1
|
Andrikopoulos D, Vassiliou G, Fatouros P, Tsirmpas C, Pehlivanidis A, Papageorgiou C. Machine learning-enabled detection of attention-deficit/hyperactivity disorder with multimodal physiological data: a case-control study. BMC Psychiatry 2024; 24:547. [PMID: 39103819 DOI: 10.1186/s12888-024-05987-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Accepted: 07/25/2024] [Indexed: 08/07/2024] Open
Abstract
BACKGROUND Attention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals' functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored. METHODS The main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection. RESULTS Results indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD. CONCLUSIONS This study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.
Collapse
Affiliation(s)
| | - Georgia Vassiliou
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
| | | | | | - Artemios Pehlivanidis
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
| | - Charalabos Papageorgiou
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
- Neurosciences and Precision Medicine Research Institute "Costas Stefanis", University Mental Health, Athens, Greece
| |
Collapse
|
2
|
Dunn A, Pyne S, Tyson B, Roth R, Shahein A, Erdodi L. Critical Item Analysis Enhances the Classification Accuracy of the Logical Memory Recognition Trial as a Performance Validity Indicator. Dev Neuropsychol 2021; 46:327-346. [PMID: 34525856 DOI: 10.1080/87565641.2021.1956499] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
OBJECTIVE : Replicate previous research on Logical Memory Recognition (LMRecog) and perform a critical item analysis. METHOD : Performance validity was psychometrically operationalized in a mixed clinical sample of 213 adults. Classification of the LMRecog and nine critical items (CR-9) was computed. RESULTS : LMRecog ≤20 produced a good combination of sensitivity (.30-.35) and specificity (.89-.90). CR-9 ≥5 and ≥6 had comparable classification accuracy. CR-9 ≥5 increased sensitivity by 4% over LMRecog ≤20; CR-9 ≥6 increased specificity by 6-8% over LMRecog ≤20; CR-9 ≥7 increased specificity by 8-15%. CONCLUSIONS : Critical item analysis enhances the classification accuracy of the optimal LMRecog cutoff (≤20).
Collapse
Affiliation(s)
- Alexa Dunn
- Department of Psychology, University of Windsor, Windsor, Canada
| | - Sadie Pyne
- Windsor Neuropsychology, Windsor, Canada
| | - Brad Tyson
- Neuroscience Institute, Evergreen Neuroscience Institute, EvergreenHealth Medical Center, Kirkland, USA
| | - Robert Roth
- Neuropsychology Services, Dartmouth-Hitchcock Medical Center, USA
| | - Ayman Shahein
- Department of Clinical Neurosciences, University of Calgary, Calgary, Canada
| | - Laszlo Erdodi
- Department of Psychology, University of Windsor, Windsor, Canada
| |
Collapse
|
3
|
Abeare CA, An K, Tyson B, Holcomb M, Cutler L, May N, Erdodi LA. The emotion word fluency test as an embedded performance validity indicator - Alone and in a multivariate validity composite. APPLIED NEUROPSYCHOLOGY. CHILD 2021; 11:713-724. [PMID: 34424798 DOI: 10.1080/21622965.2021.1939027] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
OBJECTIVE This project was designed to cross-validate existing performance validity cutoffs embedded within measures of verbal fluency (FAS and animals) and develop new ones for the Emotion Word Fluency Test (EWFT), a novel measure of category fluency. METHOD The classification accuracy of the verbal fluency tests was examined in two samples (70 cognitively healthy university students and 52 clinical patients) against psychometrically defined criterion measures. RESULTS A demographically adjusted T-score of ≤31 on the FAS was specific (.88-.97) to noncredible responding in both samples. Animals T ≤ 29 achieved high specificity (.90-.93) among students at .27-.38 sensitivity. A more conservative cutoff (T ≤ 27) was needed in the patient sample for a similar combination of sensitivity (.24-.45) and specificity (.87-.93). An EWFT raw score ≤5 was highly specific (.94-.97) but insensitive (.10-.18) to invalid performance. Failing multiple cutoffs improved specificity (.90-1.00) at variable sensitivity (.19-.45). CONCLUSIONS Results help resolve the inconsistency in previous reports, and confirm the overall utility of existing verbal fluency tests as embedded validity indicators. Multivariate models of performance validity assessment are superior to single indicators. The clinical utility and limitations of the EWFT as a novel measure are discussed.
