Time-to-event analysis for sports injury research part 1 : Time-varying exposures
- Nielsen, Rasmus, Bertelsen, Michael, Ramskov, Daniel, Møller, Merete, Hulme, Adam, Theisen, Daniel, Finch, Caroline, Fortington, Lauren, Mansournia, Mohammad, Parner, Erik
- Authors: Nielsen, Rasmus , Bertelsen, Michael , Ramskov, Daniel , Møller, Merete , Hulme, Adam , Theisen, Daniel , Finch, Caroline , Fortington, Lauren , Mansournia, Mohammad , Parner, Erik
- Date: 2019
- Type: Text , Journal article , Review
- Relation: British Journal of Sports Medicine Vol. 53, no. 1 (2019), p. 61-68
- Full Text:
- Reviewed:
- Description: Background: 'How much change in training load is too much before injury is sustained, among different athletes?' is a key question in sports medicine and sports science. To address this question the investigator/practitioner must analyse exposure variables that change over time, such as change in training load. Very few studies have included time-varying exposures (eg, training load) and time-varying effect-measure modifiers (eg, previous injury, biomechanics, sleep/stress) when studying sports injury aetiology. Aim: To discuss advanced statistical methods suitable for the complex analysis of time-varying exposures such as changes in training load and injury-related outcomes. Content: Time-varying exposures and time-varying effect-measure modifiers can be used in time-to-event models to investigate sport injury aetiology. We address four key-questions (i) Does time-to-event modelling allow change in training load to be included as a time-varying exposure for sport injury development? (ii) Why is time-to-event analysis superior to other analytical concepts when analysing training-load related data that changes status over time? (iii) How can researchers include change in training load in a time-to-event analysis? and, (iv) Are researchers able to include other time-varying variables into time-to-event analyses? We emphasise that cleaning datasets, setting up the data, performing analyses with time-varying variables and interpreting the results is time-consuming, and requires dedication. It may need you to ask for assistance from methodological peers as the analytical approaches presented this paper require specialist knowledge and well-honed statistical skills. Conclusion: To increase knowledge about the association between changes in training load and injury, we encourage sports injury researchers to collaborate with statisticians and/or methodological epidemiologists to carefully consider applying time-to-event models to prospective sports injury data. This will ensure appropriate interpretation of time-to-event data. © 2019 Author(s).
- Authors: Nielsen, Rasmus , Bertelsen, Michael , Ramskov, Daniel , Møller, Merete , Hulme, Adam , Theisen, Daniel , Finch, Caroline , Fortington, Lauren , Mansournia, Mohammad , Parner, Erik
- Date: 2019
- Type: Text , Journal article , Review
- Relation: British Journal of Sports Medicine Vol. 53, no. 1 (2019), p. 61-68
- Full Text:
- Reviewed:
- Description: Background: 'How much change in training load is too much before injury is sustained, among different athletes?' is a key question in sports medicine and sports science. To address this question the investigator/practitioner must analyse exposure variables that change over time, such as change in training load. Very few studies have included time-varying exposures (eg, training load) and time-varying effect-measure modifiers (eg, previous injury, biomechanics, sleep/stress) when studying sports injury aetiology. Aim: To discuss advanced statistical methods suitable for the complex analysis of time-varying exposures such as changes in training load and injury-related outcomes. Content: Time-varying exposures and time-varying effect-measure modifiers can be used in time-to-event models to investigate sport injury aetiology. We address four key-questions (i) Does time-to-event modelling allow change in training load to be included as a time-varying exposure for sport injury development? (ii) Why is time-to-event analysis superior to other analytical concepts when analysing training-load related data that changes status over time? (iii) How can researchers include change in training load in a time-to-event analysis? and, (iv) Are researchers able to include other time-varying variables into time-to-event analyses? We emphasise that cleaning datasets, setting up the data, performing analyses with time-varying variables and interpreting the results is time-consuming, and requires dedication. It may need you to ask for assistance from methodological peers as the analytical approaches presented this paper require specialist knowledge and well-honed statistical skills. Conclusion: To increase knowledge about the association between changes in training load and injury, we encourage sports injury researchers to collaborate with statisticians and/or methodological epidemiologists to carefully consider applying time-to-event models to prospective sports injury data. This will ensure appropriate interpretation of time-to-event data. © 2019 Author(s).
