1
|
Petri M. Drug monitoring in systemic lupus erythematosus. Curr Opin Pharmacol 2022; 64:102225. [PMID: 35490454 DOI: 10.1016/j.coph.2022.102225] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Accepted: 03/21/2022] [Indexed: 11/16/2022]
Abstract
Therapeutic drug monitoring (TDM) is not yet accepted by systemic lupus erythematosus (SLE) treatment guidelines. Studies in SLE, however, have proven benefit in three areas: identification of non-adherence or poor adherence; targets for clinical benefit; and ranges of toxicity. This review covers the data on three medications commonly used for SLE, drawing on studies from both the SLE and non-SLE literature.
Collapse
Affiliation(s)
- Michelle Petri
- Johns Hopkins University School of Medicine, Department of Medicine, Division of Rheumatology, 1830 E. Monument Street, Suite 7500, Baltimore, MD, 21205, USA.
| |
Collapse
|
2
|
Wagih S, Hussein MM, Rizk KA, Abdel Azeem AA, El-Habit OH. A study of the genotyping and vascular endothelial growth factor polymorphism differences in diabetic and diabetic retinopathy patients. EGYPTIAN JOURNAL OF MEDICAL HUMAN GENETICS 2022. [DOI: 10.1186/s43042-022-00277-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
Abstract
Background
Retinopathy is one of the major causes of visual impairment which is the most severe microvascular complication of diabetes mellitus (DM). The aim of this study was to evaluate the association between diabetic retinopathy (DR) and two SNPs (− 152G > A and − 165C > T) located in the promoter region of the vascular endothelial growth factor (VEGF) gene in a small sample from Egyptian population. One hundred diabetic patients without retinopathy (DWR) and two hundred diabetic patients with retinopathy were included in this study. Genotype analysis for the two SNPs (− 152G > A and − 165C > T) was assessed by using the PCR–RFLP technique. In addition, the serum protein level of VEGF was measured by ELISA assay.
Results
The results showed a significant relationship between − 152G > A (rs13207351) polymorphism and both proliferative and non-proliferative retinopathy in genotypes (GG, GA, AA). The risk factor increment in the mutant heterozygous genotype (GA) was significantly increased in NPDR compared to PDR (OR = 16.3, 95%CI = 0.80–331.7); (OR = 20.4, 95%CI = 1.08–385.3), respectively. There was no significance between VEGF − 165C > T (rs79469752) gene polymorphism and retinopathy. Moreover, the serum protein level of VEGF showed a highly significant increase (P = 0.0001) in PDR (Mean ± SD = 3691 ± 124.9) when compared to both DWR (Mean ± SD = 497.3 ± 18.51) and NPDR (Mean ± SD = 1674.5 ± 771.7). These results were supported by the increased level of VEGF in serum protein which is positively correlated with the severity of retinopathy. Measuring VEGF protein level in DR patients would help as a biomarker in early diagnosis.
Conclusion
The increase in the mutant heterogeneous GA genotype in VEGF − 152G > A SNP could be a risk factor for the progression of severe retinopathy in diabetic patients.
Collapse
|
3
|
Li W, Song Y, Chen K, Ying J, Zheng Z, Qiao S, Yang M, Zhang M, Zhang Y. Predictive model and risk analysis for diabetic retinopathy using machine learning: a retrospective cohort study in China. BMJ Open 2021; 11:e050989. [PMID: 34836899 PMCID: PMC8628336 DOI: 10.1136/bmjopen-2021-050989] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/03/2023] Open
Abstract
OBJECTIVE Aiming to investigate diabetic retinopathy (DR) risk factors and predictive models by machine learning using a large sample dataset. DESIGN Retrospective study based on a large sample and a high dimensional database. SETTING A Chinese central tertiary hospital in Beijing. PARTICIPANTS Information on 32 452 inpatients with type-2 diabetes mellitus (T2DM) were retrieved from the electronic medical record system from 1 January 2013 to 31 December 2017. METHODS Sixty variables (including demography information, physical and laboratory measurements, system diseases and insulin treatments) were retained for baseline analysis. The optimal 17 variables were selected by recursive feature elimination. The prediction model was built based on XGBoost algorithm, and it was compared with three other popular machine learning techniques: logistic regression, random forest and support vector machine. In order to explain the results of XGBoost model more visually, the Shapley Additive exPlanation (SHAP) method was used. RESULTS DR occurred in 2038 (6.28%) T2DM patients. The XGBoost model was identified as the best prediction model with the highest AUC (area under the curve value, 0.90) and showed that an HbA1c value greater than 8%, nephropathy, a serum creatinine value greater than 100 µmol/L, insulin treatment and diabetic lower extremity arterial disease were associated with an increased risk of DR. A patient's age over 65 was associated with a decreased risk of DR. CONCLUSIONS With better comprehensive performance, XGBoost model had high reliability to assess risk indicators of DR. The most critical risk factors of DR and the cut-off of risk factors can be found by SHAP method to render the output of the XGBoost model clinically interpretable.
