression markers initiative (PPMI)—Establishing a PD biomarker cohort. Ann. Clinical Translational Neurology 5(12):1460–1477.Crossref, Google Scholar
• Mittur A, Gupta S, Modi N (2017) Pharmacokinetics of Rytary, an extended-release capsule formulation of carbidopa–levodopa. Clinical Pharmacokinetics 56(9):999–1014.Crossref, Google Scholar
• Morgante L, Morgante F, Moro E, Epifanio A, Girlanda P, Ragonese P, Antonini A, Barone P, Bonuccelli U, Contarino M (2007) How many Parkinsonian patients are suitable candidates for deep brain stimulation of subthalamic nucleus? Results of a questionnaire. Parkinsonism Related Disorders 13(8):528–531.Crossref, Google Scholar
• Nahab F, Abu-Hussain H, Moreno L (2019) Evaluation of clinical utility of the Personal Kinetigraph in the management. Adv. Parkinson’s Disease 8(3):42–61.Crossref, Google Scholar
• Nahum-Shani I, Smith S, Spring B, Bonnie J, Collins L, Witkiewitz K, Tewari A, Murphy S (2018) Just-in-time adaptive interventions (JITAIs) in mobile health: Key components and design principles for ongoing health behavior support. Ann. Behav. Medicine 52(6):446–462.Crossref, Google Scholar
• Ossig C, Gandor F, Bosredon C, Fauser M, Reichmann H, Horne M (2015) Correlation of objective measurement of motor states using a kinetograph and patient diaries in advanced Parkinson’s disease. PLoS One 11(8):e0161559.Google Scholar
• Pahwa R, Isaacson S, Torres-Russotto D, Nahab F, Lynch P, Kotschet K (2018) Role of the Personal Kinetigraph in the routine clinical assessment of Parkinson’s disease: Recommendations from an expert panel. Expert Rev. Neurotherapeutics 18(8):669–680.Crossref, Google Scholar
• Pahwa R, Lyons KE, Hauser RA, Fahn S, Jankovic J, Pourcher E, Hsu A, et al. (2014) Randomized trial of ipx066, carbidopa/levodopa extended release, in early Parkinson’s disease. Parkinsonism Related Disorders 20(2):142–148.Crossref, Google Scholar
• Parkinson’s Disease Foundation (2019) Statistics on Parkinson’s. Accessed July 10, 2019, https://www.Parkinson.org/Understanding-Parkinsons/Statistics.Google Scholar
• Paula MD, Acosta G, Martínez E (2015) On-line policy learning and adaptation for real-time personalization of an artificial pancreas. Expert Systems Appl. 42(4):2234–2255.Crossref, Google Scholar
• Pedrosa T, Vasconcelos F, Medeiros L, Silva L (2018) Machine learning application to quantify the tremor level for Parkinson’s disease patients. Procedia Comput. Sci. 138:215–220.Crossref, Google Scholar
• Pineau J, Guez A, Vincent R, Panuccio G, Avoli M (2009) Treating epilepsy via adaptive neurostimulation: A reinforcement learning approach. Internat. J. Neural Systems 19(4):227–240.Crossref, Google Scholar
• Prasad N, Cheng L, Chivers C, Draugelis M, Engelhardt BE (2017) A reinforcement learning approach to weaning of mechanical ventilation in intensive care units. Preprint, submitted April 20, https://arxiv.org/abs/1704.06300.Google Scholar
• Raghu A, Komorowski M, Celi L, Szolovits P, Ghassemi M (2017) Continuous state-space models for optimal sepsis treatment—a deep reinforcement learning approach. Preprint, submitted May 23, https://arxiv.org/abs/1705.08422.Google Scholar
• Ramdhani R, Khojandi A, Shylo O, Kopell B (2018) Optimizing clinical assessments in Parkinson’s disease through the use of wearable sensors and data driven modeling. Frontiers Comput. Neuroscience 12:72.Crossref, Google Scholar
• Rodriguez M, Lera G, Vaamonde J, Luquin M, Obeso J (1994) Motor response to apomorphine and levodopa in asymmetric Parkinson’s disease. J. Neurology Neurosurgery Psychiatry 57(5):562–566.Crossref, Google Scholar
