Predicting cardiac autonomic neuropathy category for diabetic data with missing values
- Abawajy, Jemal, Kelarev, Andrei, Chowdhury, Morshed, Stranieri, Andrew, Jelinek, Herbert
- Authors: Abawajy, Jemal , Kelarev, Andrei , Chowdhury, Morshed , Stranieri, Andrew , Jelinek, Herbert
- Date: 2013
- Type: Text , Journal article
- Relation: Computers in Biology and Medicine Vol. 43, no. 10 (2013), p. 1328-1333
- Full Text:
- Reviewed:
- Description: Cardiovascular autonomic neuropathy (CAN) is a serious and well known complication of diabetes. Previous articles circumvented the problem of missing values in CAN data by deleting all records and fields with missing values and applying classifiers trained on different sets of features that were complete. Most of them also added alternative features to compensate for the deleted ones. Here we introduce and investigate a new method for classifying CAN data with missing values. In contrast to all previous papers, our new method does not delete attributes with missing values, does not use classifiers, and does not add features. Instead it is based on regression and meta-regression combined with the Ewing formula for identifying the classes of CAN. This is the first article using the Ewing formula and regression to classify CAN. We carried out extensive experiments to determine the best combination of regression and meta-regression techniques for classifying CAN data with missing values. The best outcomes have been obtained by the additive regression meta-learner based on M5Rules and combined with the Ewing formula. It has achieved the best accuracy of 99.78% for two classes of CAN, and 98.98% for three classes of CAN. These outcomes are substantially better than previous results obtained in the literature by deleting all missing attributes and applying traditional classifiers to different sets of features without regression. Another advantage of our method is that it does not require practitioners to perform more tests collecting additional alternative features. © 2013 Elsevier Ltd.
- Description: C1
- Authors: Abawajy, Jemal , Kelarev, Andrei , Chowdhury, Morshed , Stranieri, Andrew , Jelinek, Herbert
- Date: 2013
- Type: Text , Journal article
- Relation: Computers in Biology and Medicine Vol. 43, no. 10 (2013), p. 1328-1333
- Full Text:
- Reviewed:
- Description: Cardiovascular autonomic neuropathy (CAN) is a serious and well known complication of diabetes. Previous articles circumvented the problem of missing values in CAN data by deleting all records and fields with missing values and applying classifiers trained on different sets of features that were complete. Most of them also added alternative features to compensate for the deleted ones. Here we introduce and investigate a new method for classifying CAN data with missing values. In contrast to all previous papers, our new method does not delete attributes with missing values, does not use classifiers, and does not add features. Instead it is based on regression and meta-regression combined with the Ewing formula for identifying the classes of CAN. This is the first article using the Ewing formula and regression to classify CAN. We carried out extensive experiments to determine the best combination of regression and meta-regression techniques for classifying CAN data with missing values. The best outcomes have been obtained by the additive regression meta-learner based on M5Rules and combined with the Ewing formula. It has achieved the best accuracy of 99.78% for two classes of CAN, and 98.98% for three classes of CAN. These outcomes are substantially better than previous results obtained in the literature by deleting all missing attributes and applying traditional classifiers to different sets of features without regression. Another advantage of our method is that it does not require practitioners to perform more tests collecting additional alternative features. © 2013 Elsevier Ltd.
