Objective approach to diagnosing attention deficit hyperactivity disorder by using pixel subtraction and machine learning classification of outpatient consultation videos / Yi-Hung CHIU in Journal of Neurodevelopmental Disorders, 16 (2024)  

Public ISBD [article]  inJournal of Neurodevelopmental Disorders > 16 (2024) Titre : Objective approach to diagnosing attention deficit hyperactivity disorder by using pixel subtraction and machine learning classification of outpatient consultation videos Type de document : texte imprimé Auteurs : Yi-Hung CHIU, Auteur ; Ying-Han LEE, Auteur ; San-Yuan WANG, Auteur ; Chen-Sen OUYANG, Auteur ; Rong-Ching WU, Auteur ; Rei-Cheng YANG, Auteur ; Lung-Chang LIN, Auteur Langues : Anglais (eng) Mots-clés : Humans  Attention Deficit Disorder with Hyperactivity/diagnosis/classification  Machine Learning  Child  Male  Female  Video Recording  Outpatients  Adolescent  Attention deficit hyperactivity disorder  Machine learning  Nolan  Pelham questionnaire  Pixel subtraction  Swanson  Video analysis  consent was obtained from the participants' family members or legal guardians  after the study procedures had been explained. Informed consent was also obtained  for publication of their children’s images. This study was approved by the  Institutional Review Board of Kaohsiung Medical University Hospital  (KMUIRB-SV(I)- 20190060). Consent for publication: Not applicable. Competing  interests: The authors declare no competing interests. Index. décimale : PER Périodiques Résumé : BACKGROUND: Attention deficit hyperactivity disorder (ADHD) is a common childhood neurodevelopmental disorder, affecting between 5% and 7% of school-age children. ADHD is typically characterized by persistent patterns of inattention or hyperactivity-impulsivity, and it is diagnosed on the basis of the criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, through subjective observations and information provided by parents and teachers. Diagnosing ADHD in children is challenging, despite several assessment tools, such as the Swanson, Nolan, and Pelham questionnaire, being widely available. Such scales provide only a subjective understanding of the disorder. In this study, we employed video pixel subtraction and machine learning classification to objectively categorize 85 participants (43 with a diagnosis of ADHD and 42 without) into an ADHD group or a non-ADHD group by quantifying their movements. METHODS: We employed pixel subtraction movement quantization by analyzing movement features in videos of patients in outpatient consultation rooms. Pixel subtraction is a technique in which the number of pixels in one frame is subtracted from that in another frame to detect changes between the two frames. A difference between the pixel values indicates the presence of movement. In the current study, the patients' subtracted image sequences were characterized using three movement feature values: mean, variance, and Shannon entropy value. A classification analysis based on six machine learning models was performed to compare the performance indices and the discriminatory power of various features. RESULTS: The results revealed that compared with the non-ADHD group, the ADHD group had significantly larger values for all movement features. Notably, the Shannon entropy values were 2.38 ± 0.59 and 1.0 ± 0.38 in the ADHD and non-ADHD groups, respectively (P < 0.0001). The Random Forest machine learning classification model achieved the most favorable results, with an accuracy of 90.24%, sensitivity of 88.85%, specificity of 91.75%, and area under the curve of 93.87%. CONCLUSION: Our pixel subtraction and machine learning classification approach is an objective and practical method that can aid to clinical decisions regarding ADHD diagnosis. En ligne : https://dx.doi.org/10.1186/s11689-024-09588-z Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576 [article] Objective approach to diagnosing attention deficit hyperactivity disorder by using pixel subtraction and machine learning classification of outpatient consultation videos [texte imprimé] / Yi-Hung CHIU, Auteur ; Ying-Han LEE, Auteur ; San-Yuan WANG, Auteur ; Chen-Sen OUYANG, Auteur ; Rong-Ching WU, Auteur ; Rei-Cheng YANG, Auteur ; Lung-Chang LIN, Auteur. Langues : Anglais (eng) in Journal of Neurodevelopmental Disorders > 16 (2024) Mots-clés : Humans  Attention Deficit Disorder with Hyperactivity/diagnosis/classification  Machine Learning  Child  Male  Female  Video Recording  Outpatients  Adolescent  Attention deficit hyperactivity disorder  Machine learning  Nolan  Pelham questionnaire  Pixel subtraction  Swanson  Video analysis  consent was obtained from the participants' family members or legal guardians  after the study procedures had been explained. Informed consent was also obtained  for publication of their children’s images. This study was approved by the  Institutional Review Board of Kaohsiung Medical University Hospital  (KMUIRB-SV(I)- 20190060). Consent for publication: Not applicable. Competing  interests: The authors declare no competing interests. Index. décimale : PER Périodiques Résumé : BACKGROUND: Attention deficit hyperactivity disorder (ADHD) is a common childhood neurodevelopmental disorder, affecting between 5% and 7% of school-age children. ADHD is typically characterized by persistent patterns of inattention or hyperactivity-impulsivity, and it is diagnosed on the basis of the criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, through subjective observations and information provided by parents and teachers. Diagnosing ADHD in children is challenging, despite several assessment tools, such as the Swanson, Nolan, and Pelham questionnaire, being widely available. Such scales provide only a subjective understanding of the disorder. In this study, we employed video pixel subtraction and machine learning classification to objectively categorize 85 participants (43 with a diagnosis of ADHD and 42 without) into an ADHD group or a non-ADHD group by quantifying their movements. METHODS: We employed pixel subtraction movement quantization by analyzing movement features in videos of patients in outpatient consultation rooms. Pixel subtraction is a technique in which the number of pixels in one frame is subtracted from that in another frame to detect changes between the two frames. A difference between the pixel values indicates the presence of movement. In the current study, the patients' subtracted image sequences were characterized using three movement feature values: mean, variance, and Shannon entropy value. A classification analysis based on six machine learning models was performed to compare the performance indices and the discriminatory power of various features. RESULTS: The results revealed that compared with the non-ADHD group, the ADHD group had significantly larger values for all movement features. Notably, the Shannon entropy values were 2.38 ± 0.59 and 1.0 ± 0.38 in the ADHD and non-ADHD groups, respectively (P < 0.0001). The Random Forest machine learning classification model achieved the most favorable results, with an accuracy of 90.24%, sensitivity of 88.85%, specificity of 91.75%, and area under the curve of 93.87%. CONCLUSION: Our pixel subtraction and machine learning classification approach is an objective and practical method that can aid to clinical decisions regarding ADHD diagnosis. En ligne : https://dx.doi.org/10.1186/s11689-024-09588-z Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576

