liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 17) Show all publications
Müssener, U., Andersson, E. K., Linderoth, C., Leijon, M. E. & Bendtsen, M. (2018). A Text Message-Based Intervention Targeting Alcohol Consumption Among University Students: User Satisfaction and Acceptability Study.. JMIR Human Factors, 5(3), Article ID e23.
Open this publication in new window or tab >>A Text Message-Based Intervention Targeting Alcohol Consumption Among University Students: User Satisfaction and Acceptability Study.
Show others...
2018 (English)In: JMIR Human Factors, E-ISSN 2292-9495, Vol. 5, no 3, article id e23Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: Heavy consumption of alcohol among university students is a global problem, with excessive drinking being the social norm. Students can be a difficult target group to reach, and only a minority seek alcohol-related support. It is important to develop interventions that can reach university students in a way that does not further stretch the resources of the health services. Text messaging (short message service, SMS)-based interventions can enable continuous, real-time, cost-effective, brief support in a real-world setting, but there is a limited amount of evidence for effective interventions on alcohol consumption among young people based on text messaging. To address this, a text messaging-based alcohol consumption intervention, the Amadeus 3 intervention, was developed.

OBJECTIVE: This study explored self-reported changes in drinking habits in an intervention group and a control group. Additionally, user satisfaction among the intervention group and the experience of being allocated to a control group were explored.

METHODS: Students allocated to the intervention group (n=460) were asked about their drinking habits and offered the opportunity to give their opinion on the structure and content of the intervention. Students in the control group (n=436) were asked about their drinking habits and their experience in being allocated to the control group. Participants received an email containing an electronic link to a short questionnaire. Descriptive analyses of the distribution of the responses to the 12 questions for the intervention group and 5 questions for the control group were performed.

RESULTS: The response rate for the user feedback questionnaire of the intervention group was 38% (176/460) and of the control group was 30% (129/436). The variation in the content of the text messages from facts to motivational and practical advice was appreciated by 77% (135/176) participants, and 55% (97/176) found the number of messages per week to be adequate. Overall, 81% (142/176) participants stated that they had read all or nearly all the messages, and 52% (91/176) participants stated that they were drinking less, and increased awareness regarding negative consequences was expressed as the main reason for reduced alcohol consumption. Among the participants in the control group, 40% (52/129) stated that it did not matter that they had to wait for access to the intervention. Regarding actions taken while waiting for access, 48% (62/129) participants claimed that they continued to drink as before, whereas 35% (45/129) tried to reduce their consumption without any support.

CONCLUSIONS: Although the main randomized controlled trial was not able to detect a statistically significant effect of the intervention, most participants in this qualitative follow-up study stated that participation in the study helped them reflect upon their consumption, leading to altered drinking habits and reduced alcohol consumption.

TRIAL REGISTRATION: International Standard Randomized Controlled Trial Number ISRCTN95054707; http://www.isrctn.com/ISRCTN95054707 (Archived by WebCite at http://www.webcitation.org/705putNZT).

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2018
Keywords
SMS, alcohol consumption intervention, mobile phones, students, text messages
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-153600 (URN)10.2196/humanfactors.9641 (DOI)29991469 (PubMedID)2-s2.0-85052017018 (Scopus ID)
Available from: 2018-12-27 Created: 2018-12-27 Last updated: 2019-05-02Bibliographically approved
Thomas, K., Müssener, U., Linderoth, C., Karlsson, N., Bendtsen, P. & Bendtsen, M. (2018). Effectiveness of a Text Messaging-Based Intervention Targeting Alcohol Consumption Among University Students: Randomized Controlled Trial. JMIR mhealth and uhealth, 6(6), Article ID e146.
Open this publication in new window or tab >>Effectiveness of a Text Messaging-Based Intervention Targeting Alcohol Consumption Among University Students: Randomized Controlled Trial
Show others...
2018 (English)In: JMIR mhealth and uhealth, E-ISSN 2291-5222, Vol. 6, no 6, article id e146Article in journal (Refereed) Published
Abstract [en]

