Parkinson’s disease state recognition based on local field potentials: An ensemble model with feature division_Journal of Biomedical Engineering

Authors：

 ZHAO Dechun , YANG Tingting , SHEN Yuchen , CHEN Yi , ZHANG Yuan , LYU You , CHEN Siyu

School of Life Health Information Science and Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China;

Corresponding?author：

ZHAO Dechun, Email: zhaodc@cqupt.edu.cn

Keywords：

Local field potentials; Parkinson’s disease; Deep brain stimulation; Feature selection; Ensemble model

DOI：

10.7507/1001-5515.202601005

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Patients with Parkinson’s disease exhibit differential local field potential (LFP) activities under different deep brain stimulation (DBS) conditions. To achieve a balance between the discriminative performance and computational complexity for the identification of DBS stimulation-related neural states, this paper proposes a feature-division ensemble learning framework. First, multi-objective feature selection was conducted based on stability, discriminability and parsimony to derive a compact feature subset from time-domain, frequency-domain and nonlinear features. Then, the three categories of features were assigned to their respective advantageous base classifiers and fused via hard voting. Window-level 10-fold cross-validation results on the public STN-LFP dataset from the University of Oxford demonstrated that the proposed model reached an accuracy of 97.18%, outperforming the support vector machine (88.85%) and eXtreme Gradient Boosting (92.84%). SHAP analysis revealed that β-related frequency-domain features and partial nonlinear features had relatively high contribution. The feature division strategy reduced the cumulative input dimension of the three base classifiers from 96 to 32 and eliminated redundant feature processing. This method can provide a reference for analyzing DBS stimulation-related LFP patterns and further research on closed-loop feedback biomarkers.

Citation： ZHAO Dechun, YANG Tingting, SHEN Yuchen, CHEN Yi, ZHANG Yuan, LYU You, CHEN Siyu. Parkinson’s disease state recognition based on local field potentials: An ensemble model with feature division. Journal of Biomedical Engineering, 2026, 43(5): 947-953. doi: 10.7507/1001-5515.202601005 Copy

