What is STAT-ON?
STAT-ON is a wearable medical device designed for the continuous and objective monitoring of motor symptoms in patients with Parkinson’s disease during their daily daily activities [1].
The system is based on an advanced inertial sensing system and previously trained artificial intelligence algorithms capable of automatically detecting and quantifying relevant motor symptoms in real time. The main objective is to provide neurologists with objective information in order to optimize clinical decision-making and improve the patient’s therapeutic management.
STAT-ON is worn on the left side of the patient’s waist, close to the body’s center of mass, allowing it to capture highly representative information about overall body movement. The device monitors motor activity under real-life conditions, outside the hospital environment, where motor fluctuations and complications that are difficult to observe during a conventional consultation commonly occur.
The main clinical parameters evaluated include: • Bradykinesia [2,3]
• ON/OFF motor fluctuations [4,5]
• Peak-dose choreic dyskinesias [6,7]
• Freezing of Gait (FoG) [8–10]
• Gait parameters [11–13]
• Physical activity, posture, and postural transitions [14,15]
• Falls [16,17]
Clinical Utility
In clinical practice, STAT-ON provides objective and quantifiable information to support multiple clinical decisions related to advanced Parkinson’s disease. The main clinical applications include:
Key advantages in a clinical visit
In addition to the clinical utility described above, the STAT-ON report:
• Helps reduce patient stress and anxiety when explaining their symptoms [18].
• Improves communication between clinicians and patients and increases awareness of symptom onset [19,20].
• Reduces the time required to make complex decisions [21]. STAT-ON can also be used for research purposes and to objectively evaluate treatment efficacy. The company offers a licensed service that provides support through tools and software to obtain results for research and scientific publications.
Technology and algorithms
STAT-ON incorporates advanced machine learning algorithms specifically developed for Parkinson’s disease.
The main technological features include:
• Real-time algorithms executed directly on the device.
• Local processing without the need to continuously send data to the cloud.
• Pseudonymized data compliant with GDPR regulations.
• The company does not have access to the data; only the clinician does.
• Monitoring through a single wearable sensor.
• Detection of axial symptoms and gait disturbances.
• A system designed for routine clinical use.
• High patient adherence thanks to its simplicity.
The STAT-ON algorithms were developed as part of the European REMPARK project, in which the largest and most rigorous home-monitoring database in Parkinson’s disease was created, with patients monitored in real-life conditions using video recordings, clinical diaries, and periodic phone calls to ensure accurate data labeling and classifier validation [22].
Between 2009 and 2017, the Universitat Politècnica de Catalunya developed one of the largest real-world databases for Parkinson’s disease monitoring research using wearable devices, including 574 participants, of whom 243 were patients with Parkinson’s disease. A total of 112 patients were used for algorithm training using synchronized video recordings, clinical diaries, and UPDRS evaluations, mainly in home environments, while 131 patients participated in clinical validation studies. In addition, 331 participants without Parkinson’s disease were included to improve specificity and to develop algorithms for dyskinesia, freezing of gait (FoG), falls, and postural disturbances. The intellectual property is exclusively owned by Sense4Care, and the principal investigators are part of the company both operationally and within its shareholder structure.
Clinical validation and scientific backup
STAT-ON has extensive clinical and technological validation developed through multiple national and international studies (>80 indexed publications).
The technology has been evaluated using rigorous clinical standards, including:
• Comparison against motor diaries and periodic patient phone calls.
• Correlations with clinical scales such as MDS-UPDRS.
• Validation in fluctuating patients and candidates for advanced therapies.
• Feasibility studies in routine clinical practice.
• Cost-benefit and telemedicine studies.
