Milla Juutinen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Milla Juutinen has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Antti Vehkaoja
Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
3 shared publications Jari Ruokolainen
Faculty of Business and Management, Tampere University; Unit of Neurology, Satasairaala Central Hospital, Wellbeing Services County of Satakunta; School of Technology and Innovations, University of Vaasa
2 shared publicationsJuha Puustinen
Unit of Neurology, Satasairaala Central Hospital, Wellbeing Services County of Satakunta
2 shared publications- Alain Beuchée
Neonatology, Rennes University Hospital, Rennes, France
1 shared publication - Alpo Värri
Faculty of Medicine and Health Technology, Tampere University, Tampere
1 shared publication - Antti Kallonen
Tampere University
1 shared publication
Latest Publications
- Open Access
- 5 May 2025
- Published by Finnish Journal of eHealth and eWelfare in Finnish Journal of eHealth and eWelfare
- Vol. 17 (2) , 200–213
Walking detection for Parkinson’s disease patients and healthy control subjects measured with a smartphone accelerometer using mean amplitude deviation algorithm
Parkinson's disease is a neurodegenerative disorder that affects mobility, leading to a decline in the patient's quality of life. Analyzing gait for these patients aims to improve the mobility of the Parkinson’s disease patients. The goal of this study was to validate mean amplitude deviation for detecting gait in Parkinson’s disease patients and healthy controls. This method is robust and orientation-independent and has accurate results on physical activity detection for different study populations. The novelty of this study is to use and evaluate a previously validated method with Parkinson’s disease patients instead of healthy young subjects as in earlier studies. We utilized inertial measurement unit data measured using smartphones from pre-existing datasets with pre-defined and labeled activities and free-living data containing continuously collected over three consecutive days. One dataset included 30 healthy adults, and the other two included in total of 62 and 68 Parkinson’s disease patients and 40 and 39 healthy controls, respectively. The sensitivity of the algorithm in a controlled measurement setting was 100% and 98.7% for healthy adults and a combined dataset of Parkinson’s disease patients and control subjects, respectively. Correspondingly, the specificity was 74.9% and 81.6%. Visual inspection of the free-living data showed that the algorithm provided durations and timings of walking activities, and walking took place during the daytime as anticipated for subjects with a typical daily rhythm. Median walking times were under ten minutes per hour. The results reached the same performance range as earlier studies with an orientation-independent approach, justifying the feasibility of this method. Therefore, this study validated the use of mean amplitude deviation for walking detection in Parkinson’s disease patients and healthy adults. Future research will utilize the detected walking segments in analyzing the motor symptoms of the disease aiming to improve patient well-being through identifying the needs for additional healthcare interventions.
- 5 May 2025
- Published by Finnish Journal of eHealth and eWelfare in Finnish Journal of eHealth and eWelfare
- Vol. 17 (2) , 200–213
Open AccessWalking detection for Parkinson’s disease patients and healthy control subjects measured with a smartphone accelerometer using mean amplitude deviation algorithm
Parkinson's disease is a neurodegenerative disorder that affects mobility, leading to a decline in the patient's quality of life. Analyzing gait for these patients aims to improve the mobility of the Parkinson’s disease patients. The goal of this study was to validate mean amplitude deviation for detecting gait in Parkinson’s disease patients and healthy controls. This method is robust and orientation-independent and has accurate results on physical activity detection for different study populations. The novelty of this study is to use and evaluate a previously validated method with Parkinson’s disease patients instead of healthy young subjects as in earlier studies. We utilized inertial measurement unit data measured using smartphones from pre-existing datasets with pre-defined and labeled activities and free-living data containing continuously collected over three consecutive days. One dataset included 30 healthy adults, and the other two included in total of 62 and 68 Parkinson’s disease patients and 40 and 39 healthy controls, respectively. The sensitivity of the algorithm in a controlled measurement setting was 100% and 98.7% for healthy adults and a combined dataset of Parkinson’s disease patients and control subjects, respectively. Correspondingly, the specificity was 74.9% and 81.6%. Visual inspection of the free-living data showed that the algorithm provided durations and timings of walking activities, and walking took place during the daytime as anticipated for subjects with a typical daily rhythm. Median walking times were under ten minutes per hour. The results reached the same performance range as earlier studies with an orientation-independent approach, justifying the feasibility of this method. Therefore, this study validated the use of mean amplitude deviation for walking detection in Parkinson’s disease patients and healthy adults. Future research will utilize the detected walking segments in analyzing the motor symptoms of the disease aiming to improve patient well-being through identifying the needs for additional healthcare interventions.
