Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring
Aggression in children is highly prevalent and can have devastating consequences, yet there is currently no objective method to track its frequency in daily life. This study aims to investigate the use of wearable-sensor-derived physical activity data and machine learning to objectively identify phy...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/10/4949 |
| _version_ | 1797598273769308160 |
|---|---|
| author | Catherine Park Mohammad Dehghan Rouzi Md Moin Uddin Atique M. G. Finco Ram Kinker Mishra Griselda Barba-Villalobos Emily Crossman Chima Amushie Jacqueline Nguyen Chadi Calarge Bijan Najafi |
| author_facet | Catherine Park Mohammad Dehghan Rouzi Md Moin Uddin Atique M. G. Finco Ram Kinker Mishra Griselda Barba-Villalobos Emily Crossman Chima Amushie Jacqueline Nguyen Chadi Calarge Bijan Najafi |
| author_sort | Catherine Park |
| collection | DOAJ |
| description | Aggression in children is highly prevalent and can have devastating consequences, yet there is currently no objective method to track its frequency in daily life. This study aims to investigate the use of wearable-sensor-derived physical activity data and machine learning to objectively identify physical-aggressive incidents in children. Participants (n = 39) aged 7 to 16 years, with and without ADHD, wore a waist-worn activity monitor (ActiGraph, GT3X+) for up to one week, three times over 12 months, while demographic, anthropometric, and clinical data were collected. Machine learning techniques, specifically random forest, were used to analyze patterns that identify physical-aggressive incident with 1-min time resolution. A total of 119 aggression episodes, lasting 7.3 ± 13.1 min for a total of 872 1-min epochs including 132 physical aggression epochs, were collected. The model achieved high precision (80.2%), accuracy (82.0%), recall (85.0%), F1 score (82.4%), and area under the curve (89.3%) to distinguish physical aggression epochs. The sensor-derived feature of vector magnitude (faster triaxial acceleration) was the second contributing feature in the model, and significantly distinguished aggression and non-aggression epochs. If validated in larger samples, this model could provide a practical and efficient solution for remotely detecting and managing aggressive incidents in children. |
| first_indexed | 2024-03-11T03:20:04Z |
| format | Article |
| id | doaj.art-0c62f245d6ba4d31ab7f7898dc2cbbe8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T03:20:04Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0c62f245d6ba4d31ab7f7898dc2cbbe82023-11-18T03:15:01ZengMDPI AGSensors1424-82202023-05-012310494910.3390/s23104949Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity MonitoringCatherine Park0Mohammad Dehghan Rouzi1Md Moin Uddin Atique2M. G. Finco3Ram Kinker Mishra4Griselda Barba-Villalobos5Emily Crossman6Chima Amushie7Jacqueline Nguyen8Chadi Calarge9Bijan Najafi10Interdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAInterdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAInterdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAInterdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAInterdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAMenninger Department of Psychiatry and Behavioral Sciences and Department of Pediatrics, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX 77030, USAMenninger Department of Psychiatry and Behavioral Sciences and Department of Pediatrics, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX 77030, USAMenninger Department of Psychiatry and Behavioral Sciences and Department of Pediatrics, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX 77030, USAMenninger Department of Psychiatry and Behavioral Sciences and Department of Pediatrics, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX 77030, USAMenninger Department of Psychiatry and Behavioral Sciences and Department of Pediatrics, Baylor College of Medicine, Texas Children’s Hospital, Houston, TX 77030, USAInterdisciplinary Consortium on Advanced Motion Performance (iCAMP), Michael E. DeBakey Department of Surgery, Baylor College of Medicine, Houston, TX 77030, USAAggression in children is highly prevalent and can have devastating consequences, yet there is currently no objective method to track its frequency in daily life. This study aims to investigate the use of wearable-sensor-derived physical activity data and machine learning to objectively identify physical-aggressive incidents in children. Participants (n = 39) aged 7 to 16 years, with and without ADHD, wore a waist-worn activity monitor (ActiGraph, GT3X+) for up to one week, three times over 12 months, while demographic, anthropometric, and clinical data were collected. Machine learning techniques, specifically random forest, were used to analyze patterns that identify physical-aggressive incident with 1-min time resolution. A total of 119 aggression episodes, lasting 7.3 ± 13.1 min for a total of 872 1-min epochs including 132 physical aggression epochs, were collected. The model achieved high precision (80.2%), accuracy (82.0%), recall (85.0%), F1 score (82.4%), and area under the curve (89.3%) to distinguish physical aggression epochs. The sensor-derived feature of vector magnitude (faster triaxial acceleration) was the second contributing feature in the model, and significantly distinguished aggression and non-aggression epochs. If validated in larger samples, this model could provide a practical and efficient solution for remotely detecting and managing aggressive incidents in children.https://www.mdpi.com/1424-8220/23/10/4949pediatricsaggressionwearablesremote patient monitoringmachine learning |
| spellingShingle | Catherine Park Mohammad Dehghan Rouzi Md Moin Uddin Atique M. G. Finco Ram Kinker Mishra Griselda Barba-Villalobos Emily Crossman Chima Amushie Jacqueline Nguyen Chadi Calarge Bijan Najafi Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring Sensors pediatrics aggression wearables remote patient monitoring machine learning |
| title | Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring |
| title_full | Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring |
| title_fullStr | Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring |
| title_full_unstemmed | Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring |
| title_short | Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring |
| title_sort | machine learning based aggression detection in children with adhd using sensor based physical activity monitoring |
| topic | pediatrics aggression wearables remote patient monitoring machine learning |
| url | https://www.mdpi.com/1424-8220/23/10/4949 |
| work_keys_str_mv | AT catherinepark machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT mohammaddehghanrouzi machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT mdmoinuddinatique machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT mgfinco machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT ramkinkermishra machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT griseldabarbavillalobos machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT emilycrossman machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT chimaamushie machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT jacquelinenguyen machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT chadicalarge machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring AT bijannajafi machinelearningbasedaggressiondetectioninchildrenwithadhdusingsensorbasedphysicalactivitymonitoring |