Performance of clinical prediction models for chronic kidney disease among people with diabetes: External validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN)

Performance of clinical prediction models for chronic kidney disease among people with diabetes: External validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Performance of clinical prediction models for chronic kidney disease among people with diabetes: External validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) Jason E. Black, David JT. Campbell, Paul E. Ronksley, Kerry A. McBrien, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5937923/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Nov, 2025 Read the published version in Diagnostic and Prognostic Research → Version 1 posted 9 You are reading this latest preprint version Abstract Background Several clinical prediction models that predict the risk of chronic kidney disease (CKD) in people with diabetes have been developed; however, these models lack external validation demonstrating accurate predictions in Canadian primary care. We externally validated existing clinical prediction models for CKD in Canadian primary care data, overall and across subgroups defined by sex/gender, age, comorbidities, and neighbourhood-level deprivation. Methods We conducted a retrospective cohort study using data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) electronic medical record database (2014–2019). We identified models that use demographic, health behaviour, clinical and diabetes-related characteristics to predict incident CKD based on two recent systematic reviews and included models with sufficient predictors in CPCSSN (≤1 unavailable) and eGFR-based CKD definitions. We included adult patients (18+) with diabetes without an existing diagnosis of CKD. We identified incident cases of CKD within 5 years based on ≥2 laboratory values corresponding to eGFR < 60 mL/min/1.73 m 2 separated by ≥90 days and ≤1 year. For each model, we estimated the discrimination, precision, recall, and calibration within CPCSSN. Results Among 37,604 patients with diabetes, 14.6% met diagnostic criteria for CKD within 5 years. Overall performance of the 13 included CKD prediction models in CPCCSN was mixed: three models displayed moderate to strong discrimination (areas under the receiver-operating characteristic curves [AUROCs] > 0.70), whereas other AUROCs were as low as 0.508. After model updating, calibrations were heterogeneous with most models displaying some miscalibration. Some subgroups displayed considerable differences in performance: discriminative performance (AUROC) declined with increasing age and number of comorbidities, whereas the precision and recall improved with increasing age and number of comorbidities. We observed no difference in performance according to sex/gender or deprivation quintile. Conclusions Three models displayed moderate to strong performance predicting CKD among CPCSSN patients. Next, these models should be evaluated for their impact on practitioner and patient outcomes when implemented in clinical practice. If successful, these models hold promise in achieving widespread adoption to help identify those at highest risk of CKD and guide therapies that may prevent or delay CKD and related sequelae (e.g., end-stage renal disease) among people with diabetes. clinical prediction models external validation chronic kidney disease diabetes primary care CPCSSN Figures Figure 1 Figure 2 Figure 3 Background Diabetes is associated with the development of several micro- and macrovascular complications, including diabetic nephropathy and chronic kidney disease (CKD) [ 1 ]. In Canada, CKD remains common among people with diabetes despite established therapies and clinical guidelines aimed at preventing diabetes complications [ 2 , 3 ]. Early identification of patients with diabetes who are at increased risk of CKD may enable targeted risk-reducing strategies to help prevent or delay the onset of CKD. Such strategies include intensification of standard therapy; addition of novel kidney protective agents; closer monitoring of patient adherence to treatments and therapeutic efficacy; and referral for specialized renal or diabetes services [ 1 ]. For example, traditional approaches to managing a patient with newly diagnosed type 2 diabetes may involve gradually introducing therapies to reduce blood glucose levels. However, this initial period following diabetes diagnosis is critical in pathophysiological processes that partly determine a patient’s progression