Dynamic Prediction of Excessive Daytime Sleepiness Through Random Survival Forest: An application of the PPMI data

Year 2024, , 35 - 43, 24.03.2024

Gonca Buyrukoglu

https://doi.org/10.17798/bitlisfen.1318703

Cited By: 1

Abstract

Parkinson disease (PD) is the second most widespread neurodegenerative disease worldwide. Excessive daytime sleepiness (EDS) has a significant correlation in de novo PD patients. Identifying predictors is critical in order for early detection of disease diagnosis. We investigated clinical and biological markers related with time-dependent variables in sleepiness for early detection of PD. Data were obtained from the Parkinson’s Progression Markers Initiative study, which evaluates the progression markers in patients. The dataset also includes various longitudinal endogenous predictors. The measures of EDS were obtained through the Epworth Sleepiness Scale (ESS). Random survival forest method which can be deal with multivariate longitudinal endogenous predictors was used to predict the probability of having EDS in PD. The rate of having EDS among PD disease was 0.452. The OOB rate was 0.186. The VIMP and minimal depth indicated that the most important variables are stai state, JLO and the presence of ApoE4 Allele. In early PD, EDS is good indicator of the diagnosis of the PD and it increases over time and has association with several predictors.

Keywords

Variable importance, Individual dynamic prediction, Endogenous variables, Out-of-bag error, Epworth sleepiness scale.

