A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis

Simple item page
dc.contributor.authorVerboven, Lennert
dc.contributor.authorCalders, Toon
dc.contributor.authorCallens, Steven
dc.contributor.authorBlack, John
dc.contributor.authorMaartens, Gary
dc.contributor.authorDooley, Kelly E
dc.contributor.authorPotgieter, Samantha
dc.contributor.authorWarren, Robin M
dc.contributor.authorLaukens, Kris
dc.contributor.authorVan Rie, Annelies
dc.date.accessioned2022-04-11T21:15:15Z
dc.date.available2022-04-11T21:15:15Z
dc.date.issued2022-03-02
dc.date.updated2022-03-06T04:09:30Z
dc.description.abstractBackground Personalized medicine tailors care based on the patient’s or pathogen’s genotypic and phenotypic characteristics. An automated Clinical Decision Support System (CDSS) could help translate the genotypic and phenotypic characteristics into optimal treatment and thus facilitate implementation of individualized treatment by less experienced physicians. Methods We developed a hybrid knowledge- and data-driven treatment recommender CDSS. Stakeholders and experts first define the knowledge base by identifying and quantifying drug and regimen features for the prototype model input. In an iterative manner, feedback from experts is harvested to generate model training datasets, machine learning methods are applied to identify complex relations and patterns in the data, and model performance is assessed by estimating the precision at one, mean reciprocal rank and mean average precision. Once the model performance no longer iteratively increases, a validation dataset is used to assess model overfitting. Results We applied the novel methodology to develop a treatment recommender CDSS for individualized treatment of drug resistant tuberculosis as a proof of concept. Using input from stakeholders and three rounds of expert feedback on a dataset of 355 patients with 129 unique drug resistance profiles, the model had a 95% precision at 1 indicating that the highest ranked treatment regimen was considered appropriate by the experts in 95% of cases. Use of a validation data set however suggested substantial model overfitting, with a reduction in precision at 1 to 78%. Conclusion Our novel and flexible hybrid knowledge- and data-driven treatment recommender CDSS is a first step towards the automation of individualized treatment for personalized medicine. Further research should assess its value in fields other than drug resistant tuberculosis, develop solid statistical approaches to assess model performance, and evaluate their accuracy in real-life clinical settings.en_US
dc.identifier.apacitationVerboven, L., Calders, T., Callens, S., Black, J., Maartens, G., Dooley, K. E., ... Van Rie, A. (2022). A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis. <i>BMC Medical Informatics and Decision Making</i>, 22(1), 56. http://hdl.handle.net/11427/36337en_ZA
dc.identifier.chicagocitationVerboven, Lennert, Toon Calders, Steven Callens, John Black, Gary Maartens, Kelly E Dooley, Samantha Potgieter, Robin M Warren, Kris Laukens, and Annelies Van Rie "A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis." <i>BMC Medical Informatics and Decision Making</i> 22, 1. (2022): 56. http://hdl.handle.net/11427/36337en_ZA
dc.identifier.citationVerboven, L., Calders, T., Callens, S., Black, J., Maartens, G., Dooley, K.E., Potgieter, S. & Warren, R.M. et al. 2022. A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis. <i>BMC Medical Informatics and Decision Making.</i> 22(1):56. http://hdl.handle.net/11427/36337en_ZA
dc.identifier.ris TY - Journal Article AU - Verboven, Lennert AU - Calders, Toon AU - Callens, Steven AU - Black, John AU - Maartens, Gary AU - Dooley, Kelly E AU - Potgieter, Samantha AU - Warren, Robin M AU - Laukens, Kris AU - Van Rie, Annelies AB - Background Personalized medicine tailors care based on the patient’s or pathogen’s genotypic and phenotypic characteristics. An automated Clinical Decision Support System (CDSS) could help translate the genotypic and phenotypic characteristics into optimal treatment and thus facilitate implementation of individualized treatment by less experienced physicians. Methods We developed a hybrid knowledge- and data-driven treatment recommender CDSS. Stakeholders and experts first define the knowledge base by identifying and quantifying drug and regimen features for the prototype model input. In an iterative manner, feedback from experts is harvested to generate model training datasets, machine learning methods are applied to identify complex relations and patterns in the data, and model performance is assessed by estimating the precision at one, mean reciprocal rank and mean average precision. Once the model performance no longer iteratively increases, a validation dataset is used to assess model overfitting. Results We applied the novel methodology to develop a treatment recommender CDSS for individualized treatment of drug resistant tuberculosis as a proof of concept. Using input from stakeholders and three rounds of expert feedback on a dataset of 355 patients with 129 unique drug resistance profiles, the model had a 95% precision at 1 indicating that the highest ranked treatment regimen was considered appropriate by the experts in 95% of cases. Use of a validation data set however suggested substantial model overfitting, with a reduction in precision at 1 to 78%. Conclusion Our novel and flexible hybrid knowledge- and data-driven treatment recommender CDSS is a first step towards the automation of individualized treatment for personalized medicine. Further research should assess its value in fields other than drug resistant tuberculosis, develop solid statistical approaches to assess model performance, and evaluate their accuracy in real-life clinical settings. DA - 2022-03-02 DB - OpenUCT DP - University of Cape Town IS - 1 J1 - BMC Medical Informatics and Decision Making KW - Clinical decision support system KW - Treatment individualisation KW - Machine learning LK - https://open.uct.ac.za PY - 2022 T1 - A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis TI - A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis UR - http://hdl.handle.net/11427/36337 ER - en_ZA
dc.identifier.urihttps://doi.org/10.1186/s12911-022-01790-0
dc.identifier.urihttp://hdl.handle.net/11427/36337
dc.identifier.vancouvercitationVerboven L, Calders T, Callens S, Black J, Maartens G, Dooley KE, et al. A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis. BMC Medical Informatics and Decision Making. 2022;22(1):56. http://hdl.handle.net/11427/36337.en_ZA
dc.language.isoenen_US
dc.language.rfc3066en
dc.publisher.departmentDepartment of Medicineen_US
dc.publisher.facultyFaculty of Health Sciencesen_US
dc.rights.holderThe Author(s)
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_US
dc.sourceBMC Medical Informatics and Decision Makingen_US
dc.source.journalissue1en_US
dc.source.journalvolume22en_US
dc.source.pagination56en_US
dc.source.urihttps://bmcmedinformdecismak.biomedcentral.com/
dc.subjectClinical decision support systemen_US
dc.subjectTreatment individualisationen_US
dc.subjectMachine learningen_US
dc.titleA treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosisen_US
dc.typeJournal Articleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
12911_2022_Article_1790.pdf
Size:
1.49 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Journal Articles