Collapse
Affiliation(s)
- Wanyue Li
- Medical School of Chinese PLA, Beijing, China
- Department of Ophthalmology, Chinese PLA General Hospital, Beijing, China
| | - Yanan Song
- Medical Big Data Research Center, Medical Innovation Research Division of Chinese PLA General Hospital, Beijing, China
| | - Kang Chen
- Department of Endocrinology, Chinese PLA General Hospital, Beijing, China
| | - Jun Ying
- Information Management Department, Chinese PLA General Hospital, Beijing, China
| | - Zhong Zheng
- Information Center, Logistics Support Department, Central Military Commission, Beijing, China
| | - Shen Qiao
- Medical Big Data Research Center, Medical Innovation Research Division of Chinese PLA General Hospital, Beijing, China
| | - Ming Yang
- Medical Big Data Research Center, Medical Innovation Research Division of Chinese PLA General Hospital, Beijing, China
| | - Maonian Zhang
- Medical School of Chinese PLA, Beijing, China
- Department of Ophthalmology, Chinese PLA General Hospital, Beijing, China
| | - Ying Zhang
- Department of Ophthalmology, Chinese PLA General Hospital, Beijing, China
| |
Collapse
|
4
|
Saputro SA, Pattanaprateep O, Pattanateepapon A, Karmacharya S, Thakkinstian A. Prognostic models of diabetic microvascular complications: a systematic review and meta-analysis. Syst Rev 2021; 10:288. [PMID: 34724973 PMCID: PMC8561867 DOI: 10.1186/s13643-021-01841-z] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/11/2021] [Accepted: 10/21/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Many prognostic models of diabetic microvascular complications have been developed, but their performances still varies. Therefore, we conducted a systematic review and meta-analysis to summarise the performances of the existing models. METHODS Prognostic models of diabetic microvascular complications were retrieved from PubMed and Scopus up to 31 December 2020. Studies were selected, if they developed or internally/externally validated models of any microvascular complication in type 2 diabetes (T2D). RESULTS In total, 71 studies were eligible, of which 32, 30 and 18 studies initially developed prognostic model for diabetic retinopathy (DR), chronic kidney disease (CKD) and end stage renal disease (ESRD) with the number of derived equations of 84, 96 and 51, respectively. Most models were derived-phases, some were internal and external validations. Common predictors were age, sex, HbA1c, diabetic duration, SBP and BMI. Traditional statistical models (i.e. Cox and logit regression) were mostly applied, otherwise machine learning. In cohorts, the discriminative performance in derived-logit was pooled with C statistics of 0.82 (0.73‑0.92) for DR and 0.78 (0.74‑0.83) for CKD. Pooled Cox regression yielded 0.75 (0.74‑0.77), 0.78 (0.74‑0.82) and 0.87 (0.84‑0.89) for DR, CKD and ESRD, respectively. External validation performances were sufficiently pooled with 0.81 (0.78‑0.83), 0.75 (0.67‑0.84) and 0.87 (0.85‑0.88) for DR, CKD and ESRD, respectively. CONCLUSIONS Several prognostic models were developed, but less were externally validated. A few studies derived the models by using appropriate methods and were satisfactory reported. More external validations and impact analyses are required before applying these models in clinical practice. SYSTEMATIC REVIEW REGISTRATION PROSPERO CRD42018105287.
Collapse
Affiliation(s)
- Sigit Ari Saputro
- Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand.,Department of Epidemiology Biostatistics Population and Health Promotion, Faculty of Public Health, Airlangga University, Surabaya, Indonesia
| | - Oraluck Pattanaprateep
- Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand.