References

• [1] T. Simuni et al., “Longitudinal Change of Clinical and Biological Measures in Early Parkinson’s Disease: Parkinson’s Progression Markers Initiative Cohort,” Movement Disorders, vol. 33, no. 5, 2018, doi: 10.1002/mds.27361.
• [2] L. M. Chahine, A. W. Amara, and A. Videnovic, “A systematic review of the literature on disorders of sleep and wakefulness in Parkinson’s disease from 2005 to 2015,” Sleep Medicine Reviews, vol. 35. 2017. doi: 10.1016/j.smrv.2016.08.001.
• [3] M. D. W. Knipe, M. M. Wickremaratchi, E. Wyatt-Haines, H. R. Morris, and Y. Ben-Shlomo, “Quality of life in young- compared with late-onset Parkinson’s disease,” Movement Disorders, vol. 26, no. 11, 2011, doi: 10.1002/mds.23763.
• [4] T. Simuni et al., “Correlates of excessive daytime sleepiness in de novo Parkinson’s disease: A case control study,” Movement Disorders, vol. 30, no. 10, 2015, doi: 10.1002/mds.26248.
• [5] C. Meindorfner, Y. Körner, J. C. Möller, K. Stiasny-Kolster, W. H. Oertel, and H. P. Krüger, “Driving in Parkinson’s disease: Mobility, accidents, and sudden onset of sleep at the wheel,” Movement Disorders, vol. 20, no. 7, 2005, doi: 10.1002/mds.20412.
• [6] K. Zhu, J. J. van Hilten, and J. Marinus, “Course and risk factors for excessive daytime sleepiness in Parkinson’s disease,” Parkinsonism Relat Disord, vol. 24, 2016, doi: 10.1016/j.parkreldis.2016.01.020.
• [7] D. P. Breen, C. H. Williams-Gray, S. L. Mason, T. Foltynie, and R. A. Barker, “Excessive daytime sleepiness and its risk factors in incident Parkinson’s disease,” Journal of Neurology, Neurosurgery and Psychiatry, vol. 84, no. 2. 2013. doi: 10.1136/jnnp-2012-304097.
• [8] D. Verbaan, S. M. Van Rooden, M. Visser, J. Marinus, and J. J. Van Hilten, “Nighttime sleep problems and daytime sleepiness in Parkinson’s disease,” Movement Disorders, vol. 23, no. 1, 2008, doi: 10.1002/mds.21727.
• [9] M. D. Gjerstad, D. Aarsland, and J. P. Larsen, “Development of daytime somnolence over time in Parkinson’s disease,” Neurology, vol. 58, no. 10, 2002, doi: 10.1212/WNL.58.10.1544.
• [10] K. Marek et al., “The Parkinson Progression Marker Initiative (PPMI),” Progress in Neurobiology, vol. 95, no. 4. 2011. doi: 10.1016/j.pneurobio.2011.09.005.
• [11] D. Kaynak, G. Kiziltan, H. Kaynak, G. Benbir, and O. Uysal, “Sleep and sleepiness in patients with Parkinson’s disease before and after dopaminergic treatment,” Eur J Neurol, vol. 12, no. 3, 2005, doi: 10.1111/j.1468-1331.2004.00971.x.
• [12] G. Fabbrini, P. Barbanti, C. Aurilia, N. Vanacore, C. Pauletti, and G. Meco, “Excessive daytime sleepiness in de novo and treated Parkinson’s disease,” Movement Disorders, vol. 17, no. 5, 2002, doi: 10.1002/mds.10193.
• [13] J. Buskova et al., “Sleep disturbances in untreated Parkinson’s disease,” J Neurol, vol. 258, no. 12, 2011, doi: 10.1007/s00415-011-6109-7.
• [14] R. Erro et al., “Non-motor symptoms in early Parkinson’s disease: A 2-year follow-up study on previously untreated patients,” J Neurol Neurosurg Psychiatry, vol. 84, no. 1, 2013, doi: 10.1136/jnnp-2012-303419.
• [15] C. Pont-Sunyer et al., “The onset of nonmotor symptoms in parkinson’s disease (the onset pd study),” Movement Disorders, vol. 30, no. 2, 2015, doi: 10.1002/mds.26077.
• [16] R. D. Abbott et al., “Excessive daytime sleepiness and subsequent development of Parkinson disease,” Neurology, vol. 65, no. 9, 2005, doi: 10.1212/01.wnl.0000183056.89590.0d.
• [17] L. K. Tholfsen, J. P. Larsen, J. Schulz, O. B. Tysnes, and M. D. Gjerstad, “Development of excessive daytime sleepiness in early Parkinson disease,” Neurology, vol. 85, no. 2, 2015, doi: 10.1212/WNL.0000000000001737.
• [18] A. W. Amara et al., “Longitudinal assessment of excessive daytime sleepiness in early Parkinson’s disease,” J Neurol Neurosurg Psychiatry, vol. 88, no. 8, 2017, doi: 10.1136/jnnp-2016-315023.
• [19] D. Rizopoulos, Joint Models for Longitudinal and Time-to-Event Data. 2012. doi: 10.1201/b12208.
• [20] M. S. Wulfsohn and A. A. Tsiatis, “A Joint Model for Survival and Longitudinal Data Measured with Error,” Biometrics, vol. 53, no. 1, 1997, doi: 10.2307/2533118.
• [21] R. Henderson, “Joint modelling of longitudinal measurements and event time data,” Biostatistics, vol. 1, no. 4, 2000, doi: 10.1093/biostatistics/1.4.465.
• [22] G. Buyrukoglu, P. Philipson, and N. Lin, “Methodological Development and Advances for Joint Modelling of Longitudinal and Time-To-Event Data,” England, 2018. [Online]. Available: https://www.proquest.com/dissertations-theses/methodological-development-advances-joint/docview/2425909057/se-2?accountid=62115
• [23] G. L. Hickey, P. Philipson, A. Jorgensen, and R. Kolamunnage-Dona, “Joint modelling of time-to-event and multivariate longitudinal outcomes: Recent developments and issues,” BMC Med Res Methodol, vol. 16, no. 1, 2016, doi: 10.1186/s12874-016-0212-5.
• [24] D. Rizopoulos, “The R package jmbayes for fitting joint models for longitudinal and time-to-event data using MCMC,” J Stat Softw, vol. 72, 2016, doi: 10.18637/jss.v072.i07.
• [25] G. L. Hickey, P. Philipson, A. Jorgensen, and R. Kolamunnage-Dona, “JoineRML: A joint model and software package for time-to-event and multivariate longitudinal outcomes,” BMC Med Res Methodol, vol. 18, no. 1, 2018, doi: 10.1186/s12874-018-0502-1.