- Open Access
- 4 February 2024
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 184, 105366
Early detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study
- 4 February 2024
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 184, 105366
Open AccessEarly detection of late-onset neonatal sepsis from noninvasive biosignals using deep learning: A multicenter prospective development and validation study
- Open Access
- 23 July 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (7) , e0236258
Parkinson’s disease detection from 20-step walking tests using inertial sensors of a smartphone: Machine learning approach based on an observational case-control study
Parkinson’s disease (PD) is a neurodegenerative disease inducing dystrophy of the motor system. Automatic movement analysis systems have potential in improving patient care by enabling personalized and more accurate adjust of treatment. These systems utilize machine learning to classify the movement properties based on the features derived from the signals. Smartphones can provide an inexpensive measurement platform with their built-in sensors for movement assessment. This study compared three feature selection and nine classification methods for identifying PD patients from control subjects based on accelerometer and gyroscope signals measured with a smartphone during a 20-step walking test. Minimum Redundancy Maximum Relevance (mRMR) and sequential feature selection with both forward (SFS) and backward (SBS) propagation directions were used in this study. The number of selected features was narrowed down from 201 to 4–15 features by applying SFS and mRMR methods. From the methods compared in this study, the highest accuracy for individual steps was achieved with SFS (7 features) and Naive Bayes classifier (accuracy 75.3%), and the second highest accuracy with SFS (4 features) and k Nearest neighbours (accuracy 75.1%). Leave-one-subject-out cross-validation was used in the analysis. For the overall classification of each subject, which was based on the majority vote of the classified steps, k Nearest Neighbors provided the most accurate result with an accuracy of 84.5% and an error rate of 15.5%. This study shows the differences in feature selection methods and classifiers and provides generalizations for optimizing methodologies for smartphone-based monitoring of PD patients. The results are promising for further developing the analysis system for longer measurements carried out in free-living conditions.
- 23 July 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (7) , e0236258
Open AccessParkinson’s disease detection from 20-step walking tests using inertial sensors of a smartphone: Machine learning approach based on an observational case-control study
Parkinson’s disease (PD) is a neurodegenerative disease inducing dystrophy of the motor system. Automatic movement analysis systems have potential in improving patient care by enabling personalized and more accurate adjust of treatment. These systems utilize machine learning to classify the movement properties based on the features derived from the signals. Smartphones can provide an inexpensive measurement platform with their built-in sensors for movement assessment. This study compared three feature selection and nine classification methods for identifying PD patients from control subjects based on accelerometer and gyroscope signals measured with a smartphone during a 20-step walking test. Minimum Redundancy Maximum Relevance (mRMR) and sequential feature selection with both forward (SFS) and backward (SBS) propagation directions were used in this study. The number of selected features was narrowed down from 201 to 4–15 features by applying SFS and mRMR methods. From the methods compared in this study, the highest accuracy for individual steps was achieved with SFS (7 features) and Naive Bayes classifier (accuracy 75.3%), and the second highest accuracy with SFS (4 features) and k Nearest neighbours (accuracy 75.1%). Leave-one-subject-out cross-validation was used in the analysis. For the overall classification of each subject, which was based on the majority vote of the classified steps, k Nearest Neighbors provided the most accurate result with an accuracy of 84.5% and an error rate of 15.5%. This study shows the differences in feature selection methods and classifiers and provides generalizations for optimizing methodologies for smartphone-based monitoring of PD patients. The results are promising for further developing the analysis system for longer measurements carried out in free-living conditions.