towards microvascular complications, including nephropathy [ 4 , 5 ]. Patients at increased risk of CKD may benefit from rapidly achieving target glycemic levels through intensive therapies that may be less impactful in low-risk patients. Clinical prediction models can identify patients who are at increased risk of CKD based on patient factors, including demographic, health behaviour, clinical and diabetes-related characteristics. Many clinical prediction models that predict the risk of incident CKD (i.e., probability ranging from 0 to 1) in people with diabetes have been developed based on such patient factors [ 6 , 7 ]. In Canada, opportunities exist to deploy a CKD clinical prediction model in primary care settings—where patients with diabetes are most commonly managed; however, these models lack external validation demonstrating accurate predictions in this setting [ 8 ]. Indeed, clinical prediction models are prone to inadequate performance among subgroups, which may introduce or exacerbate inequities in care [ 9 , 10 ]. Only upon confirmation of robust performance in Canadian primary care should a CKD prediction model be implemented in clinical practice and subsequently evaluated for its ability to modify practitioner and patient behaviours and prevent CKD [ 11 ]. We sought to externally validate existing clinical prediction models for incident CKD in Canadian primary care data. We assessed the performance of CKD prediction models overall and among specific subgroups known to be associated with incident CKD [ 12 ] (i.e., sex/gender, age group, number of comorbidities, and social and material deprivation quintile). Methods Study setting and data source We conducted a retrospective cohort study using data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN), a pan-Canadian collection of electronic medical record (EMR) data for more than 2 million primary care patients [ 13 ]. Primary care practices contribute patient data describing diagnoses, procedures, laboratory tests, medication prescriptions, and referrals, as recorded by participating practitioners in the EMR. CPCSSN was established in 2008 regularly receives EMR data extracted by 14 contributing networks. Female and older patients are overrepresented in CPCSSN compared to the general Canadian population [ 14 ]; this is expected, as female and older patients are more likely to visit primary care practitioners [ 15 ]. CPCSSN uses robust processing to clean and standardize patient records (e.g., assigning diagnostic codes to free-text diagnoses) to facilitate research use [ 16 ]. Models Two recent systematic reviews identified and characterized clinical prediction models for CKD [ 6 , 7 ]. Models were developed using longitudinal data from people with pre-diabetes or type 1 or 2 diabetes. We considered 47 models published in 33 research articles, largely developed in people with type 2 diabetes. To ensure each model could feasibly be implemented within CPCSSN, we considered the availability of predictors within CPCSSN and how CKD was defined. We restricted to models where most predictors were available within CPCSSN (≤1 unavailable) and CKD was defined based on an eGFR threshold (i.e., excluding CKD definitions based on albuminuria or documentation of kidney failure), consistent with our CPCSSN incident CKD definition (see §Measures ). Selected model coefficients are presented in Supplementary Table 1, Additional File 1. Participants We used a validated case definition [ 17 ] (i.e., a combination of diagnostic codes, medication prescriptions, or laboratory test results; see Supplementary Table 2, Additional File 1) to identify adult patients (18+) with diabetes in CPCSSN. We excluded patients from Quebec and Manitoba because eGFR laboratory test results were not reliably available in CPCSSN. We identified a unique baseline visit for each patient as their first visit with a participating primary care practitioner in 2014. We included patients diagnosed with diabetes prior to or at baseline, but excluded patients diagnosed with probable type 1 diabetes (based on a combination of free-text terms, insulin prescriptions, and age [ 18 ]; see Supplementary Table 3, Additional File 1) within 5 years before their baseline visit, as guidelines recommend screening for CKD should commence 5 years following diagnosis for patients with type 1 diabetes [ 3 , 19 ]. We included patients without an existing diagnosis of CKD (see §Measures) prior to baseline; with at least 3 visits in the 2 years prior to baseline; and with at least one visit