• [26] H. Ishwaran, T. A. Gerds, U. B. Kogalur, R. D. Moore, S. J. Gange, and B. M. Lau, “Random survival forests for competing risks,” Biostatistics, vol. 15, no. 4, 2014, doi: 10.1093/biostatistics/kxu010.
• [27] H. Ishwaran, U. B. Kogalur, E. H. Blackstone, and M. S. Lauer, “Random survival forests,” Ann Appl Stat, vol. 2, no. 3, Sep. 2008, doi: 10.1214/08-AOAS169.
• [28] G. Buyrukoğlu, S. Buyrukoğlu, and Z. Topalcengiz, “Comparing Regression Models with Count Data to Artificial Neural Network and Ensemble Models for Prediction of Generic Escherichia coli Population in Agricultural Ponds Based on Weather Station Measurements,” Microb Risk Anal, vol. 19, 2021, doi: 10.1016/j.mran.2021.100171.
• [29] S. Buyrukoğlu, “Early Detection Of Alzheimer’s Disease Using Data Mining: Comparison Of Ensemble Feature Selection Approaches,” Konya Journal of Engineering Sciences, vol. 9, no. 1, 2021.
• [30] A. Devaux, C. Helmer, R. Genuer, and C. Proust-Lima, “Random survival forests with multivariate longitudinal endogenous covariates,” 2023.
• [31] M. W. Johns, “A new method for measuring daytime sleepiness: The Epworth sleepiness scale,” Sleep, vol. 14, no. 6, 1991, doi: 10.1093/sleep/14.6.540.
• [32] P. Hagell and J. E. Broman, “Measurement properties and hierarchical item structure of the Epworth sleepiness scale in Parkinson’s disease,” J Sleep Res, vol. 16, no. 1, 2007, doi: 10.1111/j.1365-2869.2007.00570.x.
• [33] C. Monaca et al., “Vigilance troubles in Parkinson’s disease: A subjective and objective polysomnographic study,” Sleep Med, vol. 7, no. 5, 2006, doi: 10.1016/j.sleep.2005.12.002.
• [34] R. Poryazova, D. Benninger, D. Waldvogel, and C. L. Bassetti, “Excessive daytime sleepiness in parkinson’s disease: Characteristics and determinants,” European Neurology, vol. 63, no. 3. 2010. doi: 10.1159/000276402.
• [35] B. Högl et al., “Scales to assess sleep impairment in Parkinson’s disease: Critique and recommendations,” Movement Disorders, vol. 25, no. 16. 2010. doi: 10.1002/mds.23190.
• [36] C. G. Goetz et al., “Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results,” Movement Disorders, vol. 23, no. 15, 2008, doi: 10.1002/mds.22340.
• [37] Z. S. Nasreddine et al., “The Montreal Cognitive Assessment, MoCA: A brief screening tool for mild cognitive impairment,” J Am Geriatr Soc, vol. 53, no. 4, 2005, doi: 10.1111/j.1532-5415.2005.53221.x.
• [38] R. H. B. Benedict, D. Schretlen, L. Groninger, and J. Brandt, “Hopkins verbal learning test - Revised: Normative data and analysis of inter-form and test-retest reliability,” Clinical Neuropsychologist, vol. 12, no. 1, 1998, doi: 10.1076/clin.12.1.43.1726.
• [39] C. E. Qualls, N. G. Bliwise, and A. Y. Stringer, “Short forms of the Benton Judgment of Line Orientation Test: Development and psychometric properties,” Archives of Clinical Neuropsychology, vol. 15, no. 2, 2000, doi: 10.1016/S0887-6177(98)00043-2.
• [40] R. H. B. Benedict, J. Deluca, G. Phillips, N. LaRocca, L. D. Hudson, and R. Rudick, “Validity of the Symbol Digit Modalities Test as a cognition performance outcome measure for multiple sclerosis,” Multiple Sclerosis, vol. 23, no. 5. 2017. doi: 10.1177/1352458517690821.
• [41] T. Joseph et al., “Screening performance of abbreviated versions of the UPSIT smell test,” J Neurol, vol. 266, no. 8, 2019, doi: 10.1007/s00415-019-09340-x.
• [42] K. Stiasny-Kolster, G. Mayer, S. Schäfer, J. C. Möller, M. Heinzel-Gutenbrunner, and W. H. Oertel, “The REM sleep behavior disorder screening questionnaire - A new diagnostic instrument,” Movement Disorders, vol. 22, no. 16, 2007, doi: 10.1002/mds.21740.
• [43] P. C. Kendall and et al, “The State-Trait Anxiety Inventory: A systematic evaluation,” J Consult Clin Psychol, vol. 44, no. 3, 1976, doi: 10.1037/0022-006X.44.3.406.
• [44] N. M. Laird and J. H. Ware, “Random-Effects Models for Longitudinal Data,” Biometrics, vol. 38, no. 4, 1982, doi: 10.2307/2529876.
• [45] T. A. Gerds and M. Schumacher, “Consistent estimation of the expected brier score in general survival models with right-censored event times,” Biometrical Journal, vol. 48, no. 6, 2006, doi: 10.1002/bimj.200610301.
• [46] A. Devaux, C. Proust-Lima, and R. Genuer, “Random Forests for time-fixed and time-dependent predictors: The DynForest R package,” Feb. 2023.
• [47] F. Feng, Y. Y. Cai, Y. B. Hou, R. Ou, Z. Jiang, and H. F. Shang, “Excessive daytime sleepiness in Parkinson’s disease: A systematic review and meta-analysis,” Parkinsonism and Related Disorders, vol. 85. 2021. doi: 10.1016/j.parkreldis.2021.02.016.
• [48] A. Höglund, P. Hagell, J. E. Broman, S. Pålhagen, K. Sorjonen, and S. Fredrikson, “A 10-Year Follow-Up of Excessive Daytime Sleepiness in Parkinson’s Disease,” Parkinsons Dis, vol. 2019, 2019, doi: 10.1155/2019/5708515.
• [49] Y. Liu et al., “Longitudinal Changes in Parkinson’s Disease Symptoms with and Without Rapid Eye Movement Sleep Behavior Disorder: The Oxford Discovery Cohort Study,” Movement Disorders, vol. 36, no. 12, 2021, doi: 10.1002/mds.28763.
• [50] R. Del Pino et al., “Clinical long-term nocturnal sleeping disturbances and excessive daytime sleepiness in Parkinson’s disease,” PLoS One, vol. 16, no. 12 December, 2021, doi: 10.1371/journal.pone.0259935.