| | - Anuchate Pattanateepapon
- Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand
| | - Swekshya Karmacharya
- Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand
| | - Ammarin Thakkinstian
- Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University, 270 Rama VI Road, Pyathai, Bangkok, 10400, Thailand
| |
Collapse
|
5
|
Hsu MY, Chiou JY, Liu JT, Lee CM, Lee YW, Chou CC, Lo SC, Kornelius E, Yang YS, Chang SY, Liu YC, Huang CN, Tseng VS. Deep Learning for Automated Diabetic Retinopathy Screening Fused With Heterogeneous Data From EHRs Can Lead to Earlier Referral Decisions. Transl Vis Sci Technol 2021; 10:18. [PMID: 34403475 PMCID: PMC8374997 DOI: 10.1167/tvst.10.9.18] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2020] [Accepted: 05/17/2021] [Indexed: 01/03/2023] Open
Abstract
Purpose Fundus images are typically used as the sole training input for automated diabetic retinopathy (DR) classification. In this study, we considered several well-known DR risk factors and attempted to improve the accuracy of DR screening. Metphods Fusing nonimage data (e.g., age, gender, smoking status, International Classification of Disease code, and laboratory tests) with data from fundus images can enable an end-to-end deep learning architecture for DR screening. We propose a neural network that simultaneously trains heterogeneous data and increases the performance of DR classification in terms of sensitivity and specificity. In the current retrospective study, 13,410 fundus images and their corresponding nonimage data were collected from the Chung Shan Medical University Hospital in Taiwan. The images were classified as either nonreferable or referable for DR by a panel of ophthalmologists. Cross-validation was used for the training models and to evaluate the classification performance. Results The proposed fusion model achieved 97.96% area under the curve with 96.84% sensitivity and 89.44% specificity for determining referable DR from multimodal data, and significantly outperformed the models that used image or nonimage information separately. Conclusions The fusion model with heterogeneous data has the potential to improve referable DR screening performance for earlier referral decisions. Translational Relevance Artificial intelligence fused with heterogeneous data from electronic health records could provide earlier referral decisions from DR screening.
Collapse
Affiliation(s)
- Min-Yen Hsu
- Department of Ophthalmology, Chung Shan Medical University Hospital, Taichung, Taiwan
- School of Medicine, Chung Shan Medical University, Taichung, Taiwan
- Biotechnology Center, National Chung Hsing University, Taichung, Taiwan
| | - Jeng-Yuan Chiou
- Department of Health Policy and Management, Chung Shan Medical University, Taichung, Taiwan
| | - Jung-Tzu Liu
- Computational Intelligence Technology Center, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Chee-Ming Lee
- Department of Ophthalmology, Chung Shan Medical University Hospital, Taichung, Taiwan
- School of Medicine, Chung Shan Medical University, Taichung, Taiwan
| | - Ya-Wen Lee
- Computational Intelligence Technology Center, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Chien-Chih Chou
- Department of Ophthalmology, Taichung Veterans General Hospital, Taichung, Taiwan
- Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan
| | - Shih-Chang Lo
- Department of Internal Medicine, Division of Endocrinology and Metabolism, Chung Shan Medical University Hospital, Taichung, Taiwan
- Institute of Medicine, College of Medicine, Chung Shan Medical University, Taichung, Taiwan
| | - Edy Kornelius
- Department of Internal Medicine, Division of Endocrinology and Metabolism, Chung Shan Medical University Hospital, Taichung, Taiwan
- Institute of Medicine, College of Medicine, Chung Shan Medical University, Taichung, Taiwan
| | - Yi-Sun Yang
- Department of Internal Medicine, Division of Endocrinology and Metabolism, Chung Shan Medical University Hospital, Taichung, Taiwan
- Institute of Medicine, College of Medicine, Chung Shan Medical University, Taichung, Taiwan
| | - Sung-Yen Chang
- Computational Intelligence Technology Center, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Yu-Cheng Liu
- Computational Intelligence Technology Center, Industrial Technology Research Institute, Hsinchu, Taiwan
| | - Chien-Ning Huang
- Department of Internal Medicine, Division of Endocrinology and Metabolism, Chung Shan Medical University Hospital, Taichung, Taiwan
- Institute of Medicine, College of Medicine, Chung Shan Medical University, Taichung, Taiwan
| | - Vincent S. Tseng
- Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan
- Institute of Data Science and Engineering, National Chiao Tung University, Hsinchu, Taiwan
| |
Collapse
|
6
|
Multiple Single Nucleotide Polymorphism Testing Improves the Prediction of Diabetic Retinopathy Risk with Type 2 Diabetes Mellitus. J Pers Med 2021; 11:jpm11080689. [PMID: 34442333 PMCID: PMC8398882 DOI: 10.3390/jpm11080689] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2021] [Revised: 07/15/2021] [Accepted: 07/19/2021] [Indexed: 11/17/2022] Open
Abstract
Diabetic retinopathy (DR) is one of the most frequent causes of irreversible blindness, thus prevention and early detection of DR is crucial. The purpose of this study is to identify genetic determinants of DR in individuals with type 2 diabetic mellitus (T2DM). A total of 551 T2DM patients (254 with DR, 297 without DR) were included in this cross-sectional research. Thirteen T2DM-related single nucleotide polymorphisms (SNPs) were utilized for constructing genetic risk prediction model. With logistic regression analysis, genetic variations of the FTO (rs8050136) and PSMD6 (rs831571) polymorphisms were independently associated with a higher risk of DR. The area under the curve (AUC) calculated on known nongenetic risk variables was 0.704. Based on the five SNPs with the highest odds ratio (OR), the combined nongenetic and genetic prediction model improved the AUC to 0.722. The discriminative accuracy of our 5-SNP combined risk prediction model increased in patients who had more severe microalbuminuria (AUC = 0.731) or poor glycemic control (AUC = 0.746). In conclusion, we found a novel association for increased risk of DR at two T2DM-associated genetic loci, FTO (rs8050136) and PSMD6 (rs831571). Our predictive risk model presents new insights in DR development, which may assist in enabling timely intervention in reducing blindness in diabetic patients.
