Integrating digital gait data with metabolomics and clinical data to predict outcomes in Parkinson’s disease

被引：2

作者：

Brzenczek, Cyril ^{[1
]}

Klopfenstein, Quentin ^{[1
]}

Hähnel, Tom ^{[2
,3
]}

Fröhlich, Holger ^{[2
,4
]}

Glaab, Enrico ^{[1
]}

Zelimkhanov, Gelani ^{[5
,7
]}

Wollscheid-Lengeling, Evi ^{[6
]}

Wilmes, Paul ^{[6
]}

Vilas Boas, Liliana ^{[7
]}

Vega, Carlos ^{[5
]}

Vaillant, Michel ^{[5
]}

Tsurkalenko, Olena ^{[5
]}

Trouet, Johanna ^{[5
]}

Ting Jiin Loo, Rebecca ^{[6
]}

Thiry, Elodie ^{[7
]}

Thien, Hermann ^{[5
]}

Theresine, Maud ^{[5
]}

Sokolowska, Kate ^{[5
]}

Soboleva, Ekaterina ^{[6
,7
]}

Soare, Ruxandra ^{[6
]}

Sharify, Amir ^{[5
]}

Severino, Raquel ^{[5
]}

Schwamborn, Jens ^{[6
]}

Schneider, Reinhard ^{[6
]}

Schmitz, Sabine ^{[6
]}

Satagopam, Venkata ^{[6
]}

Sapienza, Stefano ^{[6
]}

Rosales, Eduardo ^{[5
]}

Roomp, Kirsten ^{[6
]}

Roland, Olivia ^{[5
]}

Richard, Ilsé ^{[5
]}

Remark, Lucie ^{[5
]}

Reddy Bobbili, Dheeraj ^{[6
]}

Rawal, Rajesh ^{[6
]}

Rauschenberger, Armin ^{[6
]}

Pexaras, Achilleas ^{[5
]}

Perquin, Magali ^{[5
]}

Pavelka, Lukas ^{[5
,7
]}

Pauly, Laure ^{[5
,11
]}

Pauly, Claire ^{[5
,7
]}

Pachchek, Sinthuja ^{[6
]}

Gomes, Clarissa P. C. ^{[6
]}

Noor, Fozia ^{[5
]}

Niño Uribe, Maria Fernanda ^{[6
,7
]}

Nicolay, Jean-Paul ^{[17
]}

Nicolai, Beatrice ^{[7
]}

Nickels, Sarah ^{[6
]}

Nehrbass, Ulf ^{[5
]}

Nati, Romain ^{[7
]}

Munsch, Maeva ^{[5
]}

机构：

[1] Biomedical Data Science Group, Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, Esch-sur-Alzette, Luxembourg

[2] Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing, Sankt Augustin, Germany

[3] Department of Neurology, Medical Faculty and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

[4] Bonn-Aachen International Center for IT (b-it), University of Bonn, Bonn, Germany

[5] Luxembourg Institute of Health, Strassen, Luxembourg

[6] Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg

[7] Centre Hospitalier de Luxembourg, Strassen, Luxembourg

[8] Centre Hospitalier Emile Mayrisch, Esch-sur-Alzette, Luxembourg

[9] Laboratoire National de Santé, Dudelange, Luxembourg

[10] Association of Physiotherapists in Parkinson’s Disease Europe, Esch-sur-Alzette, Luxembourg

[11] Faculty of Science, Technology and Medicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg

[12] Department of Epidemiology, CAPHRI School for Public Health and Primary Care, Maastricht University Medical Centre, Maastricht, Netherlands

[13] Private Practice, Ettelbruck, Luxembourg

[14] Parkinson Luxembourg Association, Leudelange, Luxembourg

[15] Luxembourg Center of Neuropathology, Dudelange, Luxembourg

[16] Department of Life Sciences and Medicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg

[17] Private Practice, Luxembourg, Luxembourg

来源：

npj Digital Medicine | 2024年 / 7卷 / 01期

关键词：

81;