Online alcohol interventions: A systematic review
- White, Angela, Kavanagh, David, Stallman, Helen, Klein, Britt, Kay-Lambkin, Frances, Proudfoot, Judith, Drennan, Judy, Connor, Jason, Baker, Amanda, Hines, Emily, Young, Ross
- Authors: White, Angela , Kavanagh, David , Stallman, Helen , Klein, Britt , Kay-Lambkin, Frances , Proudfoot, Judith , Drennan, Judy , Connor, Jason , Baker, Amanda , Hines, Emily , Young, Ross
- Date: 2010
- Type: Text , Journal article , Review
- Relation: Journal of Medical Internet Research Vol. 12, no. 5 (2010), p. e62p.1-e62p.12
- Full Text:
- Reviewed:
- Description: Background: There has been a significant increase in the availability of online programs for alcohol problems. A systematic review of the research evidence underpinning these programs is timely. Objectives: Our objective was to review the efficacy of online interventions for alcohol misuse. Systematic searches of Medline, PsycINFO, Web of Science, and Scopus were conducted for English abstracts (excluding dissertations) published from 1998 onward. Search terms were: (1) Internet, Web*; (2) online, computer *; (3) alcohol*; and (4) Eeffect *, trial*, random* (where * denotes a wildcard). Forward and backward searches from identified papers were also conducted. Articles were included if (1) the primary intervention was delivered and accessed via the Internet, (2) the intervention focused on moderating or stopping alcohol consumption, and (3) the study was a randomized controlled trial of an alcohol-related screen, assessment, or intervention. Results: The literature search initially yielded 31 randomized controlled trials (RCTs), 17 of which met inclusion criteria. Of these 17 studies, 12 (70.6%) were conducted with university students, and 11 (64.7%) specifically focused on at-risk, heavy, or binge drinkers. Sample sizes ranged from 40 to 3216 (median 261), with 12 (70.6%) studies predominantly involving brief personalized feedback interventions. Using published data, effect sizes could be extracted from 8 of the 17 studies. In relation to alcohol units per week or month and based on 5 RCTs where a measure of alcohol units per week or month could be extracted, differential effect sizes to posttreatment ranged from 0.02 to 0.81 (mean 0.42, median 0.54). Pre-post effect sizes for brief personalized feedback interventions ranged from 0.02 to 0.81, and in 2 multi-session modularized interventions, a pre-post effect size of 0.56 was obtained in both. Pre-post differential effect sizes for peak blood alcohol concentrations (BAC) ranged from 0.22 to 0.88, with a mean effect size of 0.66. Conclusions: The available evidence suggests that users can benefit from online alcohol interventions and that this approach could be particularly useful for groups less likely to access traditional alcohol-related services, such as women, young people, and at-risk users. However, caution should be exercised given the limited number of studies allowing extraction of effect sizes, the heterogeneity of outcome measures and follow-up periods, and the large proportion of student-based studies. More extensive RCTs in community samples are required to better understand the efficacy of specific online alcohol approaches, program dosage, the additive effect of telephone or face-to-face interventions, and effective strategies for their dissemination and marketing.