within 5 years after baseline. We followed patients for up to 5 years (2014 through 2019) to examine patterns of incident CKD over time. We censored patients at their last visit during the study period to account for patients lacking further follow-up (e.g., due to moving or changing primary care providers). Measures For each CKD model considered, we attempted to identify all predictors using CPCSSN data. We first assessed whether the predictor was directly measured (e.g., laboratory results such as HbA1c) or whether a CPCSSN-validated case definition was available (e.g., hypertension and chronic obstructive pulmonary disease [ 17 ]). Lacking these, we searched for other case definitions validated in primary care EMR data or previous research identifying the predictor in CPCSSN. If no case definition existed, we consulted clinical colleagues to develop a case definition via a set of criteria that identify the predictor in CPCSSN. We were unable to measure predictors without any information in CPCSSN, such as most health behaviors (e.g., physical activity or alcohol use) and several laboratory tests that are not extracted by CPCSSN processing (e.g., cystatin C or serum uric acid). Details on how we identified each predictor in CPCSSN are described in Supplementary Table 4, Additional File 1. We identified diagnoses of CKD during the 5-year study period based on clinical guidelines: two or more laboratory values corresponding to an eGFR < 60 mL/min/1.73 m 2 that were separated by ≥90 days to < 1 year [ 20 ]. Some subgroups are known to be at increased risk of CKD compared to other primary care patients with diabetes [ 21 ]. We considered subgroups defined by sex/gender (female/woman and male/man), age group (18 to 39, 40 to 64, and 65 and older), number of comorbidities (none, one, two, or three or more), and social and material deprivation quintile as these subgroups could be identified within CPCSSN; other important subgroups, such as Black patients, could not be identified in CPCSSN. We determined sex/gender as recorded in the EMR—as practitioners entered this information, we cannot be certain whether sex or gender was recorded. We calculated age based on patient birth dates. We identified patient comorbidities at baseline for diseases with case definitions validated in CPCSSN data: cardiovascular disease; liver cirrhosis; chronic obstructive pulmonary disease; dementia; depression; epilepsy; hypertension; osteoarthritis; Parkinson’s disease; obesity; and dyslipidemia [ 17 , 22 – 25 ]. We estimated patients’ deprivation quintile by mapping their full postal code to neighbourhood-level Pampalon indices [ 26 ]. The Pampalon deprivation index estimates the neighbourhood social and material deprivation based on the level of education, employment, income, living situation, marital status, and single-parent status of individuals within that dissemination area according to the Census of Canada [ 26 ]. Higher Pampalon deprivation index scores indicate greater deprivation. Statistical analysis We described baseline continuous predictors using means with standard deviations [SD] or medians with first and third quartiles and categorical predictors using frequencies with percentages. We characterized the amount of missing data for predictors at baseline. Where eGFR laboratory testing was absent over follow-up, we assumed normal kidney function (i.e., the patient had not developed CKD). To evaluate the impact of this assumption, we performed a sensitivity analysis where patients without eGFR laboratory over follow-up were excluded. To compare performances between different models, we used single imputation to address missing data rather than a more complex, computationally intensive method such as multiple imputation. As a result, confidence intervals around measures of performance are artificially more precise; however, comparisons between point estimates of model performance remain valid. To ensure the imputed values were reasonable, we graphically compared imputed values against observed values using density plots [ 27 ]. We evaluated the performance of existing models within CPCSSN data using well-established validation measures: discrimination, precision, recall, and calibration. Based on the updated regression equation for each CKD prediction model (Supplementary Table 5, Additional File 1), we calculated the predicted risk of CKD within 5 years for all patients in our cohort and compared these with their observed outcome (i.e., incident CKD within 5 years). We used the receiver-operating