1
|
Shakibfar S, Zhao J, Li H, Nordeng H, Lupattelli A, Pavlovic M, Sandve GK, Nyberg F, Wettermark B, Hajiebrahimi M, Andersen M, Sessa M. Machine learning-driven development of a disease risk score for COVID-19 hospitalization and mortality: a Swedish and Norwegian register-based study. Front Public Health 2023; 11:1258840. [PMID: 38146473 PMCID: PMC10749372 DOI: 10.3389/fpubh.2023.1258840] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Accepted: 11/20/2023] [Indexed: 12/27/2023] Open
Abstract
Aims To develop a disease risk score for COVID-19-related hospitalization and mortality in Sweden and externally validate it in Norway. Method We employed linked data from the national health registries of Sweden and Norway to conduct our study. We focused on individuals in Sweden with confirmed SARS-CoV-2 infection through RT-PCR testing up to August 2022 as our study cohort. Within this group, we identified hospitalized cases as those who were admitted to the hospital within 14 days of testing positive for SARS-CoV-2 and matched them with five controls from the same cohort who were not hospitalized due to SARS-CoV-2. Additionally, we identified individuals who died within 30 days after being hospitalized for COVID-19. To develop our disease risk scores, we considered various factors, including demographics, infectious, somatic, and mental health conditions, recorded diagnoses, and pharmacological treatments. We also conducted age-specific analyses and assessed model performance through 5-fold cross-validation. Finally, we performed external validation using data from the Norwegian population with COVID-19 up to December 2021. Results During the study period, a total of 124,560 individuals in Sweden were hospitalized, and 15,877 individuals died within 30 days following COVID-19 hospitalization. Disease risk scores for both hospitalization and mortality demonstrated predictive capabilities with ROC-AUC values of 0.70 and 0.72, respectively, across the entire study period. Notably, these scores exhibited a positive correlation with the likelihood of hospitalization or death. In the external validation using data from the Norwegian COVID-19 population (consisting of 53,744 individuals), the disease risk score predicted hospitalization with an AUC of 0.47 and death with an AUC of 0.74. Conclusion The disease risk score showed moderately good performance to predict COVID-19-related mortality but performed poorly in predicting hospitalization when externally validated.
Collapse
Affiliation(s)
- Saeed Shakibfar
- Department of Drug Design and Pharmacology, Pharmacovigilance Research Center, University of Copenhagen, Copenhagen, Denmark
- Department of Drug Design and Pharmacology, Drug Safety Group, University of Copenhagen, Copenhagen, Denmark
| | - Jing Zhao
- Department of Pharmacy, Pharmacoepidemiology and Drug Safety Research Group, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
- UiO: RealArt Convergence Environment, University of Oslo, Oslo, Norway
- School of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Huiqi Li
- School of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Hedvig Nordeng
- Department of Pharmacy, Pharmacoepidemiology and Drug Safety Research Group, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
- UiO: RealArt Convergence Environment, University of Oslo, Oslo, Norway
| | - Angela Lupattelli
- Department of Pharmacy, Pharmacoepidemiology and Drug Safety Research Group, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
- UiO: RealArt Convergence Environment, University of Oslo, Oslo, Norway
| | - Milena Pavlovic
- UiO: RealArt Convergence Environment, University of Oslo, Oslo, Norway
- Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
| | - Geir Kjetil Sandve
- UiO: RealArt Convergence Environment, University of Oslo, Oslo, Norway
- Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway
| | - Fredrik Nyberg
- School of Public Health and Community Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Björn Wettermark
- Department of Pharmacy, Pharmacoepidemiology and Social Pharmacy, Uppsala University, Uppsala, Sweden
| | | | - Morten Andersen
- Department of Drug Design and Pharmacology, Pharmacovigilance Research Center, University of Copenhagen, Copenhagen, Denmark
| | - Maurizio Sessa
- Department of Drug Design and Pharmacology, Drug Safety Group, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
2
|
Khayat A, Aldharman SS, Alharbi NN, Alayyaf AS, abdulmuttalib JA, Altalhi ER. Regional and seasonal variations in functional abdominal pain and functional constipation prevalence among Saudi children. SAGE Open Med 2023; 11:20503121231163519. [PMID: 37026105 PMCID: PMC10071212 DOI: 10.1177/20503121231163519] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Accepted: 02/24/2023] [Indexed: 04/03/2023] Open
Abstract
Objectives: This study aimed to evaluate functional abdominal pain disorders and functional constipation prevalence in the central region of Saudi Arabia, and compare it to that of the western region. Methods: This was a cross-sectional study using online questionnaires targeting the general population of Riyadh region of Saudi Arabia. Subjects were randomly selected by sharing links on social media groups. Any parent with a 3–18-year-old child was included, and children with chronic medical illnesses or symptoms of organic GI disorders were excluded. Results: Three hundred nineteen subjects were included in the final analysis; the prevalence of functional abdominal pain disorders overall was 6.2% and the prevalence of functional constipation was 8.1%. Conclusions: Functional constipation diagnosis seems to be affected by life stressors or a previous viral illness. Seasonal variations had minimal effect on functional abdominal pain disorder and functional constipation symptom frequency and severity.
Collapse
Affiliation(s)
- Ammar Khayat
- Umm Al Qura University, Al Abdeyah, Makkah, Saudi Arabia
| | - Sarah Salem Aldharman
- College of Medicine, King Saud bin Abdulaziz University for Health Sciences, Riyadh, Saudi Arabia
| | - Njoud Naif Alharbi
- College of Medicine, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
| | | | | | | |
Collapse
|