Background: Excessive drinking among university students is a global challenge, leading to significant health risks. However, heavy drinking among students is widely accepted and socially normalized. Mobile phone interventions have attempted to reach students who engage in excessive drinking. A growing number of studies suggest that text message-based interventions could potentially reach many students and, if effective, such an intervention might help reduce heavy drinking in the student community. Objective: The objective of this study was to test the effectiveness of a behavior change theory-based 6-week text message intervention among university students. Methods: This study was a two-arm, randomized controlled trial with an intervention group receiving a 6-week text message intervention and a control group that was referred to treatment as usual at the local student health care center. Outcome measures were collected at baseline and at 3 months after the initial invitation to participate in the intervention. The primary outcome was total weekly alcohol consumption. Secondary outcomes were frequency of heavy episodic drinking, highest estimated blood alcohol concentration, and number of negative consequences attributable to excessive drinking. Results: A total of 896 students were randomized to either the intervention or control group. The primary outcome analysis included 92.0% of the participants in the intervention group and 90.1% of the control group. At follow-up, total weekly alcohol consumption decreased in both groups, but no significant between-group difference was seen. Data on the secondary outcomes included 49.1% of the participants in the intervention group and 41.3% of the control group. No significant between-group difference was seen for any of the secondary outcomes. Conclusions: The present study was under-powered, which could partly explain the lack of significance. However, the intervention, although theory-based, needs to be re-assessed and refined to better support the target group. Apart from establishing which content forms an effective intervention, the optimal length of an alcohol intervention targeting students also needs to be addressed in future studies.

Place, publisher, year, edition, pages
JMIR PUBLICATIONS, INC, 2018
Keywords
alcohol consumption intervention; text message-based intervention; university students; brief intervention
National Category
Substance Abuse
Identifiers
urn:nbn:se:liu:diva-149731 (URN)10.2196/mhealth.9642 (DOI)000436207100005 ()29941417 (PubMedID)
Note

Funding Agencies|Public Health Agency in Sweden [05670-2014-6.2]

Available from: 2018-07-24 Created: 2018-07-24 Last updated: 2019-04-03
Bendtsen, M. & Peña, J. M. (2017). Modelling regimes with Bayesian network mixtures. In: Niklas Lavesson (Ed.), Proceedings of the 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden: . Paper presented at The 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden (pp. 20-29). Linköping: Linköping University Electronic Press, 137, Article ID 002.
Open this publication in new window or tab >>Modelling regimes with Bayesian network mixtures
2017 (English)In: Proceedings of the 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden / [ed] Niklas Lavesson, Linköping: Linköping University Electronic Press, 2017, Vol. 137, p. 20-29, article id 002Conference paper, Published paper (Refereed)
Abstract [en]

Bayesian networks (BNs) are advantageous when representing single independence models, however they do not allow us to model changes among the relationships of the random variables over time. Due to such regime changes, it may be necessary to use different BNs at different times in order to have an appropriate model over the random variables. In this paper we propose two extensions to the traditional hidden Markov model, allowing us to represent both the different regimes using different BNs, and potential driving forces behind the regime changes, by modelling potential dependence between state transitions and some observable variables. We show how expectation maximisation can be used to learn the parameters of the proposed model, and run both synthetic and real-world experiments to show the model’s potential.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2017
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 137
Keywords
Bayesian networks, hidden Markov models, regimes, algorithmic trading
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-137664 (URN)9789176854969 (ISBN)
Conference
The 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden
Available from: 2017-05-24 Created: 2017-05-24 Last updated: 2019-07-04Bibliographically approved
Bendtsen, M. (2017). Regimes in baseball players' career data. Data mining and knowledge discovery, 31(6), 1580-1621
Open this publication in new window or tab >>Regimes in baseball players' career data
2017 (English)In: Data mining and knowledge discovery, ISSN 1384-5810, E-ISSN 1573-756X, Vol. 31, no 6, p. 1580-1621Article in journal (Refereed) Published
Abstract [en]

In this paper we investigate how we can use gated Bayesian networks, a type of probabilistic graphical model, to represent regimes in baseball players’ career data. We find that baseball players do indeed go through different regimes throughout their career, where each regime can be associated with a certain level of performance. We show that some of the transitions between regimes happen in conjunction with major events in the players’ career, such as being traded or injured, but that some transitions cannot be explained by such events. The resulting model is a tool for managers and coaches that can be used to identify where transitions have occurred, as well as an online monitoring tool to detect which regime the player currently is in.