characteristic curve and corresponding AUROC to assess the model’s ability to correctly discern between high- and low-risk patients (discrimination). We used the precision-recall curve and corresponding area under the precision-recall curve (AUPRC) to understand the balance between precision and recall for each model. Finally, we used calibration curves to assess the agreement between the predicted and observed risks (calibration) for each model. To create calibration curves, we regressed observed CKD diagnoses against the linear predictor calculated from each model using natural cubic splines. From this model, we obtained the observed probability for each patient that we then plotted against their predicted risk. We conducted all analyses in R 4.3.2 [ 28 ], including model validation using the predRupdate package [ 29 ]. We updated models by re-estimating the model intercept and scaling the model coefficients (i.e., reducing or increasing the magnitude of all coefficients by some factor). This process yields risk estimates better suited to CPCSSN's characteristics and accounts for the varying prediction horizons of different models (e.g., models predicting 3-year vs. 5-year CKD risks). We assume that 3-year and 5-year risk estimates should rank patients similarly, even if their absolute values differ. By re-estimating intercepts and scaling coefficients, we adjust for differences in the mean and distribution of risks while preserving their ranking. We evaluated performance among key groups served by primary care defined by sex/gender, age group, number of comorbidities, and deprivation quintile. Sample size We computed the minimum sample size required for external validation to estimate a 95% confidence interval (CI) for the AUROC with a width of approximately 0.04, and 95% CIs for the calibration intercept and slope both with widths of approximately 0.2 [ 30 ]. We considered multiple scenarios, varying the anticipated AUROC and prevalence of CKD based on the previous models we identified and their development datasets. Based on these specifications, the required minimum sample size ranged from 689 to 21,925. Ethics approval Our study was approved by the University of Calgary Conjoint Health Research Ethics Board under study ID REB21-1741. All patients provided consent to contribute their records to CPCSSN. Results Of the 47 prediction models for CKD we considered, only 6 had information available on all predictors and 7 had information available for all but one predictor available within CPCSSN (Fig. 1). Many excluded models required predictors such as demographic (e.g., race or ethnicity) or health behavior factors (e.g., diet or physical activity) that are unavailable within CPCSSN. The 13 selected models were developed in various European, Asian, and North American countries using logistic, multinomial logistic, Cox proportional hazards, or Weibull regression based on a range of data sources, including registries, administrative databases, electronic medical records, prospective observational studies, and randomized controlled trials. The included models were published between 2010 and 2020; however, development data for these models spanned time periods from 1990 to 2019. Most models were developed exclusively among people with type 2 diabetes; however, the Vergouwe et al. model [ 31 ] was developed among people with type 1 diabetes. The included models displayed moderate to strong internal performance based on their development data (AUROCs ranged from 0.65 to 0.87). Figure 1: CKD models included in analysis, including availability of predictors and CKD definition. We identified 37,604 patients with diabetes for external validation of CKD prediction models (Fig. 2); this CPCSSN diabetes cohort exceeded all minimum sample size estimates. Cohort characteristics are summarized in Table 1 . Supplementary Table 6, Additional File 1 compares characteristics of our validation cohort with characteristics of the development cohorts for the selected models. One model did not report any characteristics for their cohort (Dagliati et al. [ 32 ]). The mean age of the CPCSSN diabetes cohort (63.4 years) approximated those of the development cohorts, except Vergouwe et al. [ 31 ] which used a much younger cohort (mean age: 33 years). There was considerable heterogeneity in the sex/gender distribution of the development cohorts we considered; the CPCSSN diabetes cohort had slightly more males/men than females/women, similar to some development cohorts with approximately equal sex/gender distributions