- Description: C1
Posttreatment attrition and its predictors, attrition bias, and treatment efficacy of the anxiety online programs
- Al-Asadi, Ali, Klein, Britt, Meyer, Denny
- Authors: Al-Asadi, Ali , Klein, Britt , Meyer, Denny
- Date: 2014
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 16, no. 10 (2014), p. e232
- Full Text:
- Reviewed:
- Description: Background: Although relatively new, the field of e-mental health is becoming more popular with more attention given to researching its various aspects. However, there are many areas that still need further research, especially identifying attrition predictors at various phases of assessment and treatment delivery. Objective: The present study identified the predictors of posttreatment assessment completers based on 24 pre- and posttreatment demographic and personal variables and 1 treatment variable, their impact on attrition bias, and the efficacy of the 5 fully automated self-help anxiety treatment programs for generalized anxiety disorder (GAD), social anxiety disorder (SAD), panic disorder with or without agoraphobia (PD/A), obsessive-compulsive disorder (OCD), and posttraumatic stress disorder (PTSD). Methods: A complex algorithm was used to diagnose participants' mental disorders based on the criteria of the Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition, Text Revision; DSM-IV-TR). Those who received a primary or secondary diagnosis of 1 of 5 anxiety disorders were offered an online 12-week disorder-specific treatment program. A total of 3199 individuals did not formally drop out of the 12-week treatment cycle, whereas 142 individuals formally dropped out. However, only 347 participants who completed their treatment cycle also completed the posttreatment assessment measures. Based on these measures, predictors of attrition were identified and attrition bias was examined. The efficacy of the 5 treatment programs was assessed based on anxiety-specific severity scores and 5 additional treatment outcome measures. Results: On average, completers of posttreatment assessment measures were more likely to be seeking self-help online programs; have heard about the program from traditional media or from family and friends; were receiving mental health assistance; were more likely to learn best by reading, hearing and doing; had a lower pretreatment Kessler-6 total score; and were older in age. Predicted probabilities resulting from these attrition variables displayed no significant attrition bias using Heckman's method and thus allowing for the use of completer analysis. Six treatment outcome measures (Kessler-6 total score, number of diagnosed disorders, self-confidence in managing mental health issues, quality of life, and the corresponding pre- and posttreatment severity for each program-specific anxiety disorder and for major depressive episode) were used to assess the efficacy of the 5 anxiety treatment programs. Repeated measures MANOVA revealed a significant multivariate time effect for all treatment outcome measures for each treatment program. Follow-up repeated measures ANOVAs revealed significant improvements on all 6 treatment outcome measures for GAD and PTSD, 5 treatment outcome measures were significant for SAD and PD/A, and 4 treatment outcome measures were significant for OCD. Conclusions: Results identified predictors of posttreatment assessment completers and provided further support for the efficacy of self-help online treatment programs for the 5 anxiety disorders
- Authors: Al-Asadi, Ali , Klein, Britt , Meyer, Denny
- Date: 2014
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 16, no. 10 (2014), p. e232
- Full Text:
- Reviewed:
- Description: Background: Although relatively new, the field of e-mental health is becoming more popular with more attention given to researching its various aspects. However, there are many areas that still need further research, especially identifying attrition predictors at various phases of assessment and treatment delivery. Objective: The present study identified the predictors of posttreatment assessment completers based on 24 pre- and posttreatment demographic and personal variables and 1 treatment variable, their impact on attrition bias, and the efficacy of the 5 fully automated self-help anxiety treatment programs for generalized anxiety disorder (GAD), social anxiety disorder (SAD), panic disorder with or without agoraphobia (PD/A), obsessive-compulsive disorder (OCD), and posttraumatic stress disorder (PTSD). Methods: A complex algorithm was used to diagnose participants' mental disorders based on the criteria of the Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition, Text Revision; DSM-IV-TR). Those who received a primary or secondary diagnosis of 1 of 5 anxiety disorders were offered an online 12-week disorder-specific treatment program. A total of 3199 individuals did not formally drop