eprintid: 272593 rev_number: 26 eprint_status: archive userid: 6299 dir: disk0/00/27/25/93 datestamp: 2022-12-01 11:13:45 lastmod: 2022-12-08 10:18:10 status_changed: 2022-12-01 11:13:45 type: article metadata_visibility: show creators_name: Kazmi, Syed creators_name: Kambhampati, Chandrasekhar creators_name: Cleland, John G.F. creators_name: Cuthbert, Joe creators_name: Kazmi, Khurram Shehzad creators_name: Pellicori, Pierpaolo creators_name: Rigby, Alan S. creators_name: Clark, Andrew L. creators_orcid: 0000-0002-1471-7016 creators_orcid: 0000-0001-7175-0464 title: Dynamic risk stratification using Markov chain modelling in patients with chronic heart failure ispublished: pub divisions: 25200000 full_text_status: public suggestions: Status check: 11.07.22 AS 03.08.22 AS 27.09.22 AS 2022-11-16 AS abstract: Aims: Risk changes with the progression of disease and the impact of treatment. We developed a dynamic risk stratification Markov chain model using artificial intelligence in patients with chronic heart failure (CHF). Methods and results: We described the pattern of behaviour among 7496 consecutive patients assessed for suspected HF. The following mutually exclusive health states were defined and assessed every 4 months: death, hospitalization, outpatient visit, no event, and leaving the service altogether (defined as no event at any point following assessment). The observed figures at the first transition (4 months) weres 427 (6%), 1559 (21%), 2254 (30%), 1414 (19%), and 1842 (25%), respectively. The probabilities derived from the first two transitions (i.e. from baseline to 4 months and from 4 to 8 months) were used to construct the model. An example of the model's prediction is that at cycle 4, the cumulative probability of death was 14%; leaving the system, 37%; being hospitalized between 12 and 16 months, 10%; having an outpatient visit, 8%; and having no event, 31%. The corresponding observed figures were 14%, 41%, 10%, 15%, and 21%, respectively. The model predicted that during the first 2 years, a patient had a probability of dying of 0.19, and the observed value was 0.18. Conclusions: A model derived from the first 8 months of follow‐up is strongly predictive of future events in a population of patients with chronic heart failure. The course of CHF is more linear than is commonly supposed, and thus more predictable. date: 2022-10 date_type: published publication: ESC Heart Failure volume: 9 number: 5 publisher: Wiley pagerange: 3009-3018 id_number: 10.1002/ehf2.14028 refereed: TRUE issn: 2055-5822 copyright_holders: Copyright © 2022 The Authors prior: First published in ESC Heart Failure 9(5): 3009-3018 repro: Reproduced under a Creative Commons License uniqueid: glaseprints:2022-272593 issn_online: 2055-5822 funding_project_code: 303944 funding_project_name: BHF Centre of Excellence funding_investigator_name: Colin Berry funding_funder_name: British Heart Foundation (BHF) funding_funder_code: RE/18/6/34217 funding_investigator_dept: CAMS - Cardiovascular Science pubmed_id: 35736536 euro_pubmed_id: 35736536 pmcid: PMC9715820 hoa_compliant: 9205 hoa_ref_pan: AB hoa_date_acc: 2022-06-03 hoa_date_pub: 2022-06-23 hoa_date_foa: 2022-12-01 hoa_version_fcd: VoR hoa_exclude: FALSE hoa_gold: TRUE oa_research_materials_ack: No rioxx2_license_ref_input_license_ref: https://creativecommons.org/licenses/by/4.0/ rioxx2_license_ref_input_start_date: 2022-06-23 citation: Kazmi, S., Kambhampati, C., Cleland, J. G.F. , Cuthbert, J., Kazmi, K. S., Pellicori, P. , Rigby, A. S. and Clark, A. L. (2022) Dynamic risk stratification using Markov chain modelling in patients with chronic heart failure. ESC Heart Failure , 9(5), pp. 3009-3018. (doi: 10.1002/ehf2.14028 ) (PMID:35736536) (PMCID:PMC9715820) document_url: https://eprints.gla.ac.uk/272593/1/272593.pdf