1.	Luo Y, Qiao L, Li M, et al. Global, regional, national epidemiology and trends of Parkinson’s disease from 1990 to 2021: findings from the Global Burden of Disease Study 2021[J]. Front Neurosci, 2025, 16: 1498756.
2.	Poewe W, Seppi K, Tanner C M, et al. Parkinson disease[J]. Nat Rev Dis Primers, 2017, 3: 17013.
3.	Hartmann C J, Fliegen S, Groiss S J, et al. An update on best practice of deep brain stimulation in Parkinson’s disease[J]. Ther Adv Neurol Disord, 2019, 12: 1756286419838096.
4.	Bronstein J M, Tagliati M, Alterman R L, et al. Deep brain stimulation for Parkinson disease: an expert consensus and review of key issues[J]. Arch Neurol, 2011, 68(2): 165-171.
5.	Oliveira A M, Coelho M, Carvalho A, et al. Machine-learning for adaptive deep brain stimulation in Parkinson’s disease: closing the loop[J]. J Neurol, 2023, 270(11): 5313-5326.
6.	Whitmer D, de Solages C, Hill B, et al. High frequency deep brain stimulation attenuates subthalamic and cortical rhythms in Parkinson’s disease[J]. Front Hum Neurosci, 2012, 6: 155.
7.	Neumann W J, Degen K, Schneider G H, et al. Subthalamic synchronized oscillatory activity correlates with motor impairment in patients with Parkinson’s disease[J]. Mov Disord, 2016, 31(11): 1748-1751.
8.	Little S, Pogosyan A, Neal S, et al. Adaptive deep brain stimulation in advanced Parkinson disease[J]. Ann Neurol, 2013, 74(3): 449-457.
9.	Jiang H, Zhang J J, Hebb A O, et al. Time-frequency analysis of brain electrical signals for behavior recognition in patients with Parkinson’s disease[C]//2013 47th Asilomar Conference on Signals, Systems and Computers. Pacific Grove: IEEE, 2013: 1843-1847.
10.	Niketeghad S, Hebb A O, Nedrud J, et al. Single trial behavioral task classification using subthalamic nucleus local field potential signals[C]//2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Chicago: IEEE, 2014: 3793-3796.
11.	Golshan H M, Hebb A O, Hanrahan S J, et al. A multiple kernel learning approach for human behavioral task classification using STN-LFP signal[C]//2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Orlando: IEEE, 2016: 1030-1033.
12.	Shah S A, Tinkhauser G, Chen C C, et al. Parkinsonian tremor detection from subthalamic nucleus local field potentials for closed-loop deep brain stimulation[C]//2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Honolulu: IEEE, 2018: 2320-2324.
13.	Wang T, Shoaran M, Emami A, et al. Closed-loop adaptive deep brain stimulation in Parkinson’s disease: LFP-based feature analysis and classification[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary: IEEE, 2018: 2536-2540.
14.	Hirschmann J, Steina A, Vesper J, et al. Neuronal oscillations predict deep brain stimulation outcome in Parkinson’s disease[J]. Brain Stimul, 2022, 15(3): 792-802.
15.	Houston B, Thompson M, Ko A, et al. A machine-learning approach to volitional control of a closed-loop deep brain stimulation system[J]. J Neural Eng, 2019, 16(1): 016004.
16.	Reck C, Florin E, Wojtecki L, et al. Characterisation of tremor-associated local field potentials in the subthalamic nucleus in Parkinson’s disease[J]. Eur J Neurosci, 2009, 29(3): 599-612.
17.	Wüst C, Torrecillos F, Pogosyan A, et al. STN local field potential recordings from awake patients with Parkinson’s disease on and off medication during 130 Hz DBS[J]. Data Brief, 2022, 44: 108562.
18.	Zhao D, Liu Z, Yao M, et al. State-identification of Parkinson’s disease based on transfer learning[J]. Technol Health Care, 2024, 32(6): 4097-4107.
19.	Dastin-van Rijn E M, Provenza N R, Calvert J S, et al. Uncovering biomarkers during therapeutic neuromodulation with PARRM: period-based artifact reconstruction and removal method[J]. Cell Rep Methods, 2021, 1(2): 100010.
20.	Lee S B, Kim Y J, Hwang S, et al. Predicting Parkinson’s disease progression using gradient boosting decision tree models with electroencephalography signals[J]. Parkinsonism Relat Disord, 2022, 95: 77-85.
21.	Snoek J, Larochelle H, Adams R P. Practical Bayesian optimization of machine learning algorithms[J]. Adv Neural Inf Process Syst, 2012, 25: 2951-2959.
22.	Liu Y, Liu Z, Luo X, et al. Diagnosis of Parkinson’s disease based on SHAP-value feature selection and biomedical characteristics[J]. Biocybern Biomed Eng, 2022, 42(3): 856-869.
23.	Leung C H, Simpson S, Thangavelu G, et al. The place of local-field-potentials in deep brain stimulation programming for Parkinson’s disease: a review[J]. Brain Sci, 2025, 15(2): 116.
24.	Shokri M, Moghadam Faraj A, Bazzaz A, et al. Machine-learning for Parkinson’s disease: a comprehensive review of datasets, algorithms, and challenges[J]. NPJ Parkinsons Dis, 2025, 11: 187.
25.	Bakstein E, Burgess J, Warwick K, et al. Parkinsonian tremor identification with multiple local field potential feature classification[J]. J Neurosci Methods, 2012, 209(2): 320-330.

