Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease

Jeroen G V Habets; Christian Herff; Alfonso A Fasano; Martijn Beudel; Ersoy Kocabicak; Alfons Schnitzler; Muneer Abu Snineh; Suneil K Kalia; Carolina Ramirez-Gómez; Mojgan Hodaie; Renato P Munhoz; Eline Rouleau; Onur Yildiz; Eduard Linetsky; Rick Schuurman; Christian J Hartmann; Andres M Lozano; Rob M A De Bie; Yasin Temel; Marcus L F Janssen

doi:10.1159/000519960

Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease

Jeroen G V Habets^*, Christian Herff, Alfonso A Fasano, Martijn Beudel, Ersoy Kocabicak, Alfons Schnitzler, Muneer Abu Snineh, Suneil K Kalia, Carolina Ramirez-Gómez, Mojgan Hodaie, Renato P Munhoz, Eline Rouleau, Onur Yildiz, Eduard Linetsky, Rick Schuurman, Christian J Hartmann, Andres M Lozano, Rob M A De Bie, Yasin Temel, Marcus L F Janssen

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

BACKGROUND: Subthalamic nucleus deep brain stimulation (STN DBS) is an established therapy for Parkinson's disease (PD) patients suffering from motor response fluctuations despite optimal medical treatment, or severe dopaminergic side effects. Despite careful clinical selection and surgical procedures, some patients do not benefit from STN DBS. Preoperative prediction models are suggested to better predict individual motor response after STN DBS. We validate a preregistered model, DBS-PREDICT, in an external multicenter validation cohort.

METHODS: DBS-PREDICT considered eleven, solely preoperative, clinical characteristics and applied a logistic regression to differentiate between weak and strong motor responders. Weak motor response was defined as no clinically relevant improvement on the Unified Parkinson's Disease Rating Scale (UPDRS) II, III, or IV, 1 year after surgery, defined as, respectively, 3, 5, and 3 points or more. Lower UPDRS III and IV scores and higher age at disease onset contributed most to weak response predictions. Individual predictions were compared with actual clinical outcomes.

RESULTS: 322 PD patients treated with STN DBS from 6 different centers were included. DBS-PREDICT differentiated between weak and strong motor responders with an area under the receiver operator curve of 0.76 and an accuracy up to 77%.

CONCLUSION: Proving generalizability and feasibility of preoperative STN DBS outcome prediction in an external multicenter cohort is an important step in creating clinical impact in DBS with data-driven tools. Future prospective studies are required to overcome several inherent practical and statistical limitations of including clinical decision support systems in DBS care.

Original language	English
Pages (from-to)	121-129
Number of pages	9
Journal	Stereotactic and Functional Neurosurgery
Volume	100
Issue number	2
Early online date	25 Nov 2021
DOIs	https://doi.org/10.1159/000519960
Publication status	Published - Mar 2022

Keywords

Parkinson's disease
Deep brain stimulation
Motor response
Outcome prediction
Machine learning
Clinical prediction models
CLINICALLY IMPORTANT DIFFERENCE
SUBTHALAMIC NUCLEUS
TRIAL

Access to Document

10.1159/000519960Licence: CC BY-NC

Cite this

Habets, J. G. V., Herff, C., Fasano, A. A., Beudel, M., Kocabicak, E., Schnitzler, A., Snineh, M. A., Kalia, S. K., Ramirez-Gómez, C., Hodaie, M., Munhoz, R. P., Rouleau, E., Yildiz, O., Linetsky, E., Schuurman, R., Hartmann, C. J., Lozano, A. M., De Bie, R. M. A., Temel, Y., & Janssen, M. L. F. (2022). Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease. Stereotactic and Functional Neurosurgery, 100(2), 121-129. https://doi.org/10.1159/000519960

@article{53a63144dd2e45cdbfadafd8625d6543,

title = "Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease",

abstract = "BACKGROUND: Subthalamic nucleus deep brain stimulation (STN DBS) is an established therapy for Parkinson's disease (PD) patients suffering from motor response fluctuations despite optimal medical treatment, or severe dopaminergic side effects. Despite careful clinical selection and surgical procedures, some patients do not benefit from STN DBS. Preoperative prediction models are suggested to better predict individual motor response after STN DBS. We validate a preregistered model, DBS-PREDICT, in an external multicenter validation cohort.METHODS: DBS-PREDICT considered eleven, solely preoperative, clinical characteristics and applied a logistic regression to differentiate between weak and strong motor responders. Weak motor response was defined as no clinically relevant improvement on the Unified Parkinson's Disease Rating Scale (UPDRS) II, III, or IV, 1 year after surgery, defined as, respectively, 3, 5, and 3 points or more. Lower UPDRS III and IV scores and higher age at disease onset contributed most to weak response predictions. Individual predictions were compared with actual clinical outcomes.RESULTS: 322 PD patients treated with STN DBS from 6 different centers were included. DBS-PREDICT differentiated between weak and strong motor responders with an area under the receiver operator curve of 0.76 and an accuracy up to 77%.CONCLUSION: Proving generalizability and feasibility of preoperative STN DBS outcome prediction in an external multicenter cohort is an important step in creating clinical impact in DBS with data-driven tools. Future prospective studies are required to overcome several inherent practical and statistical limitations of including clinical decision support systems in DBS care.",