- Open Access
- 13 November 2018
- Published by JMIR Publications Inc. in JMIR Preprints
Identification of Motor Symptoms Related to Parkinson Disease Using Motion-Tracking Sensors at Home (KÄVELI): Protocol for an Observational Case-Control Study (Preprint)
BACKGROUND Clinical characterization of motion in patients with Parkinson disease (PD) is challenging: symptom progression, suitability of medication, and level of independence in the home environment can vary across time and patients. Appointments at the neurological outpatient clinic provide a limited understanding of the overall situation. In order to follow up these variations, longer-term measurements performed outside of the clinic setting could help optimize and personalize therapies. Several wearable sensors have been used to estimate the severity of symptoms in PD; however, longitudinal recordings, even for a short duration of a few days, are rare. Home recordings have the potential benefit of providing a more thorough and objective follow-up of the disease while providing more information about the possible need to change medications or consider invasive treatments. OBJECTIVE The primary objective of this study is to collect a dataset for developing methods to detect PD-related symptoms that are visible in walking patterns at home. The movement data are collected continuously and remotely at home during the normal lives of patients with PD as well as controls. The secondary objective is to use the dataset to study whether the registered medication intakes can be identified from the collected movement data by looking for and analyzing short-term changes in walking patterns. METHODS This paper described the protocol for an observational case-control study that measures activity using three different devices: (1) a smartphone with a built-in accelerometer, gyroscope, and phone orientation sensor, (2) a Movesense smart sensor to measure movement data from the wrist, and (3) a Forciot smart insole to measure the forces applied on the feet. The measurements are first collected during the appointment at the clinic conducted by a trained clinical physiotherapist. Subsequently, the subjects wear the smartphone at home for 3 consecutive days. Wrist and insole sensors are not used in the home recordings. RESULTS Data collection began in March 2018. Subject recruitment and data collection will continue in spring 2019. The intended sample size was 150 subjects. In 2018, we collected a sample of 103 subjects, 66 of whom were diagnosed with PD. CONCLUSIONS This study aims to produce an extensive movement-sensor dataset recorded from patients with PD in various phases of the disease as well as from a group of control subjects for effective and impactful comparison studies. The study also aims to develop data analysis methods to monitor PD symptoms and the effects of medication intake during normal life and outside of the clinic setting. Further applications of these methods may include using them as tools for health care professionals to monitor PD remotely and applying them to other movement disorders. CLINICALTRIAL ClinicalTrials.gov NCT03366558; https://clinicaltrials.gov/ct2/show/NCT03366558 INTERNATIONAL REGISTERED REPOR DERR1-10.2196/12808
- 13 November 2018
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessIdentification of Motor Symptoms Related to Parkinson Disease Using Motion-Tracking Sensors at Home (KÄVELI): Protocol for an Observational Case-Control Study (Preprint)
BACKGROUND Clinical characterization of motion in patients with Parkinson disease (PD) is challenging: symptom progression, suitability of medication, and level of independence in the home environment can vary across time and patients. Appointments at the neurological outpatient clinic provide a limited understanding of the overall situation. In order to follow up these variations, longer-term measurements performed outside of the clinic setting could help optimize and personalize therapies. Several wearable sensors have been used to estimate the severity of symptoms in PD; however, longitudinal recordings, even for a short duration of a few days, are rare. Home recordings have the potential benefit of providing a more thorough and objective follow-up of the disease while providing more information about the possible need to change medications or consider invasive treatments. OBJECTIVE The primary objective of this study is to collect a dataset for developing methods to detect PD-related symptoms that are visible in walking patterns at home. The movement data are collected continuously and remotely at home during the normal lives of patients with PD as well as controls. The secondary objective is to use the dataset to study whether the registered medication intakes can be identified from the collected movement data by looking for and analyzing short-term changes in walking patterns. METHODS This paper described the protocol for an observational case-control study that measures activity using three different devices: (1) a smartphone with a built-in accelerometer, gyroscope, and phone orientation sensor, (2) a Movesense smart sensor to measure movement data from the wrist, and (3) a Forciot smart insole to measure the forces applied on the feet. The measurements are first collected during the appointment at the clinic conducted by a trained clinical physiotherapist. Subsequently, the subjects wear the smartphone at home for 3 consecutive days. Wrist and insole sensors are not used in the home recordings. RESULTS Data collection began in March 2018. Subject recruitment and data collection will continue in spring 2019. The intended sample size was 150 subjects. In 2018, we collected a sample of 103 subjects, 66 of whom were diagnosed with PD. CONCLUSIONS This study aims to produce an extensive movement-sensor dataset recorded from patients with PD in various phases of the disease as well as from a group of control subjects for effective and impactful comparison studies. The study also aims to develop data analysis methods to monitor PD symptoms and the effects of medication intake during normal life and outside of the clinic setting. Further applications of these methods may include using them as tools for health care professionals to monitor PD remotely and applying them to other movement disorders. CLINICALTRIAL ClinicalTrials.gov NCT03366558; https://clinicaltrials.gov/ct2/show/NCT03366558 INTERNATIONAL REGISTERED REPOR DERR1-10.2196/12808