- Description: Background: There has been a significant increase in the availability of online programs for alcohol problems. A systematic review of the research evidence underpinning these programs is timely. Objectives: Our objective was to review the efficacy of online interventions for alcohol misuse. Systematic searches of Medline, PsycINFO, Web of Science, and Scopus were conducted for English abstracts (excluding dissertations) published from 1998 onward. Search terms were: (1) Internet, Web*; (2) online, computer *; (3) alcohol*; and (4) E\effect *, trial*, random* (where * denotes a wildcard). Forward and backward searches from identified papers were also conducted. Articles were included if (1) the primary intervention was delivered and accessed via the Internet, (2) the intervention focused on moderating or stopping alcohol consumption, and (3) the study was a randomized controlled trial of an alcohol-related screen, assessment, or intervention. Results: The literature search initially yielded 31 randomized controlled trials (RCTs), 17 of which met inclusion criteria. Of these 17 studies, 12 (70.6%) were conducted with university students, and 11 (64.7%) specifically focused on at-risk, heavy, or binge drinkers. Sample sizes ranged from 40 to 3216 (median 261), with 12 (70.6%) studies predominantly involving brief personalized feedback interventions. Using published data, effect sizes could be extracted from 8 of the 17 studies. In relation to alcohol units per week or month and based on 5 RCTs where a measure of alcohol units per week or month could be extracted, differential effect sizes to posttreatment ranged from 0.02 to 0.81 (mean 0.42, median 0.54). Pre-post effect sizes for brief personalized feedback interventions ranged from 0.02 to 0.81, and in 2 multi-session modularized interventions, a pre-post effect size of 0.56 was obtained in both. Pre-post differential effect sizes for peak blood alcohol concentrations (BAC) ranged from 0.22 to 0.88, with a mean effect size of 0.66. Conclusions: The available evidence suggests that users can benefit from online alcohol interventions and that this approach could be particularly useful for groups less likely to access traditional alcohol-related services, such as women, young people, and at-risk users. However, caution should be exercised given the limited number of studies allowing extraction of effect sizes, the heterogeneity of outcome measures and follow-up periods, and the large proportion of student-based studies. More extensive RCTs in community samples are required to better understand the efficacy of specific online alcohol approaches, program dosage, the additive effect of telephone or face-to-face interventions, and effective strategies for their dissemination and marketing.
- Authors: White, Angela , Kavanagh, David , Stallman, Helen , Klein, Britt , Kay-Lambkin, Frances , Proudfoot, Judith , Drennan, Judy , Connor, Jason , Baker, Amanda , Hines, Emily , Young, Ross
- Date: 2010
- Type: Text , Journal article , Review
- Relation: Journal of Medical Internet Research Vol. 12, no. 5 (2010), p. e62p.1-e62p.12
- Full Text:
- Reviewed:
- Description: Background: There has been a significant increase in the availability of online programs for alcohol problems. A systematic review of the research evidence underpinning these programs is timely. Objectives: Our objective was to review the efficacy of online interventions for alcohol misuse. Systematic searches of Medline, PsycINFO, Web of Science, and Scopus were conducted for English abstracts (excluding dissertations) published from 1998 onward. Search terms were: (1) Internet, Web*; (2) online, computer *; (3) alcohol*; and (4) Eeffect *, trial*, random* (where * denotes a wildcard). Forward and backward searches from identified papers were also conducted. Articles were included if (1) the primary intervention was delivered and accessed via the Internet, (2) the intervention focused on moderating or stopping alcohol consumption, and (3) the study was a randomized controlled trial of an alcohol-related screen, assessment, or intervention. Results: The literature search initially yielded 31 randomized controlled trials (RCTs), 17 of which met inclusion criteria. Of these 17 studies, 12 (70.6%) were conducted with university students, and 11 (64.7%) specifically focused on at-risk, heavy, or binge drinkers. Sample sizes ranged from 40 to 3216 (median 261), with 12 (70.6%) studies predominantly involving brief personalized feedback interventions. Using published data, effect sizes could be extracted from 8 of the 17 studies. In relation to alcohol units per week or month and based on 5 RCTs where a measure of alcohol units per week or month could be extracted, differential effect sizes to posttreatment ranged from 0.02 to 0.81 (mean 0.42, median 0.54). Pre-post effect sizes for brief personalized feedback interventions ranged from 0.02 to 0.81, and in 2 multi-session modularized interventions, a pre-post effect size of 0.56 was obtained in both. Pre-post differential effect sizes for peak blood alcohol concentrations (BAC) ranged from 0.22 to 0.88, with a mean effect size of 0.66. Conclusions: The available evidence suggests that users can benefit from online alcohol interventions and that this approach could be particularly useful for groups less likely to access traditional alcohol-related services, such as women, young people, and at-risk users. However, caution should be exercised given the limited number of studies allowing extraction of effect sizes, the heterogeneity of outcome measures and follow-up periods, and the large proportion of student-based studies. More extensive RCTs in community samples are required to better understand the efficacy of specific online alcohol approaches, program dosage, the additive effect of telephone or face-to-face interventions, and effective strategies for their dissemination and marketing.