out of the 12-week treatment cycle, whereas 142 individuals formally dropped out. However, only 347 participants who completed their treatment cycle also completed the posttreatment assessment measures. Based on these measures, predictors of attrition were identified and attrition bias was examined. The efficacy of the 5 treatment programs was assessed based on anxiety-specific severity scores and 5 additional treatment outcome measures. Results: On average, completers of posttreatment assessment measures were more likely to be seeking self-help online programs; have heard about the program from traditional media or from family and friends; were receiving mental health assistance; were more likely to learn best by reading, hearing and doing; had a lower pretreatment Kessler-6 total score; and were older in age. Predicted probabilities resulting from these attrition variables displayed no significant attrition bias using Heckman's method and thus allowing for the use of completer analysis. Six treatment outcome measures (Kessler-6 total score, number of diagnosed disorders, self-confidence in managing mental health issues, quality of life, and the corresponding pre- and posttreatment severity for each program-specific anxiety disorder and for major depressive episode) were used to assess the efficacy of the 5 anxiety treatment programs. Repeated measures MANOVA revealed a significant multivariate time effect for all treatment outcome measures for each treatment program. Follow-up repeated measures ANOVAs revealed significant improvements on all 6 treatment outcome measures for GAD and PTSD, 5 treatment outcome measures were significant for SAD and PD/A, and 4 treatment outcome measures were significant for OCD. Conclusions: Results identified predictors of posttreatment assessment completers and provided further support for the efficacy of self-help online treatment programs for the 5 anxiety disorders
Comorbidity structure of psychological disorders in the online e-PASS data as predictors of psychosocial adjustment measures: psychological distress, adequate social support, self-confidence, quality of life, and suicidal ideation
- Al-Asadi, Ali, Klein, Britt, Meyer, Denny
- Authors: Al-Asadi, Ali , Klein, Britt , Meyer, Denny
- Date: 2014
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 16, no. 10 (2014), p. e248
- Full Text:
- Reviewed:
- Description: BACKGROUND: A relative newcomer to the field of psychology, e-mental health has been gaining momentum and has been given considerable research attention. Although several aspects of e-mental health have been studied, 1 aspect has yet to receive attention: the structure of comorbidity of psychological disorders and their relationships with measures of psychosocial adjustment including suicidal ideation in online samples. OBJECTIVE: This exploratory study attempted to identify the structure of comorbidity of 21 psychological disorders assessed by an automated online electronic psychological assessment screening system (e-PASS). The resulting comorbidity factor scores were then used to assess the association between comorbidity factor scores and measures of psychosocial adjustments (ie, psychological distress, suicidal ideation, adequate social support, self-confidence in dealing with mental health issues, and quality of life). METHODS: A total of 13,414 participants were assessed using a complex online algorithm that resulted in primary and secondary Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition, Text Revision) diagnoses for 21 psychological disorders on dimensional severity scales. The scores on these severity scales were used in a principal component analysis (PCA) and the resulting comorbidity factor scores were related to 4 measures of psychosocial adjustments. RESULTS: A PCA based on 17 of the 21 psychological disorders resulted in a 4-factor model of comorbidity: anxiety-depression consisting of all anxiety disorders, major depressive episode (MDE), and insomnia; substance abuse consisting of alcohol and drug abuse and dependency; body image-eating consisting of eating disorders, body dysmorphic disorder, and obsessive-compulsive disorders; depression-sleep problems consisting of MDE, insomnia, and hypersomnia. All comorbidity factor scores were significantly associated with psychosocial measures of adjustment (P<.001). They were positively related to psychological distress and suicidal ideation, but negatively related to adequate social support, self-confidence, and quality of life. CONCLUSIONS: This exploratory study identified 4 comorbidity factors in the e-PASS data and these factor scores significantly predicted 5 psychosocial adjustment measures. TRIAL REGISTRATION: Australian and New Zealand Clinical Trials Registry ACTRN121611000704998; http://www.anzctr.org.au/trial_view.aspx?ID=336143 (Archived by WebCite at http://www.webcitation.org/618r3wvOG).