• Rolf E, Worledge TT, Recht B, Jordan M (2021) Representation matters: Assessing the importance of subgroup allocations in training data. Meila M, Zhang T, eds. Internat. Conf. Machine Learn. (PMLR, Virtual), 9040–9051.Google Scholar
• Schade S, Mollenhauer B, Trenkwalder C (2020) Levodopa equivalent dose conversion factors: An updated proposal including opicapone and safinamide. Movement Disorders Clinical Practice 7(3):343–345.Crossref, Google Scholar
• Schneider R, Biglan K (2017) The promise of telemedicine for chronic neurological disorders: The example of Parkinson’s disease. Lancet Neurology 16(7):541–551.Crossref, Google Scholar
• Schrag A, Sampaio C, Counsell N, Poewe W (2006) Minimal clinically important change on the Unified Parkinson’s Disease Rating Scale. Movement Disorders 21(8):1200–1207.Crossref, Google Scholar
• Stocchi F, Quinn N, Barbato L, Patsalos P, O’Connel M, Ruggieri S, Marsden C (1994) Comparison between a fast and a slow release preparation of levodopa and a combination of the two: A clinical and pharmacokinetic study. Clinical Neuropharmacology 17(1):38–44.Crossref, Google Scholar
• Tejedor M, Woldaregay A, Godtliebsen F (2020) Reinforcement learning application in diabetes blood glucose control: A systematic review. Artificial Intelligence Medicine 104:101836.Crossref, Google Scholar
• Tomkins S, Liao P, Klasnja P, Yeung S, Murphy S (2020) Rapidly personalizing mobile health treatment policies with limited data. Preprint, submitted February 23, https://arxiv.org/abs/2002.09971.Google Scholar
• Tomlinson C, Stowe R, Patel S, Rick C, Gray R, Clarke C (2010) Systematic review of levodopa dose equivalency reporting in Parkinson’s disease. Movement Disorders 25(15):2649–2653.Crossref, Google Scholar
• Wan K, Maszczyk T, See A, Dauwels J, King N (2019) A review on microelectrode recording selection of features for machine learning in deep brain stimulation surgery for Parkinson’s disease. Clinical Neurophysiology 130(1):145–154.Crossref, Google Scholar
• Watts J, Khojandi A, Shylo O, Ramdhani R (2020a) Machine learning’s application in deep brain stimulation for Parkinson’s disease: A review. Brain Sci. 10(11):809.Crossref, Google Scholar
• Watts J, Khojandi A, Vasudevan R, Nahab F, Ramdhani R (2021) Predicting Parkinson’s disease medication regimen using sensor technology. Preprint, submitted February 18, https://doi.org/10.21203/rs.3.rs-198765/v1.Google Scholar
• Watts J, Khojandi A, Vasudevan R, Ramdhani R (2020b) Optimizing individualized treatment planning for Parkinson’s disease using deep reinforcement learning. 2020 42nd Annual Internat. Conf. IEEE Engrg. Medicine Biology Soc. (EMBC) (IEEE, Piscataway, NJ), 5406–5409.Google Scholar
• Wei WWS (2006) Time Series Analysis: Univariate and Multivariate Methods, 2nd ed. (Pearson College Division, New York).Google Scholar
• Willis A, Schootman M, Evanoff B, Perlmutter J, Racette B (2011) Neurologist care in Parkinson disease: A utilization, outcomes, and survival study. Neurology 77(9):851–857.Crossref, Google Scholar
• Yang T, Tang H, Bai C, Liu J, Hao J, Meng Z, Liu P (2021) Exploration in deep reinforcement learning: A comprehensive survey. Preprint, submitted September 15, https://arxiv.org/abs/2109.06668v2.Google Scholar
• Zhu F, Guo J, Xu Z, Liao P, Yang L, Huang J (2018) Group-driven reinforcement learning for personalized mHealth intervention. Frangi A, Schnabel J, Davatzikos C, Alberola-López C, Fichtinger G, eds. Internat. Conf. Medical Image Comput. Comput.-Assisted Intervention (Springer, Singapore), 590–598.Google Scholar