Saskia L M van Loon1,2,3, Ruben Deneer4,5,6, Simon W Nienhuijs7, Anna Wilbik8, Uzay Kaymak8, Natal van Riel6, Volkher Scharnhorst4,5,6, Arjen-Kars Boer4,5,6. 1. Department of Clinical Chemistry, Catharina Hospital, P.O. Box 1350, 5602, ZA, Eindhoven, The Netherlands. saskia.s.v.loon@catharinaziekenhuis.nl. 2. Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands. saskia.s.v.loon@catharinaziekenhuis.nl. 3. Expert Center Clinical Chemistry, Eindhoven, The Netherlands. saskia.s.v.loon@catharinaziekenhuis.nl. 4. Department of Clinical Chemistry, Catharina Hospital, P.O. Box 1350, 5602, ZA, Eindhoven, The Netherlands. 5. Expert Center Clinical Chemistry, Eindhoven, The Netherlands. 6. Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. 7. Department of Surgery, Catharina Hospital, Eindhoven, The Netherlands. 8. Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands.
Abstract
PURPOSE: The focus of bariatric surgery is reduction of weight, reflected in body mass index (BMI). However, the resolution of comorbidity is a second important outcome indicator. The degree of comorbidity is hard to quantify objectively as comorbidities develop gradually and are interdependent. Multiple scoring systems quantifying comorbidity exist but they lack continuity and objectivity. In analogy with BMI as index for weight, the Metabolic Health Index (MHI) is developed as objective quantification of metabolic health status. Laboratory data were used as comorbidities affect biomarkers. Conversely, laboratory data can be used as objectively obtained variables to describe comorbidity. METHODS: Laboratory data were collected and crosschecked by national quality registry entries. Machine learning was applied to develop an ordinal logistic regression model, using 4 clinical and 32 laboratory input variables. The output was mathematically transformed into a continuous score for intuitive interpretation, ranging from 1 to 6 (MHI). RESULTS: In total, 4778 data records of 1595 patients were used. The degree of comorbidity is best described by age at phlebotomy, estimated Glomerular Filtration Rate (eGFR), and concentrations of glycated hemoglobin (HbA1c), triglycerides, and potassium. The model is independent of day of sampling and type of surgery. Mean MHI was significantly different between patient subgroups with increasing number of comorbidities. CONCLUSION: The MHI reflects severity of comorbidity, enabling objective assessment of a bariatric patient's metabolic health state, regardless day of sampling and surgery type. Next to weight-focused outcome measures like %TWL, the MHI can serve as outcome measure for metabolic health.
PURPOSE: The focus of bariatric surgery is reduction of weight, reflected in body mass index (BMI). However, the resolution of comorbidity is a second important outcome indicator. The degree of comorbidity is hard to quantify objectively as comorbidities develop gradually and are interdependent. Multiple scoring systems quantifying comorbidity exist but they lack continuity and objectivity. In analogy with BMI as index for weight, the Metabolic Health Index (MHI) is developed as objective quantification of metabolic health status. Laboratory data were used as comorbidities affect biomarkers. Conversely, laboratory data can be used as objectively obtained variables to describe comorbidity. METHODS: Laboratory data were collected and crosschecked by national quality registry entries. Machine learning was applied to develop an ordinal logistic regression model, using 4 clinical and 32 laboratory input variables. The output was mathematically transformed into a continuous score for intuitive interpretation, ranging from 1 to 6 (MHI). RESULTS: In total, 4778 data records of 1595 patients were used. The degree of comorbidity is best described by age at phlebotomy, estimated Glomerular Filtration Rate (eGFR), and concentrations of glycated hemoglobin (HbA1c), triglycerides, and potassium. The model is independent of day of sampling and type of surgery. Mean MHI was significantly different between patient subgroups with increasing number of comorbidities. CONCLUSION: The MHI reflects severity of comorbidity, enabling objective assessment of a bariatric patient's metabolic health state, regardless day of sampling and surgery type. Next to weight-focused outcome measures like %TWL, the MHI can serve as outcome measure for metabolic health.