- Authors: Al-Asadi, Ali , Klein, Britt , Meyer, Denny
- Date: 2014
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 16, no. 10 (2014), p. e248
- Full Text:
- Reviewed:
- Description: BACKGROUND: A relative newcomer to the field of psychology, e-mental health has been gaining momentum and has been given considerable research attention. Although several aspects of e-mental health have been studied, 1 aspect has yet to receive attention: the structure of comorbidity of psychological disorders and their relationships with measures of psychosocial adjustment including suicidal ideation in online samples. OBJECTIVE: This exploratory study attempted to identify the structure of comorbidity of 21 psychological disorders assessed by an automated online electronic psychological assessment screening system (e-PASS). The resulting comorbidity factor scores were then used to assess the association between comorbidity factor scores and measures of psychosocial adjustments (ie, psychological distress, suicidal ideation, adequate social support, self-confidence in dealing with mental health issues, and quality of life). METHODS: A total of 13,414 participants were assessed using a complex online algorithm that resulted in primary and secondary Diagnostic and Statistical Manual of Mental Disorders (Fourth Edition, Text Revision) diagnoses for 21 psychological disorders on dimensional severity scales. The scores on these severity scales were used in a principal component analysis (PCA) and the resulting comorbidity factor scores were related to 4 measures of psychosocial adjustments. RESULTS: A PCA based on 17 of the 21 psychological disorders resulted in a 4-factor model of comorbidity: anxiety-depression consisting of all anxiety disorders, major depressive episode (MDE), and insomnia; substance abuse consisting of alcohol and drug abuse and dependency; body image-eating consisting of eating disorders, body dysmorphic disorder, and obsessive-compulsive disorders; depression-sleep problems consisting of MDE, insomnia, and hypersomnia. All comorbidity factor scores were significantly associated with psychosocial measures of adjustment (P<.001). They were positively related to psychological distress and suicidal ideation, but negatively related to adequate social support, self-confidence, and quality of life. CONCLUSIONS: This exploratory study identified 4 comorbidity factors in the e-PASS data and these factor scores significantly predicted 5 psychosocial adjustment measures. TRIAL REGISTRATION: Australian and New Zealand Clinical Trials Registry ACTRN121611000704998; http://www.anzctr.org.au/trial_view.aspx?ID=336143 (Archived by WebCite at http://www.webcitation.org/618r3wvOG).
Collecting health and exposure data in Australian olympic combat sports : Feasibility study utilizing an electronic system
- Bromley, Sally, Drew, Michael, Talpey, Scott, McIntosh, Andrew, Finch, Caroline
- Authors: Bromley, Sally , Drew, Michael , Talpey, Scott , McIntosh, Andrew , Finch, Caroline
- Date: 2018
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 20, no. 10 (2018), p. 1-11
- Full Text:
- Reviewed:
- Description: Background: Electronic methods are increasingly being used to manage health-related data among sporting populations. Collection of such data permits the analysis of injury and illness trends, improves early detection of injuries and illnesses, collectively referred to as health problems, and provides evidence to inform prevention strategies. The Athlete Management System (AMS) has been employed across a range of sports to monitor health. Australian combat athletes train across the country without dedicated national medical or sports science teams to monitor and advocate for their health. Employing a Web-based system, such as the AMS, May provide an avenue to increase the visibility of health problems experienced by combat athletes and deliver key information to stakeholders detailing where prevention programs May be targeted. Objective: The objectives of this paper are to (1) report on the feasibility of utilizing the AMS to collect longitudinal injury and illness data of combat sports athletes and (2) describe the type, location, severity, and recurrence of injuries and illnesses that the cohort of athletes experience across a 12-week period. Methods: We invited 26 elite and developing athletes from 4 Olympic combat sports (boxing, judo, taekwondo, and wrestling) to participate in this study. Engagement with the AMS was measured, and collected health problems (injuries or illnesses) were coded using the Orchard Sports Injury Classification System (version 10.1) and International Classification of Primary Care (version 2). Results: Despite >160 contacts, athlete engagement with online tools was poor, with only 13% compliance across the 12-week period. No taekwondo or wrestling athletes were compliant. Despite low overall engagement, a large number of injuries or illness were recorded across 11 athletes who entered data—22 unique injuries, 8 unique illnesses, 30 recurrent injuries, and 2 recurrent illnesses. The most frequent injuries were to the knee in boxing (n=41) and thigh in judo (n=9). In this cohort, judo players experienced more severe, but less frequent, injuries than boxers, yet judo players sustained more illnesses than boxers. In 97.0% (126/130) of cases, athletes in this cohort continued to train irrespective of their health problems. Conclusions: Among athletes who reported injuries, many reported multiple conditions, indicating a need for health monitoring in Australian combat sports. A number of factors May have influenced engagement with the AMS, including access to the internet, the design of the system, coach views on the system, previous experiences with the system, and the existing culture within Australian combat sports. To increase engagement, there May be a requirement for sports staff to provide relevant feedback on data entered into the system. Until the Barriers are addressed, it is not feasible to implement the system in its current form across a larger cohort of combat athletes.