but dissimilar from those that were disproportionately split (e.g., nearly two-thirds of the Afghahi et al. cohort [ 33 ] and 87% of the Nelson [ 34 ] cohort were male/men). The CPCSSN diabetes cohort had a lower mean HbA1c values than the development cohorts. Similarly, systolic and diastolic blood pressures were lower among the CPCSSN diabetes cohort than the development cohorts. However, the CPCSSN diabetes cohort had a higher average body mass index (BMI) compared to the development cohorts. Table 1 Characteristics of CPCSSN diabetes cohort for external validation. N = 37,604 Demographic variables Age (years), mean ± SD 63.4 ± 12.2 Age group, n (%) 18 to 39 1,073 (2.9) 40 to 64 18,370 (48.9) 65 and older 18,161 (48.3) Sex/gender, n (%) Male/men 23,174 (53.0) Female/women 20,516 (47.0) Social and material deprivation, n (%) 1st quintile (least deprived) 6,564 (17.5) 2nd quintile 7,521 (20.0) 3rd quintile 7,032 (18.7) 4th quintile 7,123 (18.9) 5th quintile (most deprived) 7,039 (18.7) Missing 2,325 (6.2) Rurality (urban), n (%) 29,088 (77.4) Health behaviour variables Smoking, n (%) Not current 1,111 (3.0) Non-smoker 1,080 (2.9) Ex-smoker 1,344 (3.6) Current smoker 1,417 (3.8) Missing 32,652 (86.8) Diabetes-related variables Fasting blood glucose (mg/dL), mean ± SD 136.3 ± 45.5 HbA1c (%), median (first–third quartiles) 6.7 (6.3—7.4) Diabetes duration (years), median (first–third quartiles) 2.8 (1.3—5.1) Diabetes duration ≥7 years, n (%) 5,018 (13.3) Oral diabetes drugs, n (%) 21,460 (57.1) Insulin, n (%) 4,128 (11.0) Oral diabetes drugs or insulin, n (%) 22,477 (59.8) Anthropometric variables Weight (kg), mean ± SD 91.0 ± 24.9 BMI (kg/m 2 ), mean ± SD 32.3 ± 7.4 Physical examination variables Systolic blood pressure (mmHg), mean ± SD 131 ± 16 Diastolic blood pressure (mmHg), mean ± SD 76 ± 10 Pulse pressure (mmHg), mean ± SD 55 ± 14 Laboratory variables eGFR (mL/min/1.73 m2), mean ± SD 84 ± 18 Urine albumin (mg/dL), mean ± SD 3.2 ± 5.9 Urine creatinine (mg/dL), mean ± SD 127.8 ± 70.7 Urinary ACR (mg/mmol), median (first–third quartiles/IQR) 1.3 (0.6—2.9) Serum creatinine (µmol/L), mean ± SD 73 ± 17 Triglycerides (mmol/L), mean ± SD 1.7 ± 1.0 LDL cholesterol (mmol/L), mean ± SD 2.3 ± 0.9 HDL cholesterol (mmol/L), mean ± SD 1.2 ± 0.3 Total cholesterol (mmol/L), mean ± SD 4.3 ± 1.1 Cholesterol-HDL ratio, mean ± SD 3.7 ± 1.2 Medical history variables Antihypertensive medication, n (%) 24,855 (66.1) RAS-antagonist, n (%) 21,198 (56.4) Lipid-lowering drugs, n (%) 21,745 (57.8) Anticoagulants, n (%) 7,840 (20.8) Hypertension, n (%) 19,121 (50.8) Dyslipidemia, n (%) 17,434 (46.4) Hypertension or dyslipidemia, n (%) 27,657 (73.5) Diabetic retinopathy, n (%) 643 (1.7) Cerebrovascular disease, n (%) 1,137 (3.0) Previous atrial fibrillation, n (%) 668 (1.8) Macrovascular complications, n (%) 3,238 (8.6) Previous cardiovascular disease, n (%) 5,631 (15.0) Comorbidities, n (%) None 3,692 (9.8) One 9,062 (24.1) Two 10,826 (28.8) Three or more 14,024 (37.3) RAS-antagonist: renin–angiotensin system antagonist. Figure 2: CPCSSN patients included in analysis, including reason for exclusion. Table 2 Incidence proportion and rate of incident CKD over follow-up* (n = 37,604). Incidence proportion, % (95% CI) Incidence rate, per 1000 person-years (95% CI) Overall 14.6 (14.3 to 15.0) 33.1 (32.2 to 34.0) Sex/gender Female/Woman 15.0 (14.5 to 15.6) 33.9 (32.6 to 35.2) Male/Man 14.3 (13.8 to 14.8) 32.3 (31.2 to 33.5) Age at baseline 18 to 39 1.2 (0.7 to 2.1) 2.8 (1.6 to 4.7) 40 to 64 6.2 (5.9 to 6.6) 13.7 (12.9 to 14.5) 65 and older 24.0 (23.4 to 24.6) 55.1 (53.5 to 56.7) Comorbidities None 12.1 (11.0 to 13.2) 27.0 (24.5 to 29.5) One 12.5 (11.8 to 13.2) 28.0 (26.4 to 29.7) Two 14.3 (13.7 to 15.0) 32.2 (30.7 to 33.9) Three or more 17.0 (16.3 to 17.6) 38.7 (37.2 to 40.3) Social and material deprivation 1st quintile (least deprived) 14.4 (13.5 to 15.2) 32.2 (30.2 to 34.3) 2nd quintile 14.4 (13.6 to 15.2) 32.3 (30.3 to 34.2) 3rd quintile 14.0 (13.2 to 14.8) 31.5 (29.6 to 33.5) 4th quintile 14.9 (14.1 to 15.7) 33.6 (31.6 to 35.6) 5th quintile (most deprived) 14.8 (14.0 to 15.6) 33.4 (31.4 to 35.5) CKD: chronic kidney disease; CI: confidence interval. * Two or more laboratory values separated by at least 90 days but not more than 1 year apart reporting an eGFR less than 60 mL/min/1.73 m 2 . Over the 5-year follow-up period, we found that 14.6% of patients with diabetes developed incident CKD with an incidence rate of 33.1 cases per 1000 person-years (Table 2 ). Though CKD incidence proportions and rates were