CoChat

Data-driven subtyping of Parkinson's disease using longitudinal clinical records: a cohort study

Open access

The DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index.

Abstract

Parkinson’s disease (PD) is associated with diverse clinical manifestations including motor and non-motor signs and symptoms, and emerging biomarkers. We aimed to reveal the heterogeneity of PD to define subtypes and their progression rates using an automated deep learning algorithm on the top of longitudinal clinical records. This study utilizes the data collected from the Parkinson’s Progression Markers Initiative (PPMI), which is a longitudinal cohort study of patients with newly diagnosed Parkinson’s disease. Clinical information including motor and non-motor assessments, biospecimen examinations, and neuroimaging results were used for identification of PD subtypes. A deep learning algorithm, Long-Short Term Memory (LSTM), was used to represent each patient as a multi-dimensional time series for subtype identification. Both visualization and statistical analysis were performed for analyzing the obtained PD subtypes. As a result, 466 patients with idiopathic PD were investigated and three subtypes were identified. Subtype I (Mild Baseline, Moderate Motor Progression) is comprised of 43.1% of the participants, with average age 58.79 ± 9.53 years, and was characterized by moderate functional decay in motor ability but stable cognitive ability. Subtype II (Moderate Baseline, Mild Progression) is comprised of 22.9% of the participants, with average age 61.93 ± 6.56 years, and was characterized by mild functional decay in both motor and non-motor symptoms. Subtype III (Severe Baseline, Rapid Progression) is comprised 33.9% of the patients, with average age 65.32 ± 8.86 years, and was characterized by rapid progression of both motor and non-motor symptoms. These subtypes suggest that when comprehensive clinical and biomarker data are incorporated into a deep learning algorithm, the disease progression rates do not necessarily associate with baseline severities, and the progression rate of non-motor symptoms is not necessarily correlated with the progression rate of motor symptoms.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-018-37545-z

Cites

40 of 40 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The proposed data-driven subtyping method. (A) Illustration of our LSTM recurrent neural network. The patient representation derived by recurrent hidden layer. Raw patient multi-source data are pre-processed by imputation. For each patient, the merged temporal records are set as input of LSTM corresponding each timestamp. The targets are a set of disjoint temporal records for each patient and obtained by the same pre-process method. There are two kinds of targets function for continuous and binary values separately. Representations generated by all the hidden states are used in patient subtyping. (B) Overall flow of the proposed LSTM-based method.
Figure 1 The proposed data-driven subtyping method. (A) Illustration of our LSTM recurrent neural network. The patient representation derived by recurrent hidden layer. Raw patient multi-source data are pre-processed by imputation. For each patient, the merged temporal records are set as input of LSTM corresponding each timestamp. The targets are a set of disjoint temporal records for each patient and obtained by the same pre-process method. There are two kinds of targets function for continuous and binary values separately. Representations generated by all the hidden states are used in patient subtyping. (B) Overall flow of the proposed LSTM-based method.CC BY · PubMed Central
Figure 2 Visualization of patient subtyping results by various methods. (A) Representation learned by LSTM. (B) Dynamic time warping using sequential target features. (C) Representation learned using PCA with merging sequential data into static vectors. Patients are mapped to the 2-dimensional space using the t-SNE with learned representations as input. Points with three different color represent three subtypes of patients.
Figure 2 Visualization of patient subtyping results by various methods. (A) Representation learned by LSTM. (B) Dynamic time warping using sequential target features. (C) Representation learned using PCA with merging sequential data into static vectors. Patients are mapped to the 2-dimensional space using the t-SNE with learned representations as input. Points with three different color represent three subtypes of patients.CC BY · PubMed Central
Figure 3 Heatmap illustration of the patient subtyping results of LSTM for three subtypes. The colors are generated according to mean values of subtypes. The red color depicts more a severe deficit for the variable and the blue color means that the symptom is less severe. The darker color represents larger difference with total average. Variables with p-value < 0.05 are shown.
Figure 3 Heatmap illustration of the patient subtyping results of LSTM for three subtypes. The colors are generated according to mean values of subtypes. The red color depicts more a severe deficit for the variable and the blue color means that the symptom is less severe. The darker color represents larger difference with total average. Variables with p-value < 0.05 are shown.CC BY · PubMed Central
Figure 4 Comparisons of three Subtypes on disease progression of the variable MDS-UPDRS Part I-III, and H&Y. The time interval between baseline and follow-up is 6 years. The larger slope illustrates a more rapid progression on the corresponding variables. The filled regions indicate 95% Confidence Intervals as error bars for corresponding point estimates. Variables with the p-value < 0.05 are shown.
Figure 4 Comparisons of three Subtypes on disease progression of the variable MDS-UPDRS Part I-III, and H&Y. The time interval between baseline and follow-up is 6 years. The larger slope illustrates a more rapid progression on the corresponding variables. The filled regions indicate 95% Confidence Intervals as error bars for corresponding point estimates. Variables with the p-value < 0.05 are shown.CC BY · PubMed Central
Figure 5 Comparisons of three Subtypes on disease progression of the variable MoCA, LNS, SDMT, and SCOPA-AUT. The time interval between baseline and follow-up is 6 years. The larger slope illustrates a more rapid progression on the corresponding variables. The filled regions indicate 95% Confidence Intervals as error bars for corresponding point estimates. Variables with the p-value < 0.05 are shown.
Figure 5 Comparisons of three Subtypes on disease progression of the variable MoCA, LNS, SDMT, and SCOPA-AUT. The time interval between baseline and follow-up is 6 years. The larger slope illustrates a more rapid progression on the corresponding variables. The filled regions indicate 95% Confidence Intervals as error bars for corresponding point estimates. Variables with the p-value < 0.05 are shown.CC BY · PubMed Central
Figure 6 Relationship with Conventional PD Subtypes. (A) Patient correlation of three subtypes and motor subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into motor subtypes including TD, PIGD, and Indeterminate. The longitudinal correlation of three subtypes with TD and PIGD are plotted by lines respectively. (B) Patient correlation of three subtypes and cognitive subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into cognitive subtypes including Normal Cognition (PD-NC), Mild Cognitive Impairment (PD-MCI), and Dementia (PDD). The longitudinal correlation of three subtypes with PD-NC, PD-MCI, and PDD are plotted by lines respectively. (C) Patient correlation of three subtypes and mood subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into mood subtypes including Anxiety, Depression, Depression-Anxiety (DA), and Normal Mood. The longitudinal correlation of three subtypes with Anxiety, Depression, and Anxiety-Depression are plotted by lines respectively.
Figure 6 Relationship with Conventional PD Subtypes. (A) Patient correlation of three subtypes and motor subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into motor subtypes including TD, PIGD, and Indeterminate. The longitudinal correlation of three subtypes with TD and PIGD are plotted by lines respectively. (B) Patient correlation of three subtypes and cognitive subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into cognitive subtypes including Normal Cognition (PD-NC), Mild Cognitive Impairment (PD-MCI), and Dementia (PDD). The longitudinal correlation of three subtypes with PD-NC, PD-MCI, and PDD are plotted by lines respectively. (C) Patient correlation of three subtypes and mood subtypes at baseline, median time point, and 6-year follow-up. Patients are categorized into mood subtypes including Anxiety, Depression, Depression-Anxiety (DA), and Normal Mood. The longitudinal correlation of three subtypes with Anxiety, Depression, and Anxiety-Depression are plotted by lines respectively.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 40 references