- Description: Background: There has been a significant increase in the availability of online programs for alcohol problems. A systematic review of the research evidence underpinning these programs is timely. Objectives: Our objective was to review the efficacy of online interventions for alcohol misuse. Systematic searches of Medline, PsycINFO, Web of Science, and Scopus were conducted for English abstracts (excluding dissertations) published from 1998 onward. Search terms were: (1) Internet, Web*; (2) online, computer *; (3) alcohol*; and (4) E\effect *, trial*, random* (where * denotes a wildcard). Forward and backward searches from identified papers were also conducted. Articles were included if (1) the primary intervention was delivered and accessed via the Internet, (2) the intervention focused on moderating or stopping alcohol consumption, and (3) the study was a randomized controlled trial of an alcohol-related screen, assessment, or intervention. Results: The literature search initially yielded 31 randomized controlled trials (RCTs), 17 of which met inclusion criteria. Of these 17 studies, 12 (70.6%) were conducted with university students, and 11 (64.7%) specifically focused on at-risk, heavy, or binge drinkers. Sample sizes ranged from 40 to 3216 (median 261), with 12 (70.6%) studies predominantly involving brief personalized feedback interventions. Using published data, effect sizes could be extracted from 8 of the 17 studies. In relation to alcohol units per week or month and based on 5 RCTs where a measure of alcohol units per week or month could be extracted, differential effect sizes to posttreatment ranged from 0.02 to 0.81 (mean 0.42, median 0.54). Pre-post effect sizes for brief personalized feedback interventions ranged from 0.02 to 0.81, and in 2 multi-session modularized interventions, a pre-post effect size of 0.56 was obtained in both. Pre-post differential effect sizes for peak blood alcohol concentrations (BAC) ranged from 0.22 to 0.88, with a mean effect size of 0.66. Conclusions: The available evidence suggests that users can benefit from online alcohol interventions and that this approach could be particularly useful for groups less likely to access traditional alcohol-related services, such as women, young people, and at-risk users. However, caution should be exercised given the limited number of studies allowing extraction of effect sizes, the heterogeneity of outcome measures and follow-up periods, and the large proportion of student-based studies. More extensive RCTs in community samples are required to better understand the efficacy of specific online alcohol approaches, program dosage, the additive effect of telephone or face-to-face interventions, and effective strategies for their dissemination and marketing.
Time-to-event analysis for sports injury research part 2 : Time-varying outcomes
- Nielsen, Rasmus, Bertelsen, Michael, Ramskov, Daniel, Møller, Merete, Hulme, Adam, Theisen, Daniel, Finch, Caroline, Fortington, Lauren, Mansournia, Mohammad, Parner, Erik
- Authors: Nielsen, Rasmus , Bertelsen, Michael , Ramskov, Daniel , Møller, Merete , Hulme, Adam , Theisen, Daniel , Finch, Caroline , Fortington, Lauren , Mansournia, Mohammad , Parner, Erik
- Date: 2019
- Type: Text , Journal article , Review
- Relation: British Journal of Sports Medicine Vol. 53, no. 1 (2019), p. 70-78
- Full Text:
- Reviewed:
- Description: Background: Time-to-event modelling is underutilised in sports injury research. Still, sports injury researchers have been encouraged to consider time-to-event analyses as a powerful alternative to other statistical methods. Therefore, it is important to shed light on statistical approaches suitable for analysing training load related key-questions within the sports injury domain. Content: In the present article, we illuminate: (i) the possibilities of including time-varying outcomes in time-to-event analyses, (ii) how to deal with a situation where different types of sports injuries are included in the analyses (ie, competing risks), and (iii) how to deal with the situation where multiple subsequent injuries occur in the same athlete. Conclusion: Time-to-event analyses can handle time-varying outcomes, competing risk and multiple subsequent injuries. Although powerful, time-to-event has important requirements: researchers are encouraged to carefully consider prior to any data collection that five injuries per exposure state or transition is needed to avoid conducting statistical analyses on time-to-event data leading to biased results. This requirement becomes particularly difficult to accommodate when a stratified analysis is required as the number of variables increases exponentially for each additional strata included. In future sports injury research, we need stratified analyses if the target of our research is to respond to the question: 'how much change in training load is too much before injury is sustained, among athletes with different characteristics?' Responding to this question using multiple time-varying exposures (and outcomes) requires millions of injuries. This should not be a barrier for future research, but collaborations across borders to collecting the amount of data needed seems to be an important step forward.