similar between males/men and females/women, we observed increased proportions and rates among older patients, patients with more comorbidities, and patients living in areas with higher deprivation. Table 3 Discrimination of selected prediction models for incident CKD among CPCSSN patients with diabetes. First author Publication year Model Reported development AUROC CPCSSN AUROC CPCSSN AUPRC Afghahi [ 33 ] 2011 Logistic 0.67 to 0.87 0.822 (0.817 to 0.822) 0.445 (0.44 to 0.45) Basu [ 35 ] 2017 Cox 0.76 0.621 (0.613 to 0.621) 0.211 (0.206 to 0.215) Dagliati [ 32 ] 2018 Logistic 0.701 0.515 (0.507 to 0.515) 0.149 (0.146 to 0.153) Dorajoo [ 36 ] 2017 Logistic 0.76 0.572 (0.564 to 0.572) 0.185 (0.181 to 0.189) Dunkler [ 37 ] 2015 Multinomial logistic 0.68 0.524 (0.516 to 0.524) 0.149 (0.146 to 0.153) Hu [ 38 ] 2020 Logistic 0.74 0.492 (0.483 to 0.492) 0.171 (0.168 to 0.175) Jardine [ 39 ] 2012 Cox 0.65 0.752 (0.745 to 0.752) 0.359 (0.354 to 0.364) Low [ 40 ] 2017 Logistic 0.83 0.661 (0.654 to 0.661) 0.235 (0.231 to 0.24) Miao [ 41 ] 2017 Cox 0.80 0.526 (0.518 to 0.526) 0.152 (0.149 to 0.156) Nelson [ 34 ] 2019 Weibull 0.80 0.826 (0.82 to 0.826) 0.467 (0.462 to 0.472) Riphagen [ 42 ] 2015 Cox 0.69 0.679 (0.672 to 0.679) 0.248 (0.244 to 0.253) Tanaka [ 43 ] 2013 Cox 0.77 0.571 (0.562 to 0.571) 0.18 (0.176 to 0.184) Vergouwe [ 31 ] 2010 Logistic 0.69 0.549 (0.54 to 0.549) 0.178 (0.175 to 0.182) AUROC: area under the receiver-operating characteristic curve; AUPRC: area under the precision-recall curve. Overall performance of the CKD prediction models in CPCCSN was mixed (Table 3 ), with AUROCs (discrimination) ranging from 0.492 to 0.826. The models developed by Nelson et al. [ 34 ] and Afghahi et al. [ 33 ] had the best discrimination, whereas several models performed only slightly better or no better than chance (AUROC < 0.60), including models developed by Dagliati et al. [ 32 ], Dorajoo et al. [ 36 ], Dunkler et al. [ 37 ], Hu et al. [ 38 ], Miao et al. [ 41 ], Tanaka et al. [ 43 ], and Vergouwe et al. [ 31 ] The model developed by Jardine et al. [ 39 ] also performed strongly, with an AUROC of 0.752 (95% CI: 0.745 to 0.752). We found similar patterns in performance considering the AUPRC: the Nelson et al. model had the highest AUPRC (0.467 [95% CI: 0.462 to 0.472]) while the Dagliati et al. and Dunkler et al. models had the lowest (0.149 [95% CI: 0.146 to 0.153]). All models displayed poor agreement between predicted and observed risks (calibration), though in some cases calibration improved after updating (via intercept re-estimation and coefficient scaling). Even after model updating, calibrations were heterogeneous with most models displaying some miscalibration (Fig. 3 ). We found predicted risks from the Afghahi et al. model closely approximated observed risks, except for a small proportion (less than 5%) of predicted risks that exceeded values of 50% and overestimated observed risks. The Jardine et al. model had severe underestimation of risk among a small group of predicted low risk patients but good calibration thereafter. The Nelson et al. model overestimated lower risk patients and underestimated higher risk patients, though to a maximum error of approximately 10%. In some cases, coefficient scaling applied to models with poor predictive performance resulted in extremely poor calibration, with predicted values closely clustered together to minimize error in the model; however, these models do not provide meaningful predicted values. For example, the calibration plot for the Dagliati et al. model shows predicted risks clustered around one value, providing little to no valuable risk information as all patients were assigned almost the same predicted risk. Figure 3 : Calibration plots of selected prediction models for incident CKD after model updating among CPCSSN patients with diabetes. Each plot shows the predicted probability compared to the observed probability (solid blue line); the dashed line represents ideal calibration. Considering subgroups defined by sex/gender, age group at baseline, number of comorbidities, and deprivation quintile, we observed considerable differences in performance across some subgroups. For most models, discriminative performance (AUROC) declined with increasing age (Supplementary Table 7, Additional File 1); however, according to the AUPRC, performance improved with increasing age (Supplementary Table 8, Additional File 1). After model updating, patients aged 65 and older displayed the best calibration intercepts compared to younger patients, though