Among the most relevant scientific publications are:
History and Technological Development of STAT-ON
• Frontiers in Neurology – History of STAT-ON and its validation [1]
• REMPARK project book [22]
• PARK-IT project book (Industrialization and Certification of STAT-ON) [23]
Clinical Studies and Validation
• Feasibility of using STAT-ON in clinical practice [24]
• Detection of advanced Parkinson’s disease and comparison with clinical questionnaires [21]
• Correlation with UPDRS clinical scales [3]
• Validation against clinical diaries and periodic phone calls as the gold standard [5]
External Validation in Clinical Practice
• Correlations with UPDRS and PDQ-39 [25]
• Use in real-world clinical practice, demonstrating non-inferiority compared to diaries [26]
• Study on Freezing of Gait and dyskinesias [10]
Cost-Benefit and Telemedicine Studies
• Cost-benefit study conducted across five European countries [27]
• Feasibility of STAT-ON in telemedicine [28]
• Publication on telemedicine and remote monitoring [29]
International presence and clinical use
STAT-ON is currently used in multiple hospitals and specialized movement disorder centers across different countries.
The technology has been implemented in clinical settings throughout Europe and other international markets, forming part of objective monitoring and therapeutic optimization programs for patients with Parkinson’s disease.
The device is commercially available in more than 20 countries and has been used in:
• Public and private hospitals
• Movement disorder units
• DBS and advanced therapy programs
• Multicenter clinical studies
• Telemedicine and remote follow-up projects
The product carries CE marking as a Class IIa medical device under MDR 2017/745. In addition, it is registered with country-specific certifications in Israel, Kuwait, Australia, and Argentina. It is also used in the United States and other countries for clinical studies, evaluating treatment efficacy, and assessing patient symptoms under different conditions.
Why STAT-ON? Competitive advantages
STAT-ON was designed with the goal of bringing objective monitoring of Parkinson’s disease into real clinical practice, combining technological precision, scientific validation, and high usability for the patient. Unlike other systems focused solely on comfort or large-scale data collection, STAT-ON seeks an optimal balance between clinical accuracy, ease of use, and real-world applicability. This design philosophy has enabled the development of a technology capable of continuously and objectively monitoring relevant motor symptoms in home environments while maintaining high patient adherence.
Balance Between Number of Sensors and Precision
Although multiple sensors would theoretically be required to individually monitor all parts of the human body, this approach often causes patient discomfort, reduces usability, and decreases adherence to the technology under real-life conditions.
For this reason, STAT-ON uses a single sensor placed near the body’s center of mass, enabling the characterization of the maximum number of symptoms with optimal precision while maintaining a comfortable and simple user experience for the patient.
In addition, the system is particularly focused on dopamine-sensitive symptoms, allowing accurate characterization of the patient’s motor response when therapy is effective and detecting when the therapeutic effect decreases or disappears.
Advanced Machine Learning
Without a doubt, one of STAT-ON’s main competitive advantages is the scientific and methodological rigor applied in the development of its algorithms. This includes both the construction of high-quality clinical databases and the exhaustive validation of the algorithms through scientific publications in both technological and medical fields.
STAT-ON was developed using the largest and most rigorous real-world database for monitoring patients with Parkinson’s disease. All algorithms were trained using high-quality clinical labels and machine learning methodologies specifically optimized for each motor symptom. In addition to technical validation of algorithmic accuracy in specialized Computer Science journals, the technology has also been evaluated in medical journals and clinical studies focused on its utility and applicability in real clinical practice.
Placement
A wrist-worn sensor is the most comfortable option for patients. However, the scientific literature has shown that characterizing movement from the wrist presents several problems [30–32]. The first is the high randomness of hand movements, which results in a high rate of false positives. The second issue is the difficulty of characterizing axial symptoms, gait disturbances, and choreic dyskinesias from the wrist, leading to many false negatives. Maximizing patient comfort therefore compromises algorithm accuracy.
A waist-mounted sensor is located near the human body’s center of mass, from where almost all dopamine-sensitive symptoms can be characterized, with the exception of hand tremor. The sensor has demonstrated strong usability results, achieving patient satisfaction levels comparable to those of wrist-worn sensors [33,34].
References
1. Rodríguez-Martín, D.; Cabestany, J.; Pérez-López, C.; Pie, M.; Calvet, J.; Samà, A.; Capra, C.; Català, A.; Rodríguez-Molinero, A. A New Paradigm in Parkinson’s Disease Evaluation With Wearable Medical Devices: A Review of STAT-ONTM. Front. Neurol. 2022, 13, doi:10.3389/fneur.2022.912343.
