1
|
Olsson M, Currow DC, Ekström MP. Exploring the most important factors related to self-perceived health among older men in Sweden: a cross-sectional study using machine learning. BMJ Open 2022; 12:e061242. [PMID: 35728903 PMCID: PMC9214374 DOI: 10.1136/bmjopen-2022-061242] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
OBJECTIVE To evaluate which factors are the most strongly related to self-perceived health among older men and describe the shape of the association between the related factors and self-perceived health using machine learning. DESIGN AND SETTING This is a cross-sectional study within the population-based VAScular and Chronic Obstructive Lung disease study (VASCOL) conducted in southern Sweden in 2019. PARTICIPANTS A total of 475 older men aged 73 years from the VASCOL dataset. MEASURES Self-perceived health was measured using the first item of the Short Form 12. An extreme gradient-boosting model was trained to classify self-perceived health as better (rated: excellent or very good) or worse (rated: fair or poor) using self-reported data on 19 prevalent physician-diagnosed health conditions, intensity of 9 symptoms and 9 demographic and lifestyle factors. Importance of factors was measured in SHapley Additive exPlanations absolute mean and higher scores correspond to greater importance. RESULTS The most important factors for classifying self-perceived health were: pain (0.629), sleep quality (0.595), breathlessness (0.549), fatigue (0.542) and depression (0.526). Health conditions ranked well below symptoms and lifestyle variables. Low levels of symptoms, good sleep quality, regular exercise, alcohol consumption and a body mass index between 22 and 28 were associated with better self-perceived health. CONCLUSIONS Symptoms are more strongly related to self-perceived health than health conditions, which suggests that the impacts of health conditions are mediated through symptoms, which could be important targets to improve self-perceived health. Machine learning offers a new way to assess composite constructs such as well-being or quality of life.
Collapse
Affiliation(s)
- Max Olsson
- Department of Clinical Sciences Lund, Respiratory Medicine and Allergology, Lunds University Faculty of Medicine, Lund, Sweden
| | - David C Currow
- Faculty of Science, Medicine and Health, University of Wollongong, Wollongong, New South Wales, Australia
| | - Magnus Per Ekström
- Department of Clinical Sciences Lund, Respiratory Medicine and Allergology, Lunds University Faculty of Medicine, Lund, Sweden
| |
Collapse
|
2
|
Brittan MS, Moss A, Watson JD, Federico MJ, Rice JD, Dempsey AF, Ambroggio L. Association between early childhood lower respiratory tract infections and subsequent asthma. J Asthma 2021; 59:2143-2153. [PMID: 34706607 DOI: 10.1080/02770903.2021.1999469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
OBJECTIVE We examined the relationship between recurrent lower respiratory tract infections (LRTI) in young children and subsequent childhood asthma outcomes. METHODS Retrospective cohort study using 2009-2017 Colorado All Payer Claims Database to assess 0- to 2-year-old children with visits due to LRTI and acute gastroenteritis (AGE). The primary exposure was number of LRTI visits prior to 2 years of age. Children with AGE served as the no LRTI comparator group. The primary outcome was incident asthma, defined by ICD-9 (490.XX) or ICD-10 (J45.9XX) codes, in the same children between 3 and 9 years of age. Multivariable accelerated failure time (AFT) models were used to estimate the effect of LRTI visits on median time to asthma diagnosis. Sensitivity analyses were performed using more conservative asthma diagnostic criteria and with hospitalized children only. RESULTS Of 38,441 eligible subjects, 32,729 had ≥1 LRTI and 5,712 had AGE (no LRTI) between 0 and 2 years of age. Children with ≥3 LRTI visits had an 80% decrease in median time to asthma diagnosis relative to those with AGE visits only (time ratio [TR] 0.2; 95% CI 0.16, 0.24). Children with ≥3 LRTI hospitalizations had a 98% reduction in median time to asthma diagnosis relative to those with AGE hospitalizations only (TR 0.02; 95% CI 0.01, 0.07). History of atopy, wheezing, and family history of asthma documented prior to 2 years of age were also associated with earlier asthma diagnosis. CONCLUSIONS Recurrent LRTIs, especially LRTI hospitalizations, before 2 years of age are associated with earlier diagnosis of pediatric asthma.
Collapse
Affiliation(s)
- Mark S Brittan
- Section of Pediatric Hospital Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA.,Adult and Child Consortium for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado Denver, Aurora, CO, USA
| | - Angela Moss
- Adult and Child Consortium for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado Denver, Aurora, CO, USA
| | - John D Watson
- Section of Pediatric Hospital Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA
| | - Monica J Federico
- The Breathing Institute and Section of Pulmonary Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA
| | - John D Rice
- Adult and Child Consortium for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado Denver, Aurora, CO, USA.,The Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO, USA
| | - Amanda F Dempsey
- Section of Pediatric Hospital Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA.,Adult and Child Consortium for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado Denver, Aurora, CO, USA
| | - Lilliam Ambroggio
- Section of Pediatric Hospital Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA.,Section of Pediatric Emergency Medicine, Children's Hospital Colorado, University of Colorado Denver, Aurora, CO, USA
| |
Collapse
|