- Authors: Nielsen, Rasmus , Bertelsen, Michael , Ramskov, Daniel , Møller, Merete , Hulme, Adam , Theisen, Daniel , Finch, Caroline , Fortington, Lauren , Mansournia, Mohammad , Parner, Erik
- Date: 2019
- Type: Text , Journal article , Review
- Relation: British Journal of Sports Medicine Vol. 53, no. 1 (2019), p. 70-78
- Full Text:
- Reviewed:
- Description: Background: Time-to-event modelling is underutilised in sports injury research. Still, sports injury researchers have been encouraged to consider time-to-event analyses as a powerful alternative to other statistical methods. Therefore, it is important to shed light on statistical approaches suitable for analysing training load related key-questions within the sports injury domain. Content: In the present article, we illuminate: (i) the possibilities of including time-varying outcomes in time-to-event analyses, (ii) how to deal with a situation where different types of sports injuries are included in the analyses (ie, competing risks), and (iii) how to deal with the situation where multiple subsequent injuries occur in the same athlete. Conclusion: Time-to-event analyses can handle time-varying outcomes, competing risk and multiple subsequent injuries. Although powerful, time-to-event has important requirements: researchers are encouraged to carefully consider prior to any data collection that five injuries per exposure state or transition is needed to avoid conducting statistical analyses on time-to-event data leading to biased results. This requirement becomes particularly difficult to accommodate when a stratified analysis is required as the number of variables increases exponentially for each additional strata included. In future sports injury research, we need stratified analyses if the target of our research is to respond to the question: 'how much change in training load is too much before injury is sustained, among athletes with different characteristics?' Responding to this question using multiple time-varying exposures (and outcomes) requires millions of injuries. This should not be a barrier for future research, but collaborations across borders to collecting the amount of data needed seems to be an important step forward.
Anxiety online-A virtual clinic: Preliminary outcomes following completion of five fully automated treatment programs for anxiety disorders and symptoms
- Klein, Britt, Meyer, Denny, Austin, David, Kyrios, Michael
- Authors: Klein, Britt , Meyer, Denny , Austin, David , Kyrios, Michael
- Date: 2011
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 13, no. 4 (2011), p.