Objective diagnosis of attention-deficit/hyperactivity disorder by using load cell movement analysis under a smart chair in a simulated classroom: influence of sex and age / Chen-Sen OUYANG in Journal of Neurodevelopmental Disorders, 17 (2025)  

Public ISBD [article]  inJournal of Neurodevelopmental Disorders > 17 (2025) Titre : Objective diagnosis of attention-deficit/hyperactivity disorder by using load cell movement analysis under a smart chair in a simulated classroom: influence of sex and age Type de document : texte imprimé Auteurs : Chen-Sen OUYANG, Auteur ; Rong-Ching WU, Auteur ; Yi-Hung CHIU, Auteur ; Rei-Cheng YANG, Auteur ; Lung-Chang LIN, Auteur Langues : Anglais (eng) Mots-clés : Humans  Attention Deficit Disorder with Hyperactivity/diagnosis/physiopathology  Male  Female  Child  Sex Factors  Age Factors  Movement/physiology  Attention-deficit/hyperactivity disorder  Average trajectory length  Load cells  Smart chair  consent was obtained by a participant’s family member or legal guardian after the  procedure had been explained. In addition, informed consent was also obtained  from them for the publication of their children’s images. This study was approved  by the Institutional Review Board of Kaohsiung Medical University Hospital  (KMUIRB-SV(I)- 20190060) in accordance with the Declaration of Helsinki.  Competing interests: The authors declare no competing interests. Index. décimale : PER Périodiques Résumé : BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children, typically characterized by persistent patterns of inattention or hyperactivity-impulsivity. Its diagnosis relies on criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, and is primarily based on subjective observations and information provided by parents and teachers. Despite the availability of assessment tools such as the Swanson, Nolan, and Pelham questionnaire, diagnosing ADHD in children remains challenging. Such scales predominantly offer subjective insights into the disorder. Therefore, in this study, we developed an objective method that employs load cells for the objective diagnosis of ADHD. METHODS: A simulated classroom environment was constructed to replicate a real-world setting. The setup included a desk, chair, and large screen. Load cells, which deform under applied force, were integrated into the four legs of the chair to capture movement data. This study involved 30 children with ADHD (14 boys and 16 girls; mean age: 8 years and 1 month ± 1 year and 10 months) and 30 age- and sex-matched children without ADHD (mean age: 8 years and 3 months ± 1 year and 10 months). Participants were instructed to sit on the chair and watch an age-appropriate educational video on mathematics. Movement data, captured through the load cells, were analyzed to calculate the average trajectory length (ATL) as a measure of activity. For participants with ADHD, SNAP-IV questionnaires were completed by parents and teachers. RESULTS: The ATL values for the ADHD and non-ADHD groups were 0.0378 ± 0.0191 and 0.0157 ± 0.0119 (p < 0.0001), respectively. In the ADHD group, boys exhibited a higher ATL (0.0443 ± 0.0100) than girls (0.0303 ± 0.0228; p = 0.0432). The SNAP-IV scores assigned by parents and teachers for participants with ADHD were 33.14 ± 13.75 and 30.95 ± 14.32, respectively. Decision tree classifiers incorporating sex as a variable demonstrated robust performance, achieving an accuracy of 90.67%, sensitivity of 92.33%, specificity of 89.00%, and area under the curve of 91.06%. CONCLUSION: The smart chair equipped with load cells is an interesting development in progress tool for the objective diagnosis of ADHD and can aid clinical physicians in making decisions regarding ADHD