An Artificial Neural Network Predicts Gender Differences of Motor and Non-Motor Symptoms of Patients with Advanced Parkinson's Disease under Levodopa-Carbidopa Intestinal Gel
- PMID: 38929490
- PMCID: PMC11206121
- DOI: 10.3390/medicina60060873
An Artificial Neural Network Predicts Gender Differences of Motor and Non-Motor Symptoms of Patients with Advanced Parkinson's Disease under Levodopa-Carbidopa Intestinal Gel
Abstract
Background and Objectives: Currently, no tool exists to predict clinical outcomes in patients with advanced Parkinson's disease (PD) under levodopa-carbidopa intestinal gel (LCIG) treatment. The aim of this study was to develop a novel deep neural network model to predict the clinical outcomes of patients with advanced PD after two years of LCIG therapy. Materials and Methods: This was a longitudinal, 24-month observational study of 59 patients with advanced PD in a multicenter registry under LCIG treatment from September 2019 to September 2021, including 43 movement disorder centers. The data set includes 649 measurements of patients, which make an irregular time series, and they are turned into regular time series during the preprocessing phase. Motor status was assessed with the Unified Parkinson's Disease Rating Scale (UPDRS) Parts III (off) and IV. The NMS was assessed by the NMS Questionnaire (NMSQ) and the Geriatric Depression Scale (GDS), the quality of life by PDQ-39, and severity by Hoehn and Yahr (HY). Multivariate linear regression, ARIMA, SARIMA, and Long Short-Term Memory-Recurrent NeuralNetwork (LSTM-RNN) models were used. Results: LCIG significantly improved dyskinesia duration and quality of life, with men experiencing a 19% and women a 10% greater improvement, respectively. Multivariate linear regression models showed that UPDRS-III decreased by 1.5 and 4.39 units per one-unit increase in the PDQ-39 and UPDRS-IV indexes, respectively. Although the ARIMA-(2,0,2) model is the best one with AIC criterion 101.8 and validation criteria MAE = 0.25, RMSE = 0.59, and RS = 0.49, it failed to predict PD patients' features over a long period of time. Among all the time series models, the LSTM-RNN model predicts these clinical characteristics with the highest accuracy (MAE = 0.057, RMSE = 0.079, RS = 0.0053, mean square error = 0.0069). Conclusions: The LSTM-RNN model predicts, with the highest accuracy, gender-dependent clinical outcomes in patients with advanced PD after two years of LCIG therapy.
Keywords: Geriatric Depression Scale; Long Short-Term Memory–Recurrent Neural Network; NMS Questionnaire; Non-Motor Symptoms Questionnaire; Unified Parkinson’s Disease Rating Scale; advanced Parkinson’s disease; levodopa–carbidopaintestinal gel.
Conflict of interest statement
The authors declare no conflicts of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.
Figures
![Figure 1](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11206121/bin/medicina-60-00873-g001.gif)
![Figure 2](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11206121/bin/medicina-60-00873-g002.gif)
![Figure 3](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11206121/bin/medicina-60-00873-g003.gif)
![Figure 4](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11206121/bin/medicina-60-00873-g004.gif)
![Figure 5](https://www.ncbi.nlm.nih.gov/pmc/articles/instance/11206121/bin/medicina-60-00873-g005.gif)
Similar articles
-
Determination of the motor status of patients with advanced Parkinson's disease under levodopa-carbidopa intestinal gel using a machine learning model.Acta Neurol Belg. 2023 Apr;123(2):565-570. doi: 10.1007/s13760-022-02156-z. Epub 2022 Dec 6. Acta Neurol Belg. 2023. PMID: 36472797
-
The Long-Term Impact of Levodopa/Carbidopa Intestinal Gel on 'Off'-time in Patients with Advanced Parkinson's Disease: A Systematic Review.Adv Ther. 2021 Jun;38(6):2854-2890. doi: 10.1007/s12325-021-01747-1. Epub 2021 May 20. Adv Ther. 2021. PMID: 34018146 Free PMC article. Review.
-
Global long-term study on motor and non-motor symptoms and safety of levodopa-carbidopa intestinal gel in routine care of advanced Parkinson's disease patients; 12-month interim outcomes.Parkinsonism Relat Disord. 2015 Mar;21(3):231-5. doi: 10.1016/j.parkreldis.2014.12.012. Epub 2014 Dec 19. Parkinsonism Relat Disord. 2015. PMID: 25585993 Clinical Trial.
-
Levodopa/carbidopa intestinal gel can improve both motor and non-motor experiences of daily living in Parkinson's disease: An open-label study.Parkinsonism Relat Disord. 2017 Apr;37:79-86. doi: 10.1016/j.parkreldis.2017.02.001. Epub 2017 Feb 3. Parkinsonism Relat Disord. 2017. PMID: 28185758
-
Levodopa-Carbidopa Intestinal Gel in Patients with Parkinson's Disease: A Systematic Review.CNS Drugs. 2016 May;30(5):381-404. doi: 10.1007/s40263-016-0336-5. CNS Drugs. 2016. PMID: 27138916 Review.
References
-
- Fasano A., Fung V.S.C., Lopiano L., Elibol B., Smolentseva I.G., Seppi K., Takáts A., Onuk K., Parra J.C., Bergmann L., et al. Characterizing advanced Parkinson’s disease: OBSERVE-PD observational study results of 2615 patients. BMC Neurol. 2019;19:50. doi: 10.1186/s12883-019-1276-8. - DOI - PMC - PubMed
-
- Antonini A., Odin P., Pahwa R., Aldred J., Alobaidi A., Jalundhwala Y.J., Kukreja P., Bergmann L., Inguva S., Bao Y., et al. The Long-Term Impact of Levodopa/Carbidopa Intestinal Gel on O‘ff’-time in Patients with Advanced Parkinson’s Disease: A Systematic Review. Adv. Ther. 2021;38:2854–2890. doi: 10.1007/s12325-021-01747-1. - DOI - PMC - PubMed
-
- Emrani S., McGuirk A., Xiao W. Prognosis and diagnosis of Parkinson’s disease using multi-task learning; Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Halifax, NS, USA. 13–17 August 2017; pp. 1457–1466.
Publication types
MeSH terms
Substances
Grants and funding
LinkOut - more resources
Full Text Sources
Medical