1. Luo Y, Qiao L, Li M, et al. Global, regional, national epidemiology and trends of Parkinson’s disease from 1990 to 2021: findings from the Global Burden of Disease Study 2021[J]. Front Neurosci, 2025, 16: 1498756.
2. Poewe W, Seppi K, Tanner C M, et al. Parkinson disease[J]. Nat Rev Dis Primers, 2017, 3: 17013.
3. Hartmann C J, Fliegen S, Groiss S J, et al. An update on best practice of deep brain stimulation in Parkinson’s disease[J]. Ther Adv Neurol Disord, 2019, 12: 1756286419838096.
4. Bronstein J M, Tagliati M, Alterman R L, et al. Deep brain stimulation for Parkinson disease: an expert consensus and review of key issues[J]. Arch Neurol, 2011, 68(2): 165-171.
5. Oliveira A M, Coelho M, Carvalho A, et al. Machine-learning for adaptive deep brain stimulation in Parkinson’s disease: closing the loop[J]. J Neurol, 2023, 270(11): 5313-5326.
6. Whitmer D, de Solages C, Hill B, et al. High frequency deep brain stimulation attenuates subthalamic and cortical rhythms in Parkinson’s disease[J]. Front Hum Neurosci, 2012, 6: 155.
7. Neumann W J, Degen K, Schneider G H, et al. Subthalamic synchronized oscillatory activity correlates with motor impairment in patients with Parkinson’s disease[J]. Mov Disord, 2016, 31(11): 1748-1751.
8. Little S, Pogosyan A, Neal S, et al. Adaptive deep brain stimulation in advanced Parkinson disease[J]. Ann Neurol, 2013, 74(3): 449-457.
9. Jiang H, Zhang J J, Hebb A O, et al. Time-frequency analysis of brain electrical signals for behavior recognition in patients with Parkinson’s disease[C]//2013 47th Asilomar Conference on Signals, Systems and Computers. Pacific Grove: IEEE, 2013: 1843-1847.
10. Niketeghad S, Hebb A O, Nedrud J, et al. Single trial behavioral task classification using subthalamic nucleus local field potential signals[C]//2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Chicago: IEEE, 2014: 3793-3796.
11. Golshan H M, Hebb A O, Hanrahan S J, et al. A multiple kernel learning approach for human behavioral task classification using STN-LFP signal[C]//2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Orlando: IEEE, 2016: 1030-1033.
12. Shah S A, Tinkhauser G, Chen C C, et al. Parkinsonian tremor detection from subthalamic nucleus local field potentials for closed-loop deep brain stimulation[C]//2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Honolulu: IEEE, 2018: 2320-2324.
13. Wang T, Shoaran M, Emami A, et al. Closed-loop adaptive deep brain stimulation in Parkinson’s disease: LFP-based feature analysis and classification[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary: IEEE, 2018: 2536-2540.
14. Hirschmann J, Steina A, Vesper J, et al. Neuronal oscillations predict deep brain stimulation outcome in Parkinson’s disease[J]. Brain Stimul, 2022, 15(3): 792-802.
15. Houston B, Thompson M, Ko A, et al. A machine-learning approach to volitional control of a closed-loop deep brain stimulation system[J]. J Neural Eng, 2019, 16(1): 016004.
16. Reck C, Florin E, Wojtecki L, et al. Characterisation of tremor-associated local field potentials in the subthalamic nucleus in Parkinson’s disease[J]. Eur J Neurosci, 2009, 29(3): 599-612.
17. Wüst C, Torrecillos F, Pogosyan A, et al. STN local field potential recordings from awake patients with Parkinson’s disease on and off medication during 130 Hz DBS[J]. Data Brief, 2022, 44: 108562.
18. Zhao D, Liu Z, Yao M, et al. State-identification of Parkinson’s disease based on transfer learning[J]. Technol Health Care, 2024, 32(6): 4097-4107.
19. Dastin-van Rijn E M, Provenza N R, Calvert J S, et al. Uncovering biomarkers during therapeutic neuromodulation with PARRM: period-based artifact reconstruction and removal method[J]. Cell Rep Methods, 2021, 1(2): 100010.
20. Lee S B, Kim Y J, Hwang S, et al. Predicting Parkinson’s disease progression using gradient boosting decision tree models with electroencephalography signals[J]. Parkinsonism Relat Disord, 2022, 95: 77-85.
21. Snoek J, Larochelle H, Adams R P. Practical Bayesian optimization of machine learning algorithms[J]. Adv Neural Inf Process Syst, 2012, 25: 2951-2959.
22. Liu Y, Liu Z, Luo X, et al. Diagnosis of Parkinson’s disease based on SHAP-value feature selection and biomedical characteristics[J]. Biocybern Biomed Eng, 2022, 42(3): 856-869.
23. Leung C H, Simpson S, Thangavelu G, et al. The place of local-field-potentials in deep brain stimulation programming for Parkinson’s disease: a review[J]. Brain Sci, 2025, 15(2): 116.
24. Shokri M, Moghadam Faraj A, Bazzaz A, et al. Machine-learning for Parkinson’s disease: a comprehensive review of datasets, algorithms, and challenges[J]. NPJ Parkinsons Dis, 2025, 11: 187.
25. Bakstein E, Burgess J, Warwick K, et al. Parkinsonian tremor identification with multiple local field potential feature classification[J]. J Neurosci Methods, 2012, 209(2): 320-330.

Journal of Biomedical Engineering

Parkinson’s disease state recognition based on local field potentials: An ensemble model with feature division

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content