Collapse
Affiliation(s)
- Christopher A Abeare
- Department of Psychology, Neuropsychology Track, University of Windsor, Windsor, Ontario, Canada
| | - Kelly An
- Private Practice, London, Ontario, Canada
| | - Brad Tyson
- Evergreen Health Medical Center, Kirkland, Washington, USA
| | - Matthew Holcomb
- Jefferson Neurobehavioral Group, New Orleans, Louisiana, USA
| | - Laura Cutler
- Department of Psychology, Neuropsychology Track, University of Windsor, Windsor, Ontario, Canada
| | - Natalie May
- Department of Psychology, Neuropsychology Track, University of Windsor, Windsor, Ontario, Canada
| | - Laszlo A Erdodi
- Department of Psychology, Neuropsychology Track, University of Windsor, Windsor, Ontario, Canada
| |
Collapse
|
4
|
Abeare CA, Hurtubise JL, Cutler L, Sirianni C, Brantuo M, Makhzoum N, Erdodi LA. Introducing a forced choice recognition trial to the Hopkins Verbal Learning Test – Revised. Clin Neuropsychol 2020; 35:1442-1470. [DOI: 10.1080/13854046.2020.1779348] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Affiliation(s)
| | | | - Laura Cutler
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | | | - Maame Brantuo
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Nadeen Makhzoum
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Laszlo A. Erdodi
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| |
Collapse
|
5
|
Baggio S, Hasler R, Giacomini V, El-Masri H, Weibel S, Perroud N, Deiber MP. Does the Continuous Performance Test Predict ADHD Symptoms Severity and ADHD Presentation in Adults? J Atten Disord 2020; 24:840-848. [PMID: 30654686 DOI: 10.1177/1087054718822060] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Objective: Our study aimed to provide empirical evidence on the usefulness of one of the most popular neuropsychological tests, the Continuous Performance Test (CPT), as a marker of ADHD severity and presentations among adults. Method: ADHD participants were recruited in a specialized center for the diagnosis and treatment of adults suffering from ADHD (n = 201). Measures included the CPT3™ and ADHD symptoms using a clinical interview and self-reported measures. Results: Only 51.7% of the participants were classified as likely to have a disorder characterized by attention deficit, such as ADHD, by the CPT. The relationships between CPT variables and ADHD symptoms were small. The classification error was 80.3% for the inattentive presentation and 22.5% for the hyperactive presentation when using the CPT to identify ADHD presentations. Conclusion: There was no evidence of the clinical utility of the CPT to assess or monitor ADHD in adult populations diagnosed and treated for ADHD.
Collapse
Affiliation(s)
- Stéphanie Baggio
- Geneva University Hospitals, Switzerland.,University of Geneva, Switzerland.,University of Lausanne, Switzerland
| | - Roland Hasler
- Geneva University Hospitals, Switzerland.,University of Geneva, Switzerland.,NCCR Synapsy, Campus Biotech, Geneva, Switzerland
| | | | | | - Sébastien Weibel
- University Hospital of Strasbourg, France.,Inserm u114, Strasbourg, France.,Translational Medicine Federation of Strasbourg (FMTS), France
| | - Nader Perroud
- Geneva University Hospitals, Switzerland.,University of Geneva, Switzerland
| | - Marie-Pierre Deiber
- Geneva University Hospitals, Switzerland.,University of Geneva, Switzerland.,NCCR Synapsy, Campus Biotech, Geneva, Switzerland
| |
Collapse
|
6
|
Slobodin O, Davidovitch M. Gender Differences in Objective and Subjective Measures of ADHD Among Clinic-Referred Children. Front Hum Neurosci 2019; 13:441. [PMID: 31920599 PMCID: PMC6923191 DOI: 10.3389/fnhum.2019.00441] [Citation(s) in RCA: 58] [Impact Index Per Article: 11.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2019] [Accepted: 12/02/2019] [Indexed: 11/25/2022] Open
Abstract
Attention deficit hyperactivity disorder (ADHD), one of the most prevalent childhood disorders today, is generally more likely to be diagnosed and treated in boys than in girls. However, gender differences in ADHD are currently poorly understood, partly because previous research included only a limited proportion of girls and relied mainly on subjective measures of ADHD, which are highly vulnerable to reporter's bias. To further examine gender differences in ADHD and to address some of the shortcomings of previous studies, this study examined gender differences in subjective and objective measures of ADHD among clinic-referred children with ADHD. Participants were 204 children aged 6-17 years-old with ADHD (129 boys, 75 girls). A retrospective analysis was conducted using records of a clinical database. Obtained data included parent and teacher forms of the Conners ADHD rating scales, Child Behavior Checklist (CBCL), Teacher's Report Form (TRF), and child's continuous performance test (CPT) scores. Results showed that according to parents' and teachers' reports of ADHD-related symptoms (Conners ADHD rating scales), girls had more inattention problems than boys, but no differences were identified in the level of hyperactivity and impulsivity symptoms. CPT data, however, revealed higher impulsivity among boys. We did not find gender differences in the level of distractibility during CPT performance. Specifically, the effects of distractors type (visual environmental stimuli, auditory stimuli, or a combination of them) and distractors load (one or two distracting stimuli at a time) on CPT performance did not differ between boys and girls with ADHD. These findings suggest that gender effects on ADHD symptoms may differ between subjective and objective measures. Understanding gender differences in ADHD may lead to improved identification of girls with the disorder, helping to reduce the gender gap in diagnosis and treatment.
