Estimation of Prevalence and Incremental Costs of Systemic Lupus Erythematosus in a Middle-Income Country Using Machine Learning on Administrative Health Data

Castro-Villarreal, Santiago; Beltrán-Ostos, Adriana; Valencia, Carlos

doi:10.1016/j.vhri.2021.04.005

Cited by 8 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relationship between severity of lupus and disease costs has been demonstrated in cohorts from different countries. [6][7][8][9][10]31,32 Specially, patients with lupus nephritis contribute to a major economic burden comparing with lupus without nephritis. [11][12][13][14]33 Cumulative damage (highest SDI 34 scores) has also been described as a factor of increased disease costs, showing 10-year cumulative costs 9-fold higher than those with lower damage.…”

Section: Discussionmentioning

confidence: 99%

“…In Colombia, direct estimated costs per lupus patient were estimated in US$2172 (ranging from US$8823 for severe to US$447 for mild cases). 32 Also in Colombia, annual costs for patients with lupus nephritis have been calculated to be 7.46 times greater than those without nephritis. 13 As far as we know, up to date there is no other data on SLE health care resource use from other Latin American countries and no data from Argentina.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Burden of lupus activity on health care resources utilization in Buenos Aires, Argentina

Alvarado,

Alle,

Tobar–Jaramillo

et al. 2023

Lupus

View full text Add to dashboard Cite

Objective The aim is to analyze health care resource utilization (HCRU) of patients with lupus (SLE) from a health management organization (HMO) in Buenos Aires, Argentina, compared with matched controls and comparing periods of flare, low disease activity, and remission. Methods This is a retrospective observational study including all SLE incident cases (ACR 1997/SLICC 2012 criteria) between 2000 and 2020 and 5 matched controls. Clinical data and HCRU (medical and nonmedical consultations, lab and imaging tests performed, emergency room visits, hospitalizations, and drugs prescribed) were obtained from administrative databases and electronic medical records. For each patient with SLE, an activity state was determined in every month of follow-up: flare (BILAG A or 2 BILAG B); low disease activity (LLDAS); remission (DORIS definition); or intermediate activity (not fulfilling any of previous). Incidence rates for each HCRU item and incidence rate ratios between SLE and control patients were and between remission and flare periods were calculated. Multivariate negative binomial logistic regression analyses were performed for identification of variables associated with major resource use. Results A total of 62 SLE and 310 control patients were included, 88.7% were women, the median age at diagnosis was 46 years, and were followed for more than 8 years. Patients with SLE contributed with 537.2 patient-years (CI 95% 461.1–613.3) and controls with 2761.9 patient-years (CI 95% 2600.9–2922.8). HCRU in patients with SLE was significantly higher than in controls in all items, even in remission periods. Patients with SLE remained 74.4% of the time in remission, 12.1% in LLDAS, 12.2% in intermediate activity, and 1.3% in flare (there were 64 flares in 36 patients). HCRU was significantly higher during flare periods compared with remission periods. Number of flares was independently associated with emergency department consultations, lab tests and X-ray performed, number of drugs prescribed, and hospitalizations. Conclusion Significantly more HCRU was observed in patients with SLE in flare compared to remission periods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Burden of lupus activity on health care resources utilization in Buenos Aires, Argentina

Alvarado,

Alle,

Tobar–Jaramillo

et al. 2023

Lupus

View full text Add to dashboard Cite

show abstract

“…Most of these larger reports used EMRs and administrative databases to identify patients with SLE, recognising that these types of data may be limited Review by diagnostic misclassification. [17][18][19][20][21] Many reports experienced 'class imbalance', where the SLE group sample size was considerably smaller compared with healthy controls, potentially biasing ML in favour of the more prevalent class. To address this, some reports used generative adversarial networks 22 23 and Synthetic Minority Oversampling TEchnique (SMOTE) 20 24 to generate synthetic data.…”

Section: Data Collectionmentioning

confidence: 99%

“…In our scoping review, ML models were used to elucidate disease pathogenesis (n=31), 48 52–81 predict SLE diagnosis and identify cases (n=61), 23 28 37 43 44 46 47 53 63 70 73 79 82–130 disease activity and treatment response (n=33), 56 59 63 66 69 74 77 78 101 106 113 131–152 complications (n=22) 18 21 40 53 83 147 153–168 and healthcare utilisation (n=6) 17 20 41 42 142 169 ( table 2 ). Refer to online supplemental table 1 for a glossary of key terms.…”

Section: Key Sle Findings By ML Reportsmentioning

confidence: 99%

See 1 more Smart Citation

Systemic lupus in the era of machine learning medicine

Zhan,

Buhler,

Chen

et al. 2024

Lupus Sci Med

View full text Add to dashboard Cite

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

show abstract

Incremental Healthcare Costs of Diabetes Mellitus in a Middle-Income Country Using Administrative Healthcare Data

Castro-Villarreal,

Miksi,

Beltrán-Ostos

et al. 2024

Value in Health Regional Issues

View full text Add to dashboard Cite

Estimation of Prevalence and Incremental Costs of Systemic Lupus Erythematosus in a Middle-Income Country Using Machine Learning on Administrative Health Data

Cited by 8 publications

References 19 publications

Burden of lupus activity on health care resources utilization in Buenos Aires, Argentina

Burden of lupus activity on health care resources utilization in Buenos Aires, Argentina

Systemic lupus in the era of machine learning medicine

Incremental Healthcare Costs of Diabetes Mellitus in a Middle-Income Country Using Administrative Healthcare Data

Contact Info

Product

Resources

About