Place, publisher, year, edition, pages
Springer-Verlag New York, 2017
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-141031 (URN)10.1007/s10618-017-0510-5 (DOI)000412342000002 ()2-s2.0-85019679633 (Scopus ID)
Available from: 2017-09-20 Created: 2017-09-20 Last updated: 2018-01-13Bibliographically approved
Müssener, U., Bendtsen, M., Karlsson, N., White, I. R., Mccambridge, J. & Bendtsen, P. (2016). Effectiveness of Short Message Service Text-Based Smoking Cessation Intervention Among University Students A Randomized Clinical Trial. JAMA Internal Medicine, 176(3), 321-328
Open this publication in new window or tab >>Effectiveness of Short Message Service Text-Based Smoking Cessation Intervention Among University Students A Randomized Clinical Trial
Show others...
2016 (English)In: JAMA Internal Medicine, ISSN 2168-6106, E-ISSN 2168-6114, Vol. 176, no 3, p. 321-328Article in journal (Refereed) Published
Abstract [en]

IMPORTANCE Smoking is globally the most important preventable cause of ill health and death. Mobile telephone interventions and, in particular, short message service (SMS) text messaging, have the potential to overcome access barriers to traditional health services, not least among young people. OBJECTIVE To determine the effectiveness of a text-based smoking cessation intervention among young people. DESIGN, SETTING, AND PARTICIPANTS A single-blind, 2-arm, randomized clinical trial (Nicotine Exit [NEXit]) was conducted from October 23, 2014, to April 17, 2015; data analysis was performed from April 23, 2014, to May 22, 2015. Participants included daily or weekly smokers willing to set a quit date within 1 month of enrollment. The study used email to invite all college and university students throughout Sweden to participate. INTERVENTIONS The NEXit core program is initiated with a 1- to 4-week motivational phase during which participants can choose to set a stop date. The intervention group then received 157 text messages based on components of effective smoking cessation interventions for 12 weeks. The control group received 1 text every 2 weeks thanking them for participating in the study, with delayed access to the intervention. MAIN OUTCOMES AND MEASURES The primary outcomes were self-reported prolonged abstinence (not having smoked >5 cigarettes over the past 8 weeks) and 4-week point prevalence of complete smoking cessation shortly after the completion of the intervention (approximately 4 months after the quit date). RESULTS A total of 1590 participants, mainly between 21 and 30 years of age, were randomized into the study; 827 (573 [69.3%] women) were allocated to the intervention group and 763 (522 [68.4%] women) were included in the control group. Primary outcome data were available for 783 (94.7%) of the intervention group and 719 (94.2%) of the control group. At baseline, participants were smoking a median (range) of 63 (1-238) and 70 (2-280) cigarettes per week, respectively. Eight-week prolonged abstinence was reported by 203 participants (25.9%) in the intervention group and 105 (14.6%) in the control group; 4-week point prevalence of complete cessation was reported by 161 (20.6%) and 102 (14.2%) participants, respectively, a mean (SD) of 3.9 (0.37) months after the quit date. The adjusted odds ratios (95% CIs) for these findings were 2.05 (1.57-2.67) and 1.56 (1.19-2.05), respectively. CONCLUSIONS AND RELEVANCE With the limitation of assessing only the short-term effect of the intervention, the effects observed in this trial are comparable with those for traditional smoking cessation interventions. The simple NEXit intervention has the potential to improve the uptake of effective smoking cessation interventions.

