Predicting Therapy Success and Costs for Personalized Treatment Recommendations Using Baseline Characteristics: Data-Driven Analysis

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Predicting Therapy Success and Costs for Personalized Treatment Recommendations Using Baseline Characteristics: Data-Driven Analysis. / Bremer, Vincent; Becker, Dennis; Kolovos, S. et al.
in: Journal of Medical Internet Research, Jahrgang 20, Nr. 8, e10275, 21.08.2018.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{17ddaad6a1b44328b5be15cdb224b62b,
title = "Predicting Therapy Success and Costs for Personalized Treatment Recommendations Using Baseline Characteristics: Data-Driven Analysis",
abstract = "Background: Different treatment alternatives exist for psychological disorders. Both clinical and cost effectiveness of treatment are crucial aspects for policy makers, therapists, and patients and thus play major roles for healthcare decision-making. At the start of an intervention, it is often not clear which specific individuals benefit most from a particular intervention alternative or how costs will be distributed on an individual patient level.Objective: This study aimed at predicting the individual outcome and costs for patients before the start of an internet-based intervention. Based on these predictions, individualized treatment recommendations can be provided. Thus, we expand the discussion of personalized treatment recommendation.Methods: Outcomes and costs were predicted based on baseline data of 350 patients from a two-arm randomized controlled trial that compared treatment as usual and blended therapy for depressive disorders. For this purpose, we evaluated various machine learning techniques, compared the predictive accuracy of these techniques, and revealed features that contributed most to the prediction performance. We then combined these predictions and utilized an incremental cost-effectiveness ratio in order to derive individual treatment recommendations before the start of treatment.Results: Predicting clinical outcomes and costs is a challenging task that comes with high uncertainty when only utilizing baseline information. However, we were able to generate predictions that were more accurate than a predefined reference measure in the shape of mean outcome and cost values. Questionnaires that include anxiety or depression items and questions regarding the mobility of individuals and their energy levels contributed to the prediction performance. We then described how patients can be individually allocated to the most appropriate treatment type. For an incremental cost-effectiveness threshold of 25,000 €/quality-adjusted life year, we demonstrated that our recommendations would have led to slightly worse outcomes (1.98%), but with decreased cost (5.42%).Conclusions: Our results indicate that it was feasible to provide personalized treatment recommendations at baseline and thus allocate patients to the most beneficial treatment type. This could potentially lead to improved decision-making, better outcomes for individuals, and reduced health care costs.",
keywords = "Business informatics, treatment recommendation, cost effectiveness,mental health,machine learning, treatment recommendation, cost effectiveness, mental health, machine learning",
author = "Vincent Bremer and Dennis Becker and S. Kolovos and Burkhardt Funk and {van Breda}, Ward and Mark Hoogendoorn and Heleen Riper",
note = "Publisher Copyright: {\textcopyright} Vincent Bremer, Dennis Becker, Spyros Kolovos, Burkhardt Funk, Ward van Breda, Mark Hoogendoorn, Heleen Riper. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 21.08.2018. This is an open-access article distributed under the terms of the Creative Commons Attribution License.",
year = "2018",
month = aug,
day = "21",
doi = "10.2196/10275",
language = "English",
volume = "20",
journal = "Journal of Medical Internet Research",
issn = "1439-4456",
publisher = "JMIR Publications Inc.",
number = "8",

}

RIS

TY - JOUR

T1 - Predicting Therapy Success and Costs for Personalized Treatment Recommendations Using Baseline Characteristics

T2 - Data-Driven Analysis

AU - Bremer, Vincent

AU - Becker, Dennis

AU - Kolovos, S.

AU - Funk, Burkhardt

AU - van Breda, Ward

AU - Hoogendoorn, Mark

AU - Riper, Heleen

N1 - Publisher Copyright: © Vincent Bremer, Dennis Becker, Spyros Kolovos, Burkhardt Funk, Ward van Breda, Mark Hoogendoorn, Heleen Riper. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 21.08.2018. This is an open-access article distributed under the terms of the Creative Commons Attribution License.