keywords = "Parkinson's disease, Deep brain stimulation, Motor response, Outcome prediction, Machine learning, Clinical prediction models, CLINICALLY IMPORTANT DIFFERENCE, SUBTHALAMIC NUCLEUS, TRIAL",

author = "Habets, {Jeroen G V} and Christian Herff and Fasano, {Alfonso A} and Martijn Beudel and Ersoy Kocabicak and Alfons Schnitzler and Snineh, {Muneer Abu} and Kalia, {Suneil K} and Carolina Ramirez-G{\'o}mez and Mojgan Hodaie and Munhoz, {Renato P} and Eline Rouleau and Onur Yildiz and Eduard Linetsky and Rick Schuurman and Hartmann, {Christian J} and Lozano, {Andres M} and {De Bie}, {Rob M A} and Yasin Temel and Janssen, {Marcus L F}",

note = "Funding Information: No direct funding is received and there is no conflict of interest due to the reported funding for this work. RMAB received research support from Netherlands Organization for Health Research and Development, Parkinson Vereniging, Stichting Parkinson Nederland, GE Health, Medtronic, Lysosomal Therapeutics, Neuroderm, all paid to the department. AAF received research support from Medtronic and Boston Scientific and honoraria from Abbvie, Abbott, Ceregare, Boston Scientific, and Medtronic. CJH received honoraria from Abbott. MH received honoraria from Medtronic. SKK is consultant for Medtronic for declaration. AML is consultant for Medtronic, Boston Scientific, and Abbott. MAS received consultation fees from Abbvie and research support from Medtronic and Boston Scientific. RS is consultant for Medtronic, Boston Scientific, and Elekta. YT received a research grant from Weijerhorst Foundation. CH received funding from Dutch Research Council (NWO). Funding Information: No direct funding is received and there is no conflict of interest due to the reported funding for this work. RMAB received research support from Netherlands Organization for Health Research and Development, Parkinson Vereniging, Stichting Parkinson Nederland, GE Health, Medtronic, Lysosomal Therapeutics, Neuroderm, all paid to the department. AAF received research support from Medtronic and Boston Scientific and honoraria from Abbvie, Abbott, Ceregare, Boston Scientific, and Medtronic. CJH received honoraria from Abbott. MH received honoraria from Medtronic. SKK is consultant for Medtronic for declaration. AML is consultant for Medtronic, Boston Scientific, and Abbott. MAS received consultation fees from Abbvie and research support from Medtronic and Boston Scientific. RS is consultant for Medtronic, Boston Scientific, and Elekta. YT received a research grant from Weijerhorst Foundation. CH received funding from Dutch Research Council (NWO). Publisher Copyright: {\textcopyright} 2021 The Author(s) Published by S. Karger AG, Basel.",

year = "2022",

month = mar,

doi = "10.1159/000519960",

language = "English",

volume = "100",

pages = "121--129",

journal = "Stereotactic and Functional Neurosurgery",

issn = "1011-6125",

publisher = "S. Karger AG",

number = "2",

}

Habets, JGV, Herff, C, Fasano, AA, Beudel, M, Kocabicak, E, Schnitzler, A, Snineh, MA, Kalia, SK, Ramirez-Gómez, C, Hodaie, M, Munhoz, RP, Rouleau, E, Yildiz, O, Linetsky, E, Schuurman, R, Hartmann, CJ, Lozano, AM, De Bie, RMA, Temel, Y & Janssen, MLF 2022, 'Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease', Stereotactic and Functional Neurosurgery, vol. 100, no. 2, pp. 121-129. https://doi.org/10.1159/000519960

TY - JOUR

T1 - Multicenter Validation of Individual Preoperative Motor Outcome Prediction for Deep Brain Stimulation in Parkinson's Disease

