STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments

• URL: http://arxiv.org/abs/2604.17611v1
• Date: Sun, 19 Apr 2026 20:53:59 GMT
• Title: STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments
• Abstract summary: This study proposes STEP-PD, a severity-aware machine learning framework to classify PD severity using clinically interpretable boundaries.<n>Disease severity is defined using Hoehn and Yahr staging and grouped into three clinically meaningful categories: Healthy, Mild PD (stages 1-2), and Moderate-to-Severe PD (stages 3-5)<n>XGBoost achieved the strongest and most stable performance, with accuracies of 95.48% (Healthy vs. Mild), 99.44% (Healthy vs. Moderate-to-Severe), and 96.78% (Mild vs. Moderate-to-Severe)
• Score: 1.5441222602475007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parkinson's disease (PD) is a progressive disorder in which symptom burden and functional impairment evolve over time, making severity staging essential for clinical monitoring and treatment planning. However, many computational studies emphasize binary PD detection and do not fully use repeated follow-up clinical assessments for stage-aware prediction. This study proposes STEP-PD, a severity-aware machine learning framework to classify PD severity using clinically interpretable boundaries. It leverages all available visits from the Parkinson's Progression Markers Initiative (PPMI) and integrates routinely collected subjective questionnaires and objective clinician-assessed measures. Disease severity is defined using Hoehn and Yahr staging and grouped into three clinically meaningful categories: Healthy, Mild PD (stages 1-2), and Moderate-to-Severe PD (stages 3-5). Three binary classification problems and a three-class severity task were evaluated using stratified cross-validation with imbalance-aware training. To enhance interpretability, SHAP was used to provide global explanations and local patient-level waterfall explanations. Across all tasks, XGBoost achieved the strongest and most stable performance, with accuracies of 95.48% (Healthy vs. Mild), 99.44% (Healthy vs. Moderate-to-Severe), and 96.78% (Mild vs. Moderate-to-Severe), and 94.14% accuracy with 0.8775 Macro-F1 for three-class severity classification. Explainability results highlight a shift from early motor features to progression-related axial and balance impairments. These findings show that multimodal clinical assessments within the PPMI cohort can support accurate and interpretable visit-level PD severity stratification.