PY - 2018/8/21

Y1 - 2018/8/21

N2 - Background: Different treatment alternatives exist for psychological disorders. Both clinical and cost effectiveness of treatment are crucial aspects for policy makers, therapists, and patients and thus play major roles for healthcare decision-making. At the start of an intervention, it is often not clear which specific individuals benefit most from a particular intervention alternative or how costs will be distributed on an individual patient level.Objective: This study aimed at predicting the individual outcome and costs for patients before the start of an internet-based intervention. Based on these predictions, individualized treatment recommendations can be provided. Thus, we expand the discussion of personalized treatment recommendation.Methods: Outcomes and costs were predicted based on baseline data of 350 patients from a two-arm randomized controlled trial that compared treatment as usual and blended therapy for depressive disorders. For this purpose, we evaluated various machine learning techniques, compared the predictive accuracy of these techniques, and revealed features that contributed most to the prediction performance. We then combined these predictions and utilized an incremental cost-effectiveness ratio in order to derive individual treatment recommendations before the start of treatment.Results: Predicting clinical outcomes and costs is a challenging task that comes with high uncertainty when only utilizing baseline information. However, we were able to generate predictions that were more accurate than a predefined reference measure in the shape of mean outcome and cost values. Questionnaires that include anxiety or depression items and questions regarding the mobility of individuals and their energy levels contributed to the prediction performance. We then described how patients can be individually allocated to the most appropriate treatment type. For an incremental cost-effectiveness threshold of 25,000 €/quality-adjusted life year, we demonstrated that our recommendations would have led to slightly worse outcomes (1.98%), but with decreased cost (5.42%).Conclusions: Our results indicate that it was feasible to provide personalized treatment recommendations at baseline and thus allocate patients to the most beneficial treatment type. This could potentially lead to improved decision-making, better outcomes for individuals, and reduced health care costs.

AB - Background: Different treatment alternatives exist for psychological disorders. Both clinical and cost effectiveness of treatment are crucial aspects for policy makers, therapists, and patients and thus play major roles for healthcare decision-making. At the start of an intervention, it is often not clear which specific individuals benefit most from a particular intervention alternative or how costs will be distributed on an individual patient level.Objective: This study aimed at predicting the individual outcome and costs for patients before the start of an internet-based intervention. Based on these predictions, individualized treatment recommendations can be provided. Thus, we expand the discussion of personalized treatment recommendation.Methods: Outcomes and costs were predicted based on baseline data of 350 patients from a two-arm randomized controlled trial that compared treatment as usual and blended therapy for depressive disorders. For this purpose, we evaluated various machine learning techniques, compared the predictive accuracy of these techniques, and revealed features that contributed most to the prediction performance. We then combined these predictions and utilized an incremental cost-effectiveness ratio in order to derive individual treatment recommendations before the start of treatment.Results: Predicting clinical outcomes and costs is a challenging task that comes with high uncertainty when only utilizing baseline information. However, we were able to generate predictions that were more accurate than a predefined reference measure in the shape of mean outcome and cost values. Questionnaires that include anxiety or depression items and questions regarding the mobility of individuals and their energy levels contributed to the prediction performance. We then described how patients can be individually allocated to the most appropriate treatment type. For an incremental cost-effectiveness threshold of 25,000 €/quality-adjusted life year, we demonstrated that our recommendations would have led to slightly worse outcomes (1.98%), but with decreased cost (5.42%).Conclusions: Our results indicate that it was feasible to provide personalized treatment recommendations at baseline and thus allocate patients to the most beneficial treatment type. This could potentially lead to improved decision-making, better outcomes for individuals, and reduced health care costs.