AU - Habets, Jeroen G V

AU - Herff, Christian

AU - Fasano, Alfonso A

AU - Beudel, Martijn

AU - Kocabicak, Ersoy

AU - Schnitzler, Alfons

AU - Snineh, Muneer Abu

AU - Kalia, Suneil K

AU - Ramirez-Gómez, Carolina

AU - Hodaie, Mojgan

AU - Munhoz, Renato P

AU - Rouleau, Eline

AU - Yildiz, Onur

AU - Linetsky, Eduard

AU - Schuurman, Rick

AU - Hartmann, Christian J

AU - Lozano, Andres M

AU - De Bie, Rob M A

AU - Temel, Yasin

AU - Janssen, Marcus L F

N1 - Funding Information: No direct funding is received and there is no conflict of interest due to the reported funding for this work. RMAB received research support from Netherlands Organization for Health Research and Development, Parkinson Vereniging, Stichting Parkinson Nederland, GE Health, Medtronic, Lysosomal Therapeutics, Neuroderm, all paid to the department. AAF received research support from Medtronic and Boston Scientific and honoraria from Abbvie, Abbott, Ceregare, Boston Scientific, and Medtronic. CJH received honoraria from Abbott. MH received honoraria from Medtronic. SKK is consultant for Medtronic for declaration. AML is consultant for Medtronic, Boston Scientific, and Abbott. MAS received consultation fees from Abbvie and research support from Medtronic and Boston Scientific. RS is consultant for Medtronic, Boston Scientific, and Elekta. YT received a research grant from Weijerhorst Foundation. CH received funding from Dutch Research Council (NWO). Funding Information: No direct funding is received and there is no conflict of interest due to the reported funding for this work. RMAB received research support from Netherlands Organization for Health Research and Development, Parkinson Vereniging, Stichting Parkinson Nederland, GE Health, Medtronic, Lysosomal Therapeutics, Neuroderm, all paid to the department. AAF received research support from Medtronic and Boston Scientific and honoraria from Abbvie, Abbott, Ceregare, Boston Scientific, and Medtronic. CJH received honoraria from Abbott. MH received honoraria from Medtronic. SKK is consultant for Medtronic for declaration. AML is consultant for Medtronic, Boston Scientific, and Abbott. MAS received consultation fees from Abbvie and research support from Medtronic and Boston Scientific. RS is consultant for Medtronic, Boston Scientific, and Elekta. YT received a research grant from Weijerhorst Foundation. CH received funding from Dutch Research Council (NWO). Publisher Copyright: © 2021 The Author(s) Published by S. Karger AG, Basel.

PY - 2022/3

Y1 - 2022/3

N2 - BACKGROUND: Subthalamic nucleus deep brain stimulation (STN DBS) is an established therapy for Parkinson's disease (PD) patients suffering from motor response fluctuations despite optimal medical treatment, or severe dopaminergic side effects. Despite careful clinical selection and surgical procedures, some patients do not benefit from STN DBS. Preoperative prediction models are suggested to better predict individual motor response after STN DBS. We validate a preregistered model, DBS-PREDICT, in an external multicenter validation cohort.METHODS: DBS-PREDICT considered eleven, solely preoperative, clinical characteristics and applied a logistic regression to differentiate between weak and strong motor responders. Weak motor response was defined as no clinically relevant improvement on the Unified Parkinson's Disease Rating Scale (UPDRS) II, III, or IV, 1 year after surgery, defined as, respectively, 3, 5, and 3 points or more. Lower UPDRS III and IV scores and higher age at disease onset contributed most to weak response predictions. Individual predictions were compared with actual clinical outcomes.RESULTS: 322 PD patients treated with STN DBS from 6 different centers were included. DBS-PREDICT differentiated between weak and strong motor responders with an area under the receiver operator curve of 0.76 and an accuracy up to 77%.CONCLUSION: Proving generalizability and feasibility of preoperative STN DBS outcome prediction in an external multicenter cohort is an important step in creating clinical impact in DBS with data-driven tools. Future prospective studies are required to overcome several inherent practical and statistical limitations of including clinical decision support systems in DBS care.

AB - BACKGROUND: Subthalamic nucleus deep brain stimulation (STN DBS) is an established therapy for Parkinson's disease (PD) patients suffering from motor response fluctuations despite optimal medical treatment, or severe dopaminergic side effects. Despite careful clinical selection and surgical procedures, some patients do not benefit from STN DBS. Preoperative prediction models are suggested to better predict individual motor response after STN DBS. We validate a preregistered model, DBS-PREDICT, in an external multicenter validation cohort.METHODS: DBS-PREDICT considered eleven, solely preoperative, clinical characteristics and applied a logistic regression to differentiate between weak and strong motor responders. Weak motor response was defined as no clinically relevant improvement on the Unified Parkinson's Disease Rating Scale (UPDRS) II, III, or IV, 1 year after surgery, defined as, respectively, 3, 5, and 3 points or more. Lower UPDRS III and IV scores and higher age at disease onset contributed most to weak response predictions. Individual predictions were compared with actual clinical outcomes.RESULTS: 322 PD patients treated with STN DBS from 6 different centers were included. DBS-PREDICT differentiated between weak and strong motor responders with an area under the receiver operator curve of 0.76 and an accuracy up to 77%.CONCLUSION: Proving generalizability and feasibility of preoperative STN DBS outcome prediction in an external multicenter cohort is an important step in creating clinical impact in DBS with data-driven tools. Future prospective studies are required to overcome several inherent practical and statistical limitations of including clinical decision support systems in DBS care.

KW - Parkinson's disease

KW - Deep brain stimulation

KW - Motor response

KW - Outcome prediction

KW - Machine learning

KW - Clinical prediction models

KW - CLINICALLY IMPORTANT DIFFERENCE

KW - SUBTHALAMIC NUCLEUS

KW - TRIAL

U2 - 10.1159/000519960

DO - 10.1159/000519960

M3 - Article

C2 - 34823246

SN - 1011-6125

VL - 100

SP - 121

EP - 129

JO - Stereotactic and Functional Neurosurgery

JF - Stereotactic and Functional Neurosurgery

IS - 2

ER -