FoG-STAR: Freezing of Gait Severity, Tasks, Activities, and Ratings

README – FoG-STAR: Freezing of Gait Severity, Tasks, Activities, and Ratings 📌 OverviewThis dataset contains wearable inertial sensor recordings and clinical/demographic information collected from 22 people with Parkinson’s disease.It is designed to support research on Freezing of Gait (FoG) detection, severity estimation, activity recognition, and digital biomarkers.The dataset is organized in two CSV files:sensor_data.csv → synchronized inertial sensor signals with FoG labels and task annotationsclinical_data.csv → subject-level demographic and clinical assessments📂 Filessensor_data.csv → Sensor-based recordings (31 columns, sampled at 60 Hz)clinical_data.csv → Demographic and clinical metadata (10 variables × 22 subjects)README.md → This documentationLICENSE → Dataset license (CC-BY 4.0)FoG-Star_Analytics.ipynb → Example Python utilities for generating statistics and figures📑 1. Sensor Data (sensor_data.csv)Recording setupSensors: Accelerometer (g) + Gyroscope (°/s)Positions: Left ankle, Right ankle, Back, WristSampling frequency: 60 HzRecording context: Motor tasks designed to elicit or challenge gaitColumn definitionsColumn(s)NameDescription1timestampFloat, timestamp in ms (60 Hz)2–25Sensor signalsFormat: [position][sensor][axis]. Positions = ankleL, ankleR, back, wrist; Sensor = acc (g), gyro (°/s); Axis = x,y,z26activityMotor activity code: 1=Walking, 2=Sit, 3=Stand, 4=Sit-to-Stand, 5=Stand-to-Sit, 6=Turn Right, 7=Turn Left27fogBinary FoG label: 0=No FoG, 1=FoG28fog_severitySeverity during FoG: 1=Shuffling, 2=Trembling, 3=Akinesia29subjectIDSubject identifier (1–22), link to clinical_data.csv30sessionIDRecording session ID (usually 1, but >1 if multiple recordings were needed)31taskIDTask code: 1=Timed Up-and-Go, 2=Stand 1min, 3=Walk back/forth, 4=Walk+Doorway, 5=Walk+Water, 6=Walk+Count, 7=360° turn📑 2. Clinical Data (clinical_data.csv)Population22 subjects with Parkinson’s diseaseEach row corresponds to one subject (linked via subjectID)Column definitionsColumnVariableDescription1subjectIDSubject ID (1–22), matches sensor_data.csv2ageAge in years3genderGender (M/F)4disease_durationYears since PD diagnosis5h_yHoehn & Yahr stage (0–5, higher = more advanced PD)6updrs_iiiMDS-UPDRS Part III score (0–76, higher = worse motor impairment)7fog_qFreezing of Gait Questionnaire (0–24, higher = more severe FoG)8mocaMontreal Cognitive Assessment (0–30, lower = worse cognition)9fes_iFalls Efficacy Scale–International (16–64, higher = more fear of falling)10pdq_8Parkinson’s Disease Questionnaire–8 (0–32, higher = poorer QoL)👩‍⚕️ Study ProtocolParticipants: 22 people with PDTasks performed: 7 mobility tasks (see taskID) designed to elicit FoGAnnotations: FoG presence and severity labeled by experts via video analysisClinical scales: Hoehn & Yahr, MDS-UPDRS III, FoG-Q, MoCA, FES-I, PDQ-8📊 Example Usageimport pandas as pd# Load datadf_sensors = pd.read_csv("fog_star.csv")df_clinical = pd.read_csv("clinical_data.csv")# Merge datasetsdf = df_sensors.merge(df_clinical, on="subjectID")# Example: Average FoG severity per subjectprint(df.groupby("subjectID")["fog_severity"].mean())# Example: Correlation between UPDRS-III score and FoG proportionfog_ratio = df.groupby("subjectID")["fog"].mean().reset_index()merged = fog_ratio.merge(df_clinical, on="subjectID")print(merged[["subjectID","fog","updrs_iii"]])📈 Provided ScriptsData exploration: distributions of FoG vs non-FoG, FoG severity, time per task/activity/subjectFoG event analysis: duration distributions, severity-based comparisonsSignal visualization: example raw traces with shaded FoG episodesClinical correlation: merge sensor_data with clinical_data🔖 CitationIf you use this dataset, please cite:Borzi, L. et al. Freezing of Gait Wearable Sensor and Clinical Dataset. Zenodo, 2025. DOI: 10.5281/zenodo.16989602Borzi, L. et al.. Freezing of gait detection: The effect of sensor type, position, activities, datasets, and machine learning model. Journal of Parkinson’s Disease, 15(1), 163-181.Demrozi, F. et al. "A low-cost wireless body area network for human activity recognition in healthy life and medical applications." IEEE Transactions on Emerging Topics in Computing 11, no. 4 (2023): 839-850.⚖️ LicenseThis dataset is licensed under CC-BY 4.0. You are free to share and adapt the data with proper attribution.