Collapse
Affiliation(s)
- Ortal Slobodin
- Department of Education, Ben-Gurion University, Beer-Sheva, Israel
| | - Michael Davidovitch
- Medical Department and Research Institute, Maccabi Healthcare Services, Tel Aviv, Israel
| |
Collapse
|
7
|
Olla P, Rykulski N, Hurtubise JL, Bartol S, Foote R, Cutler L, Abeare K, McVinnie N, Sabelli AG, Hastings M, Erdodi LA. Short-term effects of cannabis consumption on cognitive performance in medical cannabis patients. APPLIED NEUROPSYCHOLOGY-ADULT 2019; 28:647-657. [PMID: 31790276 DOI: 10.1080/23279095.2019.1681424] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/25/2023]
Abstract
This observational study examined the acute cognitive effects of cannabis. We hypothesized that cognitive performance would be negatively affected by acute cannabis intoxication. Twenty-two medical cannabis patients from Southwestern Ontario completed the study. The majority (n = 13) were male. Mean age was 36.0 years, and mean level of education was 13.7 years. Participants were administered the same brief neurocognitive battery three times during a six-hour period: at baseline ("Baseline"), once after they consumed a 20% THC cannabis product ("THC"), and once again several hours later ("Recovery"). The average self-reported level of cannabis intoxication prior to the second assessment (i.e., during THC) was 5.1 out of 10. Contrary to expectations, performance on neuropsychological tests remained stable or even improved during the acute intoxication stage (THC; d: .49-.65, medium effect), and continued to increase during Recovery (d: .45-.77, medium-large effect). Interestingly, the failure rate on performance validity indicators increased during THC. Contrary to our hypothesis, there was no psychometric evidence for a decline in cognitive ability following THC intoxication. There are several possible explanations for this finding but, in the absence of a control group, no definitive conclusion can be reached at this time.
Collapse
Affiliation(s)
| | - Nicholas Rykulski
- College of Human Medicine, Michigan State University, Lansing, MI, USA
| | | | - Stephen Bartol
- School of Medicine, Wayne State University, Detroit, MI, USA
| | | | - Laura Cutler
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Kaitlyn Abeare
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Nora McVinnie
- Brain-Cognition-Neuroscience Program, University of Windsor, Windsor, ON, Canada
| | - Alana G Sabelli
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Maurissa Hastings
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| | - Laszlo A Erdodi
- Department of Psychology, University of Windsor, Windsor, ON, Canada
| |
Collapse
|
8
|
Beyond Rare-Symptoms Endorsement: a Clinical Comparison Simulation Study Using the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) with the Inventory of Problems-29 (IOP-29). PSYCHOLOGICAL INJURY & LAW 2019. [DOI: 10.1007/s12207-019-09357-7] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|
9
|
The Effect of Menstrual Cycle Phase and Hormonal Contraceptive Use on Post-concussive Symptom Reporting in Non-concussed Adults. PSYCHOLOGICAL INJURY & LAW 2019. [DOI: 10.1007/s12207-019-09351-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
|
10
|
Psychometric Markers of Genuine and Feigned Neurodevelopmental Disorders in the Context of Applying for Academic Accommodations. PSYCHOLOGICAL INJURY & LAW 2017. [DOI: 10.1007/s12207-017-9287-5] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
|
11
|
Erdodi LA, Roth RM, Kirsch NL, Lajiness-O'neill R, Medoff B. Aggregating Validity Indicators Embedded in Conners' CPT-II Outperforms Individual Cutoffs at Separating Valid from Invalid Performance in Adults with Traumatic Brain Injury. Arch Clin Neuropsychol 2014; 29:456-66. [DOI: 10.1093/arclin/acu026] [Citation(s) in RCA: 54] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
|
12
|
Cassuto H, Ben-Simon A, Berger I. Using environmental distractors in the diagnosis of ADHD. Front Hum Neurosci 2013; 7:805. [PMID: 24319423 PMCID: PMC3837230 DOI: 10.3389/fnhum.2013.00805] [Citation(s) in RCA: 34] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2013] [Accepted: 11/06/2013] [Indexed: 11/26/2022] Open
Abstract
This study examined the effect of the incorporation of environmental distractors in computerized continuous performance test (CPT) on the ability of the test in distinguishing ADHD from non-ADHD children. It was hypothesized that children with ADHD would display more distractibility than controls while performing CPT as measured by omission errors in the presence of pure visual, pure auditory, and a combination of visual and auditory distracting stimuli. Participants were 663 children aged 7–12 years, of them 345 diagnosed with ADHD and 318 without ADHD. Results showed that ADHD children demonstrated more omission errors than their healthy peers in all CPT conditions (no distractors, pure visual or auditory distractors and combined distractors). However, ADHD and non-ADHD children differed in their reaction to distracting stimuli; while all types of distracting stimuli increased the rate of omission errors in ADHD children, only combined visual and auditory distractors increased it in non-ADHD children. Given the low ecological validity of many CPT, these findings suggest that incorporating distractors in CPT improves the ability to distinguish ADHD from non-ADHD children.
Collapse
Affiliation(s)
- Hanoch Cassuto
- Pediatric Neurology Clinic, Leumit and Clalit HMO Jerusalem, Israel
| | | | | |
Collapse
|