2. Samà, A.; Pérez-López, C.; Rodríguez-Martín, D.; Català, A.; Moreno-Aróstegui, J.M.; Cabestany, J.; de Mingo, E.; Rodríguez-Molinero, A. Estimating Bradykinesia Severity in Parkinson’s Disease by Analysing Gait through a Waist-Worn Sensor. Comput. Biol. Med. 2017, 84, doi:10.1016/j.compbiomed.2017.03.020.
3. Rodríguez-Molinero, A.; Samà, A.; Pérez-López, C.; Rodríguez-Martín, D.; Alcaine, S.; Mestre, B.; Quispe, P.; Giuliani, B.; Vainstein, G.; Browne, P.; et al. Analysis of Correlation between an Accelerometer-Based Algorithm for Detecting Parkinsonian Gait and UPDRS Subscales. Front. Neurol. 2017, 8, 3–8, doi:10.3389/fneur.2017.00431.
4. Pérez-López, C.; Samà, A.; Rodríguez-Martín, D.; Català, A.; Cabestany, J.; Moreno-Arostegui, J.; de Mingo, E.; Rodríguez-Molinero, A. Assessing Motor Fluctuations in Parkinson’s Disease Patients Based on a Single Inertial Sensor. Sensors 2016, 16, 2132, doi:10.3390/s16122132.
5. Bayés, À.; Samá, A.; Prats, A.; Pérez-López, C.; Crespo-Maraver, M.; Moreno, J.M.; Alcaine, S.; Rodriguez-Molinero, A.; Mestre, B.; Quispe, P.; et al. A “HOLTER” for Parkinson’s Disease: Validation of the Ability to Detect on-off States Using the REMPARK System. Gait Posture 2018, 59, 1–6, doi:10.1016/j.gaitpost.2017.09.031.
6. Pérez-López, C.; Samà, A.; Rodríguez-Martín, D.; Moreno-Aróstegui, J.M.; Cabestany, J.; Bayes, A.; Mestre, B.; Alcaine, S.; Quispe, P.; Laighin, G.T.; et al. Dopaminergic-Induced Dyskinesia Assessment Based on a Single Belt-Worn Accelerometer. Artif. Intell. Med. 2016, 67, doi:10.1016/j.artmed.2016.01.001.
7. Rodríguez-Molinero, A.; Pérez-López, C.; Samà, A.; Rodríguez-Martín, D.; Alcaine, S.; Mestre, B.; Quispe, P.; Giuliani, B.; Vainstein, G.; Browne, P.; et al. Estimating Dyskinesia Severity in Parkinson’s Disease by Using a Waist-Worn Sensor: Concurrent Validity Study. Sci. Rep. 2019, 9, 13434, doi:10.1038/s41598-019-49798-3.
8. Rodríguez-Martín, D.; Samà, A.; Pérez-López, C.; Català, A.; Arostegui, J.M.M.; Cabestany, J.; Bayés, A.; Alcaine, S.; Mestre, B.; Prats, A.; et al. Home Detection of Freezing of Gait Using Support Vector Machines through a Single Waist-Worn Triaxial Accelerometer. PLoS One 2017, 12, doi:10.1371/journal.pone.0171764.
9. Samà, A.; Rodríguez-Martín, D.; Pérez-López, C.; Català, A.; Alcaine, S.; Mestre, B.; Prats, A.; Crespo, M.C.; Bayés, À. Determining the Optimal Features in Freezing of Gait Detection through a Single Waist Accelerometer in Home Environments. Pattern Recognit. Lett. 2018, 105, 135–143, doi:10.1016/j.patrec.2017.05.009.
10. Zampogna, A.; Borzì, L.; Rinaldi, D.; Artusi, C.A.; Imbalzano, G.; Patera, M.; Lopiano, L.; Pontieri, F.; Olmo, G.; Suppa, A. Unveiling the Unpredictable in Parkinson’s Disease: Sensor-Based Monitoring of Dyskinesias and Freezing of Gait in Daily Life. Bioengineering 2024, 11, 440, doi:10.3390/bioengineering11050440.
11. Sayeed, T.; Samà, A.; Català, A.; Rodríguez-Molinero, A.; Cabestany, J. Adapted Step Length Estimators for Patients with Parkinson’s Disease Using a Lateral Belt Worn Accelerometer. Technology and Health Care 2015, 23, 179–194, doi:10.3233/THC-140882.