Related papers

• Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis [47.559337485629904]
  This work introduces MedVCR, a counterfactual reasoning framework that mimics clinical diagnostic thinking.<n> MedVCR comprises three components: a Counterfactual Generator that synthesizes tissue evolution under specified pathological states.<n>It is evaluated under both fully supervised (e.g., colposcopy) and weakly supervised (e.g., colonoscopy) video diagnosis settings, yielding 2.6%-10.2% performance gains.
  arXiv  Detail & Related papers  (2026-05-26T02:46:15Z)
• From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction [61.12883122613684]
  This Review focuses on intervention-aware disease trajectory modeling in clinical AI--methods estimating patient-specific longitudinal disease evolution and assessing trajectory changes under alternative treatments.<n>We organize the field around six linked components: three decision tasks (factual forecasting, counterfactual estimation, policy evaluation) and three data-generating mechanisms (disease evolution, treatment assignment, observation process) that determine identifiability.<n>We present the first unified framework bridging forecasting, counterfactual trajectories, and policy evaluation across discrete/continuous time, explicitly addressing treatment assignment, time-varying confounding, and observation bias.
  arXiv  Detail & Related papers  (2026-05-16T10:45:26Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• AD-CARE: A Guideline-grounded, Modality-agnostic LLM Agent for Real-world Alzheimer's Disease Diagnosis with Multi-cohort Assessment, Fairness Analysis, and Reader Study [45.632341143278886]
  We introduce AD-CARE, a modality-agnostic agent that performs guideline-grounded diagnostic assessment from incomplete, heterogeneous inputs.<n>By dynamically orchestrating specialized diagnostic tools, AD-CARE generates transparent, report-style outputs aligned with real-world clinical outputs.
  arXiv  Detail & Related papers  (2026-03-26T11:10:01Z)
• Topological descriptors of foot clearance gait dynamics improve differential diagnosis of Parkinsonism [0.8388591755871735]
  We evaluate Topological Data Analysis as a complementary tool for Parkinsonism classification.<n> Persistent homology produced Betti curves, persistence landscapes, and silhouettes.<n>For IPD vs VaP, foot clearance variables minimum toe clearance, maximum toe late swing, and maximum heel clearance achieved 83% accuracy.
  arXiv  Detail & Related papers  (2026-03-06T12:29:05Z)
• SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making [1.4572472675272603]
  Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors.<n>Machine learning (ML) has demonstrated potential in supporting PD diagnosis, but existing approaches often rely on subjective reports only.<n>This study proposes SCOPE-PD, an explainable AI-based prediction framework, by integrating subjective and objective assessments.
  arXiv  Detail & Related papers  (2026-01-30T03:49:31Z)
• Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases [48.87360916431396]
  We introduce MedR-Bench, a benchmarking dataset of 1,453 structured patient cases, annotated with reasoning references.<n>We propose a framework encompassing three critical examination recommendation, diagnostic decision-making, and treatment planning, simulating the entire patient care journey.<n>Using this benchmark, we evaluate five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and Gemini-2.0-Flash Thinking, etc.
  arXiv  Detail & Related papers  (2025-03-06T18:35:39Z)
• SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy [45.2233252981348]
  Large Language Models (LLMs) have been shown to encode clinical knowledge.<n>We present SemioLLM, an evaluation framework that benchmarks 6 state-of-the-art models.<n>We show that most LLMs are able to accurately and confidently generate probabilistic predictions of seizure onset zones in the brain.
  arXiv  Detail & Related papers  (2024-07-03T11:02:12Z)
• AXIAL: Attention-based eXplainability for Interpretable Alzheimer's Localized Diagnosis using 2D CNNs on 3D MRI brain scans [43.06293430764841]
  This study presents an innovative method for Alzheimer's disease diagnosis using 3D MRI designed to enhance the explainability of model decisions. Our approach adopts a soft attention mechanism, enabling 2D CNNs to extract volumetric representations. With voxel-level precision, our method identified which specific areas are being paid attention to, identifying these predominant brain regions.
  arXiv  Detail & Related papers  (2024-07-02T16:44:00Z)
• Predicting Parkinson's disease evolution using deep learning [1.4610685586329806]
  Parkinson's disease is a neurological condition that occurs in nearly 1% of the world's population. There is not a single blood test or biomarker available to diagnose Parkinson's disease. No AI tools have been designed to identify the stage of progression.
  arXiv  Detail & Related papers  (2023-12-28T10:30:54Z)
• Pose-based Tremor Type and Level Analysis for Parkinson's Disease from Video [10.577497906432498]
  We propose to analyze Parkinson's tremor (PT) to support the analysis of PD. We present SPA-PTA, a deep learning-based PT classification and severity estimation system.
  arXiv  Detail & Related papers  (2023-12-21T12:05:01Z)
• IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction [47.999621481852266]
  We propose an interpretable graph learning-based model which interprets the clinical relevance of the input features towards the task. In a clinical scenario, such a model can assist the clinical experts in better decision-making for diagnosis and treatment planning. Our proposed model shows superior performance with respect to compared methods with an increase in an average accuracy of 3.2% for Tadpole, 1.6% for UKBB Gender, and 2% for the UKBB Age prediction task.
  arXiv  Detail & Related papers  (2021-03-29T13:04:02Z)
• Machine learning discrimination of Parkinson's Disease stages from walker-mounted sensors data [0.0]
  This study applies machine learning methods to discriminate six stages of Parkinson's Disease (PD) progression. The data was acquired by low cost walker-mounted sensors in an experiment at a movement disorders clinic.
  arXiv  Detail & Related papers  (2020-06-22T09:34:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.