D O I：

10.1038/s41746-024-01236-z

中图分类号：

学科分类号：

摘要：

Parkinson’s disease (PD) presents diverse symptoms and comorbidities, complicating its diagnosis and management. The primary objective of this cross-sectional, monocentric study was to assess digital gait sensor data’s utility for monitoring and diagnosis of motor and gait impairment in PD. As a secondary objective, for the more challenging tasks of detecting comorbidities, non-motor outcomes, and disease progression subgroups, we evaluated for the first time the integration of digital markers with metabolomics and clinical data. Using shoe-attached digital sensors, we collected gait measurements from 162 patients and 129 controls in a single visit. Machine learning models showed significant diagnostic power, with AUC scores of 83–92% for PD vs. control and up to 75% for motor severity classification. Integrating gait data with metabolomics and clinical data improved predictions for challenging-to-detect comorbidities such as hallucinations. Overall, this approach using digital biomarkers and multimodal data integration can assist in objective disease monitoring, diagnosis, and comorbidity detection.

引用

共 50 条

[31] A Gait Data-Driven Approach to Identify Different Clinical Subtypes of Parkinson's Disease: a Proposal for a New Classification
Mostile, G.
Portaro, G.
Dibilio, V.
Terranova, R.
Cunsolo, P.
Contrafatto, F.
Donzuso, G.
Rascuna, C.
Cicero, C. E.
Luca, A.
Nicoletti, A.
Zappia, M.
EUROPEAN JOURNAL OF NEUROLOGY, 2020, 27 : 322 - 322
[32] Spinal Cord Stimulation for Gait Disorders in Parkinson's Disease and Atypical Parkinsonism: A Systematic Review of Preclinical and Clinical Data
Ciocca, Matteo
Seemungal, Barry M.
Tai, Yen F.
NEUROMODULATION, 2023, 26 (07): : 1339 - 1361
[33] Correlation between the brain activity with gait imagery and gait performance in adults with Parkinson's disease: A data set
Nishida, Daisuke
Mizuno, Katsuhiro
Yamada, Emi
Tsuji, Tetsuya
Hanakawa, Takashi
Liu, Meigen
DATA IN BRIEF, 2021, 36
[34] Hyposmia may predict development of freezing of gait in Parkinson's disease
Lee, Jae Jung
Hong, Jin Yong
Baik, Jong Sam
JOURNAL OF NEURAL TRANSMISSION, 2021, 128 (06) : 763 - 770
[35] Gait and Posture Control Impairments Predict Falls in Parkinson's Disease
Salins, Naomi
Krishnamurthi, Narayanan
Santiago, Anthony
Dhall, Rohit
Moguel-Cobos, Guillermo
Sadreddin, Arshia
Husain, Sameea
Lieberman, Abraham
Pan, Di
Dhanani, Sara
NEUROLOGY, 2012, 78
[36] Freezing of Gait Can Predict Cognitive Decline in Parkinson's Disease
Qu, Y.
Li, J. T.
Chen, Y. P.
Li, J. Y.
Qin, Q. X.
Wang, D. L.
Zhao, J. W.
Mao, Z. J.
Xiong, Y. J.
Min, Z.
Xue, Z.
MOVEMENT DISORDERS, 2022, 37 : S548 - S549
[37] Hyposmia may predict development of freezing of gait in Parkinson’s disease
Jae Jung Lee
Jin Yong Hong
Jong Sam Baik
Journal of Neural Transmission, 2021, 128 : 763 - 770
[38] Identification of blood metabolites associated with risk of Alzheimer's disease by integrating genomics and metabolomics data
Liu, Shuai
Zhong, Hua
Zhu, Jingjing
Wu, Lang
MOLECULAR PSYCHIATRY, 2024, 29 (04) : 1153 - 1162
[39] Metabolomics in Parkinson's disease
Troisi, Jacopo
Landolfi, Annamaria
Cavallo, Pierpaolo
Marciano, Francesca
Barone, Paolo
Amboni, Marianna
ADVANCES IN CLINICAL CHEMISTRY, VOL 104, 2021, 104 : 107 - 149
[40] Analysis of Parkinson's Disease Data
Gottapu, Ram Deepak
Dagli, Cihan H.
CYBER PHYSICAL SYSTEMS AND DEEP LEARNING, 2018, 140 : 334 - 341

← 1 2 3 4 5 →