Entities:
Keywords:
Bariatric surgery; Biomarkers; Diabetes; Dyslipidemia; Hypertension; METABOLIC SURGERY; Machine learning; Metabolic syndrome; Outcome measure; Value based health care
Authors: Daniel Dylan Cohen; Diego Gómez-Arbeláez; Paul Anthony Camacho; Sandra Pinzon; Claudia Hormiga; Juanita Trejos-Suarez; John Duperly; Patricio Lopez-Jaramillo Journal: PLoS One Date: 2014-04-08 Impact factor: 3.240
Authors: Marie Ng; Tom Fleming; Margaret Robinson; Blake Thomson; Nicholas Graetz; Christopher Margono; Erin C Mullany; Stan Biryukov; Cristiana Abbafati; Semaw Ferede Abera; Jerry P Abraham; Niveen M E Abu-Rmeileh; Tom Achoki; Fadia S AlBuhairan; Zewdie A Alemu; Rafael Alfonso; Mohammed K Ali; Raghib Ali; Nelson Alvis Guzman; Walid Ammar; Palwasha Anwari; Amitava Banerjee; Simon Barquera; Sanjay Basu; Derrick A Bennett; Zulfiqar Bhutta; Jed Blore; Norberto Cabral; Ismael Campos Nonato; Jung-Chen Chang; Rajiv Chowdhury; Karen J Courville; Michael H Criqui; David K Cundiff; Kaustubh C Dabhadkar; Lalit Dandona; Adrian Davis; Anand Dayama; Samath D Dharmaratne; Eric L Ding; Adnan M Durrani; Alireza Esteghamati; Farshad Farzadfar; Derek F J Fay; Valery L Feigin; Abraham Flaxman; Mohammad H Forouzanfar; Atsushi Goto; Mark A Green; Rajeev Gupta; Nima Hafezi-Nejad; Graeme J Hankey; Heather C Harewood; Rasmus Havmoeller; Simon Hay; Lucia Hernandez; Abdullatif Husseini; Bulat T Idrisov; Nayu Ikeda; Farhad Islami; Eiman Jahangir; Simerjot K Jassal; Sun Ha Jee; Mona Jeffreys; Jost B Jonas; Edmond K Kabagambe; Shams Eldin Ali Hassan Khalifa; Andre Pascal Kengne; Yousef Saleh Khader; Young-Ho Khang; Daniel Kim; Ruth W Kimokoti; Jonas M Kinge; Yoshihiro Kokubo; Soewarta Kosen; Gene Kwan; Taavi Lai; Mall Leinsalu; Yichong Li; Xiaofeng Liang; Shiwei Liu; Giancarlo Logroscino; Paulo A Lotufo; Yuan Lu; Jixiang Ma; Nana Kwaku Mainoo; George A Mensah; Tony R Merriman; Ali H Mokdad; Joanna Moschandreas; Mohsen Naghavi; Aliya Naheed; Devina Nand; K M Venkat Narayan; Erica Leigh Nelson; Marian L Neuhouser; Muhammad Imran Nisar; Takayoshi Ohkubo; Samuel O Oti; Andrea Pedroza; Dorairaj Prabhakaran; Nobhojit Roy; Uchechukwu Sampson; Hyeyoung Seo; Sadaf G Sepanlou; Kenji Shibuya; Rahman Shiri; Ivy Shiue; Gitanjali M Singh; Jasvinder A Singh; Vegard Skirbekk; Nicolas J C Stapelberg; Lela Sturua; Bryan L Sykes; Martin Tobias; Bach X Tran; Leonardo Trasande; Hideaki Toyoshima; Steven van de Vijver; Tommi J Vasankari; J Lennert Veerman; Gustavo Velasquez-Melendez; Vasiliy Victorovich Vlassov; Stein Emil Vollset; Theo Vos; Claire Wang; XiaoRong Wang; Elisabete Weiderpass; Andrea Werdecker; Jonathan L Wright; Y Claire Yang; Hiroshi Yatsuya; Jihyun Yoon; Seok-Jun Yoon; Yong Zhao; Maigeng Zhou; Shankuan Zhu; Alan D Lopez; Christopher J L Murray; Emmanuela Gakidou Journal: Lancet Date: 2014-05-29 Impact factor: 79.321
Authors: Ivan Soldatovic; Rade Vukovic; Djordje Culafic; Milan Gajic; Vesna Dimitrijevic-Sreckovic Journal: PLoS One Date: 2016-01-08 Impact factor: 3.240