- Authors: Bromley, Sally , Drew, Michael , Talpey, Scott , McIntosh, Andrew , Finch, Caroline
- Date: 2018
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 20, no. 10 (2018), p. 1-11
- Full Text:
- Reviewed:
- Description: Background: Electronic methods are increasingly being used to manage health-related data among sporting populations. Collection of such data permits the analysis of injury and illness trends, improves early detection of injuries and illnesses, collectively referred to as health problems, and provides evidence to inform prevention strategies. The Athlete Management System (AMS) has been employed across a range of sports to monitor health. Australian combat athletes train across the country without dedicated national medical or sports science teams to monitor and advocate for their health. Employing a Web-based system, such as the AMS, May provide an avenue to increase the visibility of health problems experienced by combat athletes and deliver key information to stakeholders detailing where prevention programs May be targeted. Objective: The objectives of this paper are to (1) report on the feasibility of utilizing the AMS to collect longitudinal injury and illness data of combat sports athletes and (2) describe the type, location, severity, and recurrence of injuries and illnesses that the cohort of athletes experience across a 12-week period. Methods: We invited 26 elite and developing athletes from 4 Olympic combat sports (boxing, judo, taekwondo, and wrestling) to participate in this study. Engagement with the AMS was measured, and collected health problems (injuries or illnesses) were coded using the Orchard Sports Injury Classification System (version 10.1) and International Classification of Primary Care (version 2). Results: Despite >160 contacts, athlete engagement with online tools was poor, with only 13% compliance across the 12-week period. No taekwondo or wrestling athletes were compliant. Despite low overall engagement, a large number of injuries or illness were recorded across 11 athletes who entered data—22 unique injuries, 8 unique illnesses, 30 recurrent injuries, and 2 recurrent illnesses. The most frequent injuries were to the knee in boxing (n=41) and thigh in judo (n=9). In this cohort, judo players experienced more severe, but less frequent, injuries than boxers, yet judo players sustained more illnesses than boxers. In 97.0% (126/130) of cases, athletes in this cohort continued to train irrespective of their health problems. Conclusions: Among athletes who reported injuries, many reported multiple conditions, indicating a need for health monitoring in Australian combat sports. A number of factors May have influenced engagement with the AMS, including access to the internet, the design of the system, coach views on the system, previous experiences with the system, and the existing culture within Australian combat sports. To increase engagement, there May be a requirement for sports staff to provide relevant feedback on data entered into the system. Until the Barriers are addressed, it is not feasible to implement the system in its current form across a larger cohort of combat athletes.
- Miloyan, Beyon, Suddendorf, Thomas
- Authors: Miloyan, Beyon , Suddendorf, Thomas
- Date: 2015
- Type: Text , Journal article
- Relation: Trends in Cognitive Sciences Vol. 19, no. 4 (2015), p. 196-200
- Full Text: false
- Reviewed:
- Description: Affective forecasting refers to the capacity to predict future feelings. Humans have been found to exhibit systematic affective forecasting biases that involve overestimation of the intensity and duration of future feelings. Although recent research has elucidated the proximate mechanisms underlying our ability to predict future feelings, explanations concerning the potential adaptive significance of these biases have attracted little attention. Here we consider the function of affective forecasts as signals of biological value, drivers of goal pursuit, and tools for eliciting collaboration. Although affective forecasting biases can have significant costs, for instance in terms of one's pursuit of happiness, they may ultimately serve adaptive functions.