- Full Text:
- Reviewed:
- Description: Background: The development of e-mental health interventions to treat or prevent mental illness and to enhance wellbeing has risen rapidly over the past decade. This development assists the public in sidestepping some of the obstacles that are often encountered when trying to access traditional face-to-face mental health care services. Objective: The objective of our study was to investigate the posttreatment effectiveness of five fully automated self-help cognitive behavior e-therapy programs for generalized anxiety disorder (GAD), panic disorder with or without agoraphobia (PD/A), obsessive-compulsive disorder (OCD), posttraumatic stress disorder (PTSD), and social anxiety disorder (SAD) offered to the international public via Anxiety Online, an open-access full-service virtual psychology clinic for anxiety disorders. Methods: We used a naturalistic participant choice, quasi-experimental design to evaluate each of the five Anxiety Online fully automated self-help e-therapy programs. Participants were required to have at least subclinical levels of one of the anxiety disorders to be offered the associated disorder-specific fully automated self-help e-therapy program. These programs are offered free of charge via Anxiety Online. Results: A total of 225 people self-selected one of the five e-therapy programs (GAD, n = 88; SAD, n = 50; PD/A, n = 40; PTSD, n = 30; OCD, n = 17) and completed their 12-week posttreatment assessment. Significant improvements were found on 21/25 measures across the five fully automated self-help programs. At postassessment we observed significant reductions on all five anxiety disorder clinical disorder severity ratings (Cohen d range 0.72-1.22), increased confidence in managing one's own mental health care (Cohen d range 0.70-1.17), and decreases in the total number of clinical diagnoses (except for the PD/A program, where a positive trend was found) (Cohen d range 0.45-1.08). In addition, we found significant improvements in quality of life for the GAD, OCD, PTSD, and SAD e-therapy programs (Cohen d range 0.11-0.96) and significant reductions relating to general psychological distress levels for the GAD, PD/A, and PTSD e-therapy programs (Cohen d range 0.23-1.16). Overall, treatment satisfaction was good across all five e-therapy programs, and posttreatment assessment completers reported using their e-therapy program an average of 395.60 (SD 272.2) minutes over the 12-week treatment period. Conclusions: Overall, all five fully automated self-help e-therapy programs appear to be delivering promising high-quality outcomes; however, the results require replication. © Britt Klein, Denny Meyer, David William Austin, Michael Kyrios.
- Authors: Klein, Britt , Meyer, Denny , Austin, David , Kyrios, Michael
- Date: 2011
- Type: Text , Journal article
- Relation: Journal of Medical Internet Research Vol. 13, no. 4 (2011), p.
- Full Text:
- Reviewed:
- Description: Background: The development of e-mental health interventions to treat or prevent mental illness and to enhance wellbeing has risen rapidly over the past decade. This development assists the public in sidestepping some of the obstacles that are often encountered when trying to access traditional face-to-face mental health care services. Objective: The objective of our study was to investigate the posttreatment effectiveness of five fully automated self-help cognitive behavior e-therapy programs for generalized anxiety disorder (GAD), panic disorder with or without agoraphobia (PD/A), obsessive-compulsive disorder (OCD), posttraumatic stress disorder (PTSD), and social anxiety disorder (SAD) offered to the international public via Anxiety Online, an open-access full-service virtual psychology clinic for anxiety disorders. Methods: We used a naturalistic participant choice, quasi-experimental design to evaluate each of the five Anxiety Online fully automated self-help e-therapy programs. Participants were required to have at least subclinical levels of one of the anxiety disorders to be offered the associated disorder-specific fully automated self-help e-therapy program. These programs are offered free of charge via Anxiety Online. Results: A total of 225 people self-selected one of the five e-therapy programs (GAD, n = 88; SAD, n = 50; PD/A, n = 40; PTSD, n = 30; OCD, n = 17) and completed their 12-week posttreatment assessment. Significant improvements were found on 21/25 measures across the five fully automated self-help programs. At postassessment we observed significant reductions on all five anxiety disorder clinical disorder severity ratings (Cohen d range 0.72-1.22), increased confidence in managing one's own mental health care (Cohen d range 0.70-1.17), and decreases in the total number of clinical diagnoses (except for the PD/A program, where a positive trend was found) (Cohen d range 0.45-1.08). In addition, we found significant improvements in quality of life for the GAD, OCD, PTSD, and SAD e-therapy programs (Cohen d range 0.11-0.96) and significant reductions relating to general psychological distress levels for the GAD, PD/A, and PTSD e-therapy programs (Cohen d range 0.23-1.16). Overall, treatment satisfaction was good across all five e-therapy programs, and posttreatment assessment completers reported using their e-therapy program an average of 395.60 (SD 272.2) minutes over the 12-week treatment period. Conclusions: Overall, all five fully automated self-help e-therapy programs appear to be delivering promising high-quality outcomes; however, the results require replication. © Britt Klein, Denny Meyer, David William Austin, Michael Kyrios.
- «
- ‹
- 1
- ›
- »