Place, publisher, year, edition, pages
AMER MEDICAL ASSOC, 2016
National Category
Basic Medicine Computer and Information Sciences
Identifiers
urn:nbn:se:liu:diva-127282 (URN)10.1001/jamainternmed.2015.8260 (DOI)000372302500008 ()26903176 (PubMedID)
Note

Funding Agencies|Swedish Research Council [521-2012-2865]; Swedish Medical Research Council [U105260558]

Available from: 2016-04-20 Created: 2016-04-19 Last updated: 2018-01-10
Bendtsen, M. & Peña, J. M. (2016). Gated Bayesian Networks for Algorithmic Trading. International Journal of Approximate Reasoning, 69, 58-80
Open this publication in new window or tab >>Gated Bayesian Networks for Algorithmic Trading
2016 (English)In: International Journal of Approximate Reasoning, ISSN 0888-613X, E-ISSN 1873-4731, Vol. 69, p. 58-80Article in journal (Refereed) Published
Abstract [en]

Gated Bayesian networks (GBNs) are a recently introduced extension of Bayesian networks that aims to model dynamical systems consisting of several distinct phases. In this paper, we present an algorithm for semi-automatic learning of GBNs. We use the algorithm to learn GBNs that output buy and sell decisions for use in algorithmic trading systems. We show how using the learnt GBNs can substantially lower risks towards invested capital, while at the same time generating similar or better rewards, compared to the benchmark investment strategy buy-and-hold.

Place, publisher, year, edition, pages
Elsevier: , 2016
Keywords
Probabilistic graphical models, Bayesian networks, algorithmic
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-124066 (URN)10.1016/j.ijar.2015.11.002 (DOI)000368957000004 ()
Note

Funding agencies: Center for Industrial Information Technology, Linkoping University (CENIIT) [09.01]; Swedish Research Council [2010-4808]

Available from: 2016-01-19 Created: 2016-01-19 Last updated: 2018-01-10
Bendtsen, M. (2015). Bayesian Optimisation of Gated Bayesian Networks for Algorithmic Trading. In: John Mark Agosta, Rommel Novaes Carvalho (Ed.), : . Paper presented at Twelfth UAI Bayesian Modeling Applications Workshop, (BMAW 2015), Amsterdam, The Netherlands, July 16, 2015 (pp. 2-11). CEUR-WS.org, 1565
Open this publication in new window or tab >>Bayesian Optimisation of Gated Bayesian Networks for Algorithmic Trading
2015 (English)In: / [ed] John Mark Agosta, Rommel Novaes Carvalho, CEUR-WS.org , 2015, Vol. 1565, p. 2-11Conference paper, Published paper (Refereed)
Abstract [en]

Gated Bayesian networks (GBNs) are an extension of Bayesian networks that aim to model systems that have distinct phases. In this paper, we aim to use GBNs to output buy and sell decisions for use in algorithmic trading systems. These systems may have several parameters that require tuning, and assessing the performance of these systems as a function of their parameters cannot be expressed in closed form, and thus requires simulation. Bayesian optimisation has grown in popularity as a means of global optimisation of parameters where the objective function may be costly or a black box. We show how algorithmic trading using GBNs, supported by Bayesian optimisation, can lower risk towards invested capital, while at the same time generating similar or better rewards, compared to the benchmark investment strategy buy-and-hold.

Place, publisher, year, edition, pages
CEUR-WS.org, 2015
Series
CEUR Workshop Proceedings, ISSN 1613-0073
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-120685 (URN)
Conference
Twelfth UAI Bayesian Modeling Applications Workshop, (BMAW 2015), Amsterdam, The Netherlands, July 16, 2015
Available from: 2015-08-20 Created: 2015-08-20 Last updated: 2018-01-11Bibliographically approved
Bendtsen, P., Bendtsen, M., Karlsson, N., White, I. R. & McCambridge, J. (2015). Online Alcohol Assessment and Feedback for Hazardous and Harmful Drinkers: Findings From the AMADEUS-2 Randomized Controlled Trial of Routine Practice in Swedish Universities. Journal of Medical Internet Research, 17(7), e170
Open this publication in new window or tab >>Online Alcohol Assessment and Feedback for Hazardous and Harmful Drinkers: Findings From the AMADEUS-2 Randomized Controlled Trial of Routine Practice in Swedish Universities
Show others...
2015 (English)In: Journal of Medical Internet Research, ISSN 1438-8871, E-ISSN 1438-8871, Vol. 17, no 7, p. e170-Article in journal (Refereed) Published
Abstract [en]