12. Sama, A.; Perez-Lopez, C.; Romagosa, J.; Rodriguez-Martin, D.; Catala, A.; Cabestany, J.; Perez-Martinez, D.A.; Rodriguez-Molinero, A. Dyskinesia and Motor State Detection in Parkinson’s Disease Patients with a Single Movement Sensor. In Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society; IEEE, August 2012; Vol. 2012, pp. 1194–1197.
13. Samà, A.; Angulo, C.; Pardo, D.; Català, A.; Cabestany, J. Analyzing Human Gait and Posture by Combining Feature Selection and Kernel Methods. Neurocomputing 2011, 74, 2665–2674, doi:10.1016/j.neucom.2011.03.028.
14. Rodríguez-Martín, D.; Samà, A.; Pérez-López, C.; Cabestany, J.; Català, A.; Rodríguez-Molinero, A. Posture Transition Identification on PD Patients through a SVM-Based Technique and a Single Waist-Worn Accelerometer. Neurocomputing 2015, 164, 144–153, doi:10.1016/j.neucom.2014.09.084.
15. Rodriguez-Martin, D.; Samà, A.; Perez-Lopez, C.; Català, A.; Cabestany, J.; Rodriguez-Molinero, A. SVM-Based Posture Identification with a Single Waist-Located Triaxial Accelerometer. Expert Syst. Appl. 2013, 40, 7203–7211, doi:10.1016/j.eswa.2013.07.028.
16. FATE-Fall Detector for the Elder. FP7-CIP-ICT-PSP-2011-5-297178. 2011-2014;
17. Cabestany, J.; Moreno, J.M.; Perez, C.; Sama, A.; Catala, A. FATE: One Step Towards an Automatic Aging People Fall Detection Service. In Proceedings of the 20th International Conference on Mixed Design of Integrated Circuits and Systems; 2013.
18. Carrasco, L.; Álvarez, D.; Pérez, M.; Capra, C.; Rodriguez-Martin, D.; Mata, M.; Kurtis, M.; Borrué, C.; López-Manzanares, L. A Pilot Study to Prepare Patients for Doctor’s Consultation Based on the NMS-Quest and a Wearable Medical Device. In Proceedings of the International Congress of Parkinson’s Disease and Movement Disorders 2023; 38 (suppl. 1); Copenhagen, 2023.
19. Caballol, N.; Ávila, M.A.; PLanas-Ballvé, A.; Peral, A.; Hernández-Vara, J.; Belmonte, S.; Enríquez, S.; Sánchez, S.; Cerdán, D.; Cabo, I.; et al. Improving Awareness of Motor Fluctuations in Parkinson’s Disease: An Educational Patient Support Program Using a Waist-Worn Device. In Proceedings of the Movement Disorders; Philadelphia, 2024.
20. Caballol, N.; Perez-Soriano, A.; Planas-Ballvé, A.; Ávila, A.; Quispe, P.; Bayes, À. Improving the Patient Self-Awareness of the First Motor Fluctuations in Early Parkinson’s Disease with a Wearable Sensor. In Proceedings of the Mov Disord. 2022; Movement Disorders Society: Madrid, 2022.
21. Cabo-Lopez, I.; Puy-Nuñez, A.; Redondo-Rafales, N.; Teixeira Baltazar, S.; Calderón-Cruz, B. Holter STAT-ONTM against Other Tools for Detecting MF in Advanced Parkinson’s Disease: An Observational Study. Front. Neurol. 2023, 14, doi:10.3389/fneur.2023.1249385.
22. Cabestany, J.; Bayés, À. Parkinson’s Disease Management through ICT: The REMPARK Approach; River Publishers, 2017; ISBN 9788793519466.
23. Cabestany, J.; Bayés, A. A Holter for Parkinson’s Disease Motor Symptoms: STAT-OnTM; River Publishers: New York, 2023; ISBN 9781032632865.
24. Caballol, N.; Bayés, À.; Prats, A.; Martín-Baranera, M.; Quispe, P. Feasibility of a Wearable Inertial Sensor to Assess Motor Complications and Treatment in Parkinson’s Disease. PLoS One 2023, 18, e0279910, doi:10.1371/journal.pone.0279910.