KW - Business informatics

KW - treatment recommendation, cost effectiveness,mental health,machine learning

KW - treatment recommendation

KW - cost effectiveness

KW - mental health

KW - machine learning

UR - http://www.jmir.org/2018/8/e10275/

UR - http://www.scopus.com/inward/record.url?scp=85052857433&partnerID=8YFLogxK

U2 - 10.2196/10275

DO - 10.2196/10275

M3 - Journal articles

C2 - 30131318

VL - 20

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1439-4456

IS - 8

M1 - e10275

ER -

Dokumente

DOI

Zuletzt angesehen

Aktivitäten

  1. Towards more radical forms of governance for business and human rights: From management practice to management education
  2. The generalizability of instructional leadership and student achievement across contexts: A meta-analytical big data study
  3. Roe deer browsing induces changes in phytohormones, primary metabolites and defense chemistry in beech and maple saplings
  4. Machbarkeitsstudie "Fluglärm und Lebensqualität": Methodenstudie im Auftrag des Regionalen Dialogforums Flughafen Frankfurt
  5. Transparenz und Selbstschutz in konfliktiven Forschungsfeldern – Reflektionen aus dem Forschungsprojekt „Alltag im Dissens“
  6. Bildung und Betreuung im Fokus der Wissenschaft - Aktuelle Diskussionen und Forschungsbefunde mit dem Schwerpunkt Ganztag
  7. 3rd International Conference on Innovations in Bio-Inspired Computing and Applications: Program Committee Member - IBICA2012
  8. Freiheit, die ich meine: Zum Wahlverhalten in fachübergreifenden Studienangeboten – Nomothetische und ideographische Zugänge
  9. Erfolgsfaktor Mensch im digitalen Zeitalter Jahresforum für NPOs, öffentliche Verwaltung, Stiftungen und Sozialunternehmen
  10. “Man that is so funny” – Negotiating group membership through humour rejection among members of a professional football team.
  11. Die Kompetenzentwicklung von Lehramtsstudierenden im inklusiven naturwissenschaftlichen Unterricht videobasiert erforschen
  12. Arbeitszeitflexibilität und Zufriedenheit, The evvect of transition to flexible working hous on job satisfaction in Germany
  13. Arbeitszeitflexibilität und Zufriedenheit, The effect of transition to flesible working hous on job satisfaction in Germany
  14. Going Green: Digital project work as a transdisciplinary and transcultural task in the foreign language and STEM classrooms
  15. International Conference on Advances in Social Network Analysis and Mining: Member of Program Committee - ASONAM IEEE/ACM 2013

Publikationen

  1. Leuphana Lernwerkstatt Lüneburg – multifunktionelle Ausrichtung eines inklusiven naturwissenschaftlichen Lehr-Lern-Raums
  2. Von Kalfelis zu Brogsitter - Künftig enge Grenzen der Annexkompetenz im europäischen Vertrags- und Deliktsgerichtsstand
  3. Jugenddelinquenz in der Bundesrepublik Deutschland und den Vereinigten Staaten von Amerika nach dem Zweiten Weltkrieg
  4. Local and landscape level variables influence butterfly diversity in critically endangered South African renosterveld
  5. Neon ist ein Gas und hat zwei Ringe – Zur Trennung der makroskopischen und submikroskopischen Ebene des Periodensystems
  6. Biodegradability and genotoxicity of surface functionalized colloidal silica (SiO2) particles in the aquatic environment
  7. Nachhaltigkeit und Geschlechtergerechtigkeit - ein sperriges und zugleich unverzichtbares Feld für Zukunftsentwicklungen
  8. Rezension von Voigt, Christian/Kreiml, Thomas (Hrsg.): Soziale Bewegungen und Social Media. Handbuch für den Einsatz von Web 2.0
  9. Helfen Bürgerbeteiligungen bei der Finanzierung von Erneuerbare-Energien-Vorhaben kommunaler Energieversorgungsunternehmen?
  10. Comprehensive Package of Climate Protection Measures Could Substantially Decrease Cost of Emission Reductions in Germany
  11. Aufgabeninterdependenzen und Emotionen bei der Arbeit – Ansatzpunkte für eine vollständigere Analyse psychischer Belastung?
  12. Sonderbetriebsvermögen II bei Personengesellschaften (Kommentierung des BFH-Urteils vom 10.06.1999, IV R 21/98), Fach 3 EStG, § 15
  13. Access to Information on Legislative Proceedings - Case Note on Judgment of the Court (2nd Chamber) of 18 July 2013 - C 515/11
  14. Metabolites and Transformation Products of Pharmaceuticals in the Aquatic Environment as Contaminants of Emerging Concern