Background: Previous research on the effectiveness of online alcohol interventions for college students has shown mixed results. Small benefits have been found in some studies and because online interventions are inexpensive and possible to implement on a large scale, there is a need for further study. Objective: This study evaluated the effectiveness of national provision of a brief online alcohol intervention for students in Sweden. Methods: Risky drinkers at 9 colleges and universities in Sweden were invited by mail and identified using a single screening question. These students (N=1605) gave consent and were randomized into a 2-arm parallel group randomized controlled trial consisting of immediate or delayed access to a fully automated online assessment and intervention with personalized feedback. Results: After 2 months, there was no strong evidence of effectiveness with no statistically significant differences in the planned analyses, although there were some indication of possible benefit in sensitivity analyses suggesting an intervention effect of a 10% reduction (95% CI -30% to 10%) in total weekly alcohol consumption. Also, differences in effect sizes between universities were seen with participants from a major university (n=365) reducing their weekly alcohol consumption by 14% (95% CI -23% to -4%). However, lower recruitment than planned and differential attrition in the intervention and control group (49% vs 68%) complicated interpretation of the outcome data. Conclusions: Any effects of current national provision are likely to be small and further research and development work is

Place, publisher, year, edition, pages
Journal of Medical Internet Research / JMIR Publications, 2015
Keywords
alcohol drinking; behavior therapy; students; Internet; electronic mail; feedback
National Category
Basic Medicine Computer and Information Sciences
Identifiers
urn:nbn:se:liu:diva-120461 (URN)10.2196/jmir.4020 (DOI)000358010200001 ()26159179 (PubMedID)
Note

Funding Agencies|Swedish Council for Working Life and Social Research (FAS, in Swedish) [2010-0024]; Wellcome Trust Research Career Development fellowship in Basic Biomedical Science [WT086516MA]; Medical Research Council [U105260558]

Available from: 2015-08-12 Created: 2015-08-11 Last updated: 2018-01-11
Müssener, U., Bendtsen, M., Karlsson, N., White, I. R., McCambridge, J. & Bendtsen, P. (2015). SMS-based smoking cessation intervention among university students: study protocol for a randomised controlled trial (NEXit trial). Trials, 16, Article ID 140.
Open this publication in new window or tab >>SMS-based smoking cessation intervention among university students: study protocol for a randomised controlled trial (NEXit trial)
Show others...
2015 (English)In: Trials, ISSN 1745-6215, E-ISSN 1745-6215, Vol. 16, article id 140Article in journal (Refereed) Published
Abstract [en]

Background: Most smoking efforts targeting young people have so far been focused on prevention of initiation, whereas smoking cessation interventions have largely been targeted towards adult populations. Thus, there is limited evidence for effective smoking cessation interventions in young people, even though many young people want to quit smoking. Mobile communication technology has the potential to reach large numbers of young people and recent text-based smoking cessation interventions using phones have shown promising results. Methods/design: The study aims to evaluate a newly developed text-based smoking cessation intervention for students in colleges and universities in Sweden. The design is a randomised controlled trial (RCT) with a delayed/waiting list intervention control condition. The trial will be performed simultaneously in all colleges and universities served by 25 student health care centres in Sweden. Outcomes will be evaluated after 4 months, with 2 cessation primary outcomes and 4 secondary outcomes. After outcome evaluation the control group will be given access to the intervention. Discussion: The study will examine the effectiveness of a stand-alone SMS text-based intervention. The intervention starts with a motivational phase in which the participants are given an opportunity to set a quit date within 4 weeks of randomisation. This first phase and the subsequent core intervention phase of 12 weeks are totally automated in order to easily integrate the intervention into the daily routines of student and other health care settings. As well as providing data for the effectiveness of the intervention, the study will also provide data for methodological analyses addressing a number issues commonly challenging in Internet-based RCTs. For example, an extensive follow-up strategy will be used in order to evaluate the use of repeated attempts in the analysis, and in particular to explore the validity of a possible missing not at random assumption that the odds ratio between the primary outcome and response is the same at every attempt.