calibration slopes were heterogeneous across age groups (Supplementary Table 9, Additional File 1). Like the patterns we observed by age group, we found decreasing discriminative performance (AUROC) with increasing numbers of comorbidities but increasing AUPRC with increasing numbers of comorbidities. However, we observed no patterns in calibration (intercept or slope) depending on the number of comorbidities. We observed no difference in performance according to sex/gender or deprivation quintile. In our sensitivity analysis, we found models performed similarly after excluding 2,030 patients (5.4%) who had no eGFR testing over follow-up (Supplementary Tables 10 to 13, Additional File 1): overall AUROCs were slightly higher due to the increased incidence of CKD in this cohort. Discussion Principal findings We externally validated several CKD clinical prediction models for use in Canadian primary care using EMR data, considering performance within specific subgroups. Of the CKD prediction models previously identified in the literature [ 6 , 7 ], we found only 13 models where most predictors could be successfully characterized using CPCSSN data (≤1 unavailable). We found performance of these models within CPCSSN was mixed, though some models demonstrated strong performance, namely the models developed by Afghahi et al., Jardine et al. and Nelson et al. Comparing subgroups defined by sex/gender, age, number of comorbidities, and deprivation quintile, we found similar model performance across sex/genders and deprivation quintiles; however, greater discrimination (AUROC) was observed among younger patients with fewer comorbidities, yet greater precision and recall (AUPRC) was observed among older patients with more comorbidities. This pattern may be explained as AUROC is prone to optimism when the outcome is rare, whereas AUPRC is not subject to this optimism [ 44 ]. Age- and comorbidity-specific patterns were similar across all the models we assessed. Model performance in CPCSSN may have differed from performance in their development cohorts for various reasons. Differences in case-mix between the development cohort and the CPCSSN diabetes cohort may contribute to the performance differences we observed; Supplementary Table 6, Additional File 1 presents the baseline characteristic for the CPCSSN diabetes cohort and all development cohorts. For example, the mean age among the Vergouwe et al. development cohort was much younger than that of the CPCSSN diabetes cohort (33 years vs. 63.4 years). Further, differences in how predictors and/or incident CKD were measured may have also contributed to differences in model performance. For some models, performance in the CPCSSN diabetes cohort was markedly worse than the development cohort (i.e., models developed by Dagliati et al., Dorajoo et al., Dunkler et al., Hu et al., Miao et al., Tanaka et al., and Vergouwe et al.). Excluding Dunker et al. and Miao et al., these models did not include age as a predictor, despite known increases in incident CKD risk associated with age [ 1 ]. In general, models that had fewer predictors available in CPCSSN tended to have poorer performance in the CPCSSN diabetes cohort compared to models with more predictors. For example, the model with the best performance in the CPCSSN diabetes cohort developed by Nelson et al. included 14 available predictors, whereas the models developed by Dagliati et al., Dorajoo et al., Dunkler et al., Tanaka et al., and Vergouwe et al. used only 5 or fewer predictors. Implications The CKD models developed by Afghahi et al. and Nelson et al. demonstrated robust performance using Canadian primary care data. All predictors necessary for the Afghahi et al. model are routinely collected and stored in CPCSSN, facilitating straightforward integration into clinical practice; whereas the Nelson et al. model includes one predictor that was not available in CPCSSN data (i.e., race) but demonstrated strong performance nonetheless. Collecting race information could improve the performance of the Nelson et al. model. Another strong performing model was developed by Jardine et al.; however, it displayed greater miscalibration, especially among predicted low risk patients. Next, these models should be implemented and evaluated in clinical practice to determine how to best support practitioner decision-making to improve patient health behaviours and reduce risk of incident CKD. Clinical prediction models for incident CKD have not been used widely in Canadian primary care; however, similar tools have