Collapse
|
7
|
Causal Relationship between Adiponectin and Diabetic Retinopathy: A Mendelian Randomization Study in an Asian Population. Genes (Basel) 2020; 12:genes12010017. [PMID: 33374471 PMCID: PMC7823606 DOI: 10.3390/genes12010017] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2020] [Revised: 12/04/2020] [Accepted: 12/22/2020] [Indexed: 01/03/2023] Open
Abstract
Adiponectin (APN) is suggested to be a potential biomarker for predicting diabetic retinopathy (DR) risk, but the association between APN and DR has been inconsistent in observational studies. We used a Mendelian randomization (MR) analysis to evaluate if circulating APN levels result in DR. We applied three different genetic risk scores (GRS): GRSAll combined all 47 single nucleotide polymorphisms (SNPs), which from a genome-wide association study (GWAS) database-catalog reach significance level; GRSLimited comprised 16 GRSAll-SNPs with a rigorous threshold (p < 5.0 × 10-8 for GWAS), and GRSAPN combined 5 SNPs significantly associated with APN level. The MR-inverse-variance weighted method analysis showed that for each 1-SD increase in genetically induced increase in plasma APN, the OR of having DR was β = 0.20 (95% CI: -0.46-0.85, p = 0.553) for GRSAPN, 0.61 (95% CI: 0.10-1.13, p = 0.020) for GRSAll, and 0.57 (95% CI: -0.06 to 1.20, p = 0.078) for GRSLimited. Sensitivity analysis, including MR-egger regression and the weighted-median approach, did not provide evidence of the pleiotropic effect of IVs. Limited evidence for the causal role of APN in DR risk among Taiwanese diabetic patients was shown based on MR analysis in the present study.
Collapse
|
8
|
Hsieh AR, Huang YC, Yang YF, Lin HJ, Lin JM, Chang YW, Wu CM, Liao WL, Tsai FJ. Lack of association of genetic variants for diabetic retinopathy in Taiwanese patients with diabetic nephropathy. BMJ Open Diabetes Res Care 2020; 8:8/1/e000727. [PMID: 31958309 PMCID: PMC7039583 DOI: 10.1136/bmjdrc-2019-000727] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/02/2019] [Revised: 12/11/2019] [Accepted: 01/04/2020] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVE Diabetic nephropathy (DN) and diabetic retinopathy (DR) comprise major microvascular complications of diabetes that occur with a high concordance rate in patients and are considered to potentially share pathogeneses. In this case-control study, we sought to investigate whether DR-related single nucleotide polymorphisms (SNPs) exert pleiotropic effects on renal function outcomes among patients with diabetes. RESEARCH DESIGN AND METHODS A total of 33 DR-related SNPs were identified by replicating published SNPs and via a genome-wide association study. Furthermore, we assessed the cumulative effects by creating a weighted genetic risk score and evaluated the discriminatory and prediction ability of these genetic variants using DN cases according to estimated glomerular filtration rate (eGFR) status along with a cohort with early renal functional decline (ERFD). RESULTS Multivariate logistic regression models revealed that the DR-related SNPs afforded no individual or cumulative genetic effect on the nephropathy risk, eGFR status or ERFD outcome among patients with type two diabetes in Taiwan. CONCLUSION Our findings indicate that larger studies would be necessary to clearly ascertain the effects of individual genetic variants and further investigation is also required to identify other genetic pathways underlying DN.
Collapse
Affiliation(s)
- Ai-Ru Hsieh
- Department of Statistics, Tamkang University, Taipei, Taiwan
| | - Yu-Chuen Huang
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
- Human Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Ya-Fei Yang
- Kidney Institute and Division of Nephrology, Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan
| | - Hui-Ju Lin
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
- Department of Ophthalmology, China Medical University Hospital, Taichung, Taiwan
| | - Jane-Ming Lin
- Department of Ophthalmology, China Medical University Hospital, Taichung, Taiwan
| | - Ya-Wen Chang
- Human Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Chia-Ming Wu
- Human Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Wen-Ling Liao
- Graduate Institute of Integrated Medicine, China Medical University, Taichung, Taiwan
- Center for Personalized Medicine, China Medical University Hospital, Taichung, Taiwan
| | - Fuu-Jen Tsai
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
- Human Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
- Department of Health and Nutrition Biotechnology, Asia University, Taichung, Taiwan
| |
Collapse
|