Research works printed but not linked: 1

  1. Van Der Maaten, L., Postma, E. & Van den Herik, J. Dimensionality reduction: a comparative. J Mach Learn. Res 10, 66–71 (2009).

Cited by

See all 144

Metadata

Authors
Zhang, X., Chou, J., Liang, J., Xiao, C., Zhao, Y., Sarva, H., Henchcliffe, C., & Wang, F.
Affiliations
  • Cornell University (US)
  • Tsinghua University (CN)
  • IBM Research - Cambridge (United States) (US)
Corresponding author
Wang, Fei
Venue
Scientific Reports
Published
2019-01-28
Volume
9
Issue
1
Pages
797-797
ISSN
2045-2322 (ISSN-L)
OpenAlex
W2914683543
Cited by
137
References
42
Citations by year
2026: 12 · 2025: 15 · 2024: 17 · 2023: 22 · 2022: 26 · 2021: 22 · 2020: 19 · 2019: 4
FWCI
12.01
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • eScholarship (California Digital Library) (submittedVersion)
  • eScholarship (California Digital Library) (submittedVersion, cc-by)
Funders
  • National Science Foundation
  • National Science Foundation Michael J. Fox Foundation
Topics
  • Health Sciences › Medicine › Clinical Neurology › Parkinson's Disease Mechanisms and Treatments
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
Keywords
Parkinson's disease, disease subtyping, disease progression, deep learning, long short-term memory, Parkinson's Progression Markers Initiative, motor symptoms, non-motor symptoms, disease heterogeneity, biomarkers
MeSH terms
Deep Learning, Aged, Female, Humans, Longitudinal Studies, Male, Middle Aged, Neuropsychological Tests, Parkinson Disease, Age Distribution, Disease Progression, Neuroimaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Data-driven subtyping of Parkinson's disease using longitudinal clinical records: a cohort study. https://app.cochat.ai/papers/10.1038/s41598-018-37545-z
The paper
Zhang, X., Chou, J., Liang, J., Xiao, C., Zhao, Y., Sarva, H., Henchcliffe, C., & Wang, F. (2019). Data-driven subtyping of Parkinson's disease using longitudinal clinical records: a cohort study. Scientific Reports. https://doi.org/10.1038/s41598-018-37545-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.