25. Pérez-López, C.; Caballol, N.; Buongiorno, M.; Ávila Rivera, M.A.; Ariztegui, N.L.; López-Manzanares, L.; Hernández-Vara, J.; Rusiñol, À.B.; Carreró, A.G.; Saúco, M.Á.; et al. Comparison of Clinical Measures of Motor Function with a Holter Monitor in Parkinson’s Disease. Clin. Park. Relat. Disord. 2025, 12, 100325, doi:10.1016/j.prdoa.2025.100325.
26. Rodríguez-Molinero, A.; Pérez-López, C.; Caballol, N.; Buongiorno, M.; Ávila Rivera, M.A.; López Ariztegui, N.; López-Manzanares, L.; Hernández-Vara, J.; Bayes-Rusiñol, À.; Gironell Carreró, A.; et al. Parkinson’s Disease Medication Adjustments Based on Wearable Device Information Compared to Other Methods: Randomized Clinical Trial. NPJ Parkinsons Dis. 2025, 11, 249, doi:10.1038/s41531-025-00977-2.
27. Rodriguez-Martin, D.; Català, A.; Cabestany, J. Improving Parkinson’s Disease Management through Wearable Technology: A Cost-Benefit Perspective. PLoS One 2025, 20, e0334413, doi:10.1371/journal.pone.0334413.
28. Del Pino, R.; de Echevarría, A.O.; Díez-Cirarda, M.; Ustarroz-Aguirre, I.; Caprino, M.; Liu, J.; Gand, K.; Schlieter, H.; Gabilondo, I.; Gómez-Esteban, J.C. Virtual Coach and Telerehabilitation for Parkinson´s Disease Patients: VCare System. J. Public Health (Bangkok). 2023, doi:10.1007/s10389-023-02082-1.
29. Cubo, E.; Rohani, M.; Eissazade, N.; Garcia‐Bustillo, Á.; Ramírez‐Sanz, J.M.; Garrido‐Labrador, J.L.; Olivares‐Gil, A.; Valiñas‐Sieiro Rn, F.; Allende‐Río Rn, M.; Gonzalez‐Santos, J.; et al. Cost‐utility Analysis of a Coadjutant Telemedicine Intervention for Fall Prevention in Parkinson’s Disease. Eur. J. Neurol. 2025, 32, doi:10.1111/ene.16561.
30. Shcherbina, A.; Mattsson, C.; Waggott, D.; Salisbury, H.; Christle, J.; Hastie, T.; Wheeler, M.; Ashley, E. Accuracy in Wrist-Worn, Sensor-Based Measurements of Heart Rate and Energy Expenditure in a Diverse Cohort. J. Pers. Med. 2017, 7, 3, doi:10.3390/jpm7020003.
31. Kondama Reddy, R.; Pooni, R.; Zaharieva, D.P.; Senf, B.; El Youssef, J.; Dassau, E.; Doyle, F.J.; Clements, M.A.; Rickels, M.R.; Patton, S.R.; et al. Accuracy of Wrist-Worn Activity Monitors during Common Daily Physical Activities and Types of Structured Exercise: Evaluation Study. JMIR Mhealth Uhealth 2018, 6, doi:10.2196/10338.
32. Gjoreski, M.; Gjoreski, H.; Luštrek, M.; Gams, M. How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls? Sensors 2016, 16, 800, doi:10.3390/s16060800.
33. Grahn, F. Evaluation of Two Commercial Sensor Systems for Monitoring Parkinsonism and Their Possible Influence on Management of Parkinson’s Disease. Degree Project in Medicine, Institute of Neuroscience and Physiology Sahlgrenska Academy University of Gothenburg: Gothenburg, 2022.
34. Caballol, N.; Prats, A.; Quispe, P.; Ranchal, M.; Alcaine, S.; Fondevilla, F.; Bayes, A. Early Detection of Parkinson‘s Disease Motor Fluctuations with a Wearable Inertial Sensor. In Proceedings of the Movement Disorders; 2020; p. 35 (suppl. 1).