Place, publisher, year, edition, pages
BioMed Central, 2015
Keywords
: Tobacco, Smoking cessation, Students, Text messages, Mobile phones, SMS
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-117550 (URN)10.1186/s13063-015-0640-2 (DOI)000353116200001 ()25872503 (PubMedID)
Available from: 2015-05-04 Created: 2015-05-04 Last updated: 2017-12-04
Bendtsen, M. & Bendtsen, P. (2014). Feasibility and user perception of a fully automated push-based multiple-session alcohol intervention for university students: randomized controlled trial.. JMIR mhealth and uhealth, 2(2), e30
Open this publication in new window or tab >>Feasibility and user perception of a fully automated push-based multiple-session alcohol intervention for university students: randomized controlled trial.
2014 (English)In: JMIR mhealth and uhealth, E-ISSN 2291-5222, Vol. 2, no 2, p. e30-Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: In recent years, many electronic health behavior interventions have been developed in order to reach individuals with unhealthy behaviors, such as risky drinking. This is especially relevant for university students, many of whom are risky drinkers.

OBJECTIVE: This study explored the acceptability and feasibility in a nontreatment-seeking group of university students (including both risk and nonrisk drinkers), of a fully automated, push-based, multiple-session, alcohol intervention, comparing two modes of delivery by randomizing participants to receive the intervention either by SMS text messaging (short message service, SMS) or by email.

METHODS: A total of 5499 students at Luleå University in northern Sweden were invited to participate in a single-session alcohol assessment and feedback intervention; 28.04% (1542/5499) students completed this part of the study. In total, 29.44% (454/1542) of those participating in the single-session intervention accepted to participate further in the extended multiple-session intervention lasting for 4 weeks. The students were randomized to receive the intervention messages via SMS or email. A follow-up questionnaire was sent immediately after the intervention and 52.9% (240/454) responded.

RESULTS: No difference was seen regarding satisfaction with the length and frequency of the intervention, regardless of the mode of delivery. Approximately 15% in both the SMS (19/136) and email groups (15/104) would have preferred the other mode of delivery. On the other hand, more students in the SMS group (46/229, 20.1%) stopped participating in the intervention during the 4-week period compared with the email group (10/193, 5.2%). Most students in both groups expressed satisfaction with the content of the messages and would recommend the intervention to a fellow student in need of reducing drinking. A striking difference was seen regarding when a message was read; 88.2% (120/136) of the SMS group read the messages within 1 hour in contrast to 45.2% (47/104) in the email group. In addition, 83.1% (113/136) in the SMS group stated that they read all or almost all the messages, compared with only 63.5% (66/104) in the email group.

CONCLUSIONS: Based on the feedback from the students, an extended, multiple-session, push-based intervention seems to be a feasible option for students interested in additional support after a single-session alcohol intervention. SMS as a mode of delivery seems to have some advantages over email regarding when a message is read and the proportion of messages read. However, more students in the SMS group stopped the intervention than in the email group. Based on these promising findings, further studies comparing the effectiveness of single-session interventions with extended multiple-session interventions delivered separately or in combination are warranted.

Place, publisher, year, edition, pages
JMIR Publications, 2014
National Category
Computer and Information Sciences Health Sciences
Identifiers
urn:nbn:se:liu:diva-115372 (URN)10.2196/mhealth.3233 (DOI)000209895000005 ()25098296 (PubMedID)
Available from: 2015-03-13 Created: 2015-03-13 Last updated: 2018-01-11
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-8678-1164

Search in DiVA

Show all publications