evaluation. En ligne : https://dx.doi.org/10.1186/s11689-025-09641-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576 [article] Objective diagnosis of attention-deficit/hyperactivity disorder by using load cell movement analysis under a smart chair in a simulated classroom: influence of sex and age [texte imprimé] / Chen-Sen OUYANG, Auteur ; Rong-Ching WU, Auteur ; Yi-Hung CHIU, Auteur ; Rei-Cheng YANG, Auteur ; Lung-Chang LIN, Auteur. Langues : Anglais (eng) in Journal of Neurodevelopmental Disorders > 17 (2025) Mots-clés : Humans  Attention Deficit Disorder with Hyperactivity/diagnosis/physiopathology  Male  Female  Child  Sex Factors  Age Factors  Movement/physiology  Attention-deficit/hyperactivity disorder  Average trajectory length  Load cells  Smart chair  consent was obtained by a participant’s family member or legal guardian after the  procedure had been explained. In addition, informed consent was also obtained  from them for the publication of their children’s images. This study was approved  by the Institutional Review Board of Kaohsiung Medical University Hospital  (KMUIRB-SV(I)- 20190060) in accordance with the Declaration of Helsinki.  Competing interests: The authors declare no competing interests. Index. décimale : PER Périodiques Résumé : BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children, typically characterized by persistent patterns of inattention or hyperactivity-impulsivity. Its diagnosis relies on criteria outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, and is primarily based on subjective observations and information provided by parents and teachers. Despite the availability of assessment tools such as the Swanson, Nolan, and Pelham questionnaire, diagnosing ADHD in children remains challenging. Such scales predominantly offer subjective insights into the disorder. Therefore, in this study, we developed an objective method that employs load cells for the objective diagnosis of ADHD. METHODS: A simulated classroom environment was constructed to replicate a real-world setting. The setup included a desk, chair, and large screen. Load cells, which deform under applied force, were integrated into the four legs of the chair to capture movement data. This study involved 30 children with ADHD (14 boys and 16 girls; mean age: 8 years and 1 month ± 1 year and 10 months) and 30 age- and sex-matched children without ADHD (mean age: 8 years and 3 months ± 1 year and 10 months). Participants were instructed to sit on the chair and watch an age-appropriate educational video on mathematics. Movement data, captured through the load cells, were analyzed to calculate the average trajectory length (ATL) as a measure of activity. For participants with ADHD, SNAP-IV questionnaires were completed by parents and teachers. RESULTS: The ATL values for the ADHD and non-ADHD groups were 0.0378 ± 0.0191 and 0.0157 ± 0.0119 (p < 0.0001), respectively. In the ADHD group, boys exhibited a higher ATL (0.0443 ± 0.0100) than girls (0.0303 ± 0.0228; p = 0.0432). The SNAP-IV scores assigned by parents and teachers for participants with ADHD were 33.14 ± 13.75 and 30.95 ± 14.32, respectively. Decision tree classifiers incorporating sex as a variable demonstrated robust performance, achieving an accuracy of 90.67%, sensitivity of 92.33%, specificity of 89.00%, and area under the curve of 91.06%. CONCLUSION: The smart chair equipped with load cells is an interesting development in progress tool for the objective diagnosis of ADHD and can aid clinical physicians in making decisions regarding ADHD evaluation. En ligne : https://dx.doi.org/10.1186/s11689-025-09641-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=576

---

1 (1 - 2 / 2) Par page : 25 50 100 200