The diagnostic validity and reliability of an internet-based clinical assessment program for mental disorders
- Nguyen, David, Klein, Britt, Meyer, Denny, Austin, David, Abbott, Jo-Anne
- Authors: Nguyen, David , Klein, Britt , Meyer, Denny , Austin, David , Abbott, Jo-Anne
- Date: 2015
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 17, no. 9 (2015), p.
- Full Text:
- Reviewed:
- Description: Background: Internet-based assessment has the potential to assist with the diagnosis of mental health disorders and overcome the barriers associated with traditional services (eg, cost, stigma, distance). Further to existing online screening programs available, there is an opportunity to deliver more comprehensive and accurate diagnostic tools to supplement the assessment and treatment of mental health disorders. Objective: The aim was to evaluate the diagnostic criterion validity and test-retest reliability of the electronic Psychological Assessment System (e-PASS), an online, self-report, multidisorder, clinical assessment and referral system. Methods: Participants were 616 adults residing in Australia, recruited online, and representing prospective e-PASS users. Following e-PASS completion, 158 participants underwent a telephone-administered structured clinical interview and 39 participants repeated the e-PASS within 25 days of initial completion. Results: With structured clinical interview results serving as the gold standard, diagnostic agreement with the e-PASS varied considerably from fair (eg, generalized anxiety disorder:kappa=.37) to strong (eg, panic disorder:kappa=.62). Although the e-PASS' sensitivity also varied (0.43-0.86) the specificity was generally high (0.68-1.00). The e-PASS sensitivity generally improved when reducing the e-PASS threshold to a subclinical result. Test-retest reliability ranged from moderate (eg, specific phobia:kappa=.54) to substantial (eg, bulimia nervosa:kappa=.87). Conclusions: The e-PASS produces reliable diagnostic results and performs generally well in excluding mental disorders, although at the expense of sensitivity. For screening purposes, the e-PASS subclinical result generally appears better than a clinical result as a diagnostic indicator. Further development and evaluation is needed to support the use of online diagnostic assessment programs for mental disorders.
- Authors: Nguyen, David , Klein, Britt , Meyer, Denny , Austin, David , Abbott, Jo-Anne
- Date: 2015
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 17, no. 9 (2015), p.
- Full Text:
- Reviewed:
- Description: Background: Internet-based assessment has the potential to assist with the diagnosis of mental health disorders and overcome the barriers associated with traditional services (eg, cost, stigma, distance). Further to existing online screening programs available, there is an opportunity to deliver more comprehensive and accurate diagnostic tools to supplement the assessment and treatment of mental health disorders. Objective: The aim was to evaluate the diagnostic criterion validity and test-retest reliability of the electronic Psychological Assessment System (e-PASS), an online, self-report, multidisorder, clinical assessment and referral system. Methods: Participants were 616 adults residing in Australia, recruited online, and representing prospective e-PASS users. Following e-PASS completion, 158 participants underwent a telephone-administered structured clinical interview and 39 participants repeated the e-PASS within 25 days of initial completion. Results: With structured clinical interview results serving as the gold standard, diagnostic agreement with the e-PASS varied considerably from fair (eg, generalized anxiety disorder:kappa=.37) to strong (eg, panic disorder:kappa=.62). Although the e-PASS' sensitivity also varied (0.43-0.86) the specificity was generally high (0.68-1.00). The e-PASS sensitivity generally improved when reducing the e-PASS threshold to a subclinical result. Test-retest reliability ranged from moderate (eg, specific phobia:kappa=.54) to substantial (eg, bulimia nervosa:kappa=.87). Conclusions: The e-PASS produces reliable diagnostic results and performs generally well in excluding mental disorders, although at the expense of sensitivity. For screening purposes, the e-PASS subclinical result generally appears better than a clinical result as a diagnostic indicator. Further development and evaluation is needed to support the use of online diagnostic assessment programs for mental disorders.
- «
- ‹
- 1
- ›
- »