had some adoption, such as the KidneyWise toolkit that was implemented in primary care practices by the Ontario Renal Network. This toolkit includes the Kidney Failure Risk Equation that predicts the risk of end-stage kidney disease among patients with CKD based on their age, sex, eGFR and urine ACR [ 45 ]. While KidneyWise did not improve the appropriateness of primary care referrals to nephrology, it was successful in modifying practitioner behaviours such as including a urine ACR result referrals [ 46 ]. Existing tools like the KidneyWise toolkit could be modified to include a clinical prediction model for incident CKD among patients with diabetes, such as the strongly performing models we identified. Strengths and limitations We analysed a large, Canada-wide cohort of representative patients from primary care practices using EMRs to measure and detect differences in the performance of CKD prediction models. Indeed, our cohort size exceeded the largest estimate of required sample size by more than 15,000 patients. Further, our external validation involved numerous primary care practices across Canada where a CKD clinical prediction model could be implemented, offering crucial performance data to support its use in this context [ 8 ]. We only validated models that had information for most predictors available in CPCSSN; thus, models that relied heavily on factors such as ethnicity, education, physical activity, and alcohol use were excluded. Although this limited the range of models we evaluated, the models we considered can be integrated into an EMR system to facilitate model uptake and generate risk predictions using only the data contained within the EMR [ 47 ]. We recognize that our study has some limitations. Missing data was common among some predictors; however, we used a robust process to impute missing data and found that imputed predictor distributions closely approximated those observed. Similarly, eGFR values were not collected for some patients. In this case, we assumed that missing eGFR values did not indicate incident CKD. Sensitivity analyses suggested the impact of this assumption on our results was minimal. Blinding to mitigate unbiased outcome assessment was not possible; however, CKD diagnoses were based on laboratory measurements that were not influenced by practitioner bias. We could not distinguish between people with type 1 and 2 diabetes; thus, we could not confirm whether model performance differed by diabetes type. Given most of the models we evaluated were developed in patients with type 2 diabetes, models should be applied with caution among patients with type 1 diabetes as we cannot be certain that performance will be consistent between patients with type 1 diabetes and patients with type 2 diabetes. Additionally, we had no information describing patients’ race or ethnicity—despite known associations between these factors and risk of incident CKD [ 48 ]—precluding our ability to use these factors as predictors or confirm model performance among groups defined by these characteristics. Finally, our validation was limited to patients managed by their primary care practitioner; model performance may differ for patients managed by endocrinologists or other specialists where predictive relationships may differ. Conclusions Our study externally validated several models for CKD among patients with diabetes in Canadian primary care. Performance of these models was mixed, though the models developed by Afghahi et al., Jardine et al. and Nelson et al. displayed strong discrimination and calibration in the CPCSSN diabetes cohort overall and across a variety of subgroups. Despite strong performance, these models displayed opportunities for improved performance. Additionally, a single model must be selected for use to predict CKD in clinical settings, ignoring all other models. Ensemble methods (a type of machine learning) could be used to combine multiple prediction models for CKD to hopefully improve the performance in predicting CKD [ 49 , 50 ]. In future research, we will explore the use of ensemble methods to integrate risk information across multiple models and improve CKD prediction. Prior to regular clinical use, these models should be implemented in clinical practice and evaluated for their impact on practitioner and patient outcomes, such as use of risk-lowering therapies or incident CKD. If successful, these models hold promise in achieving widespread adoption to help prevent or delay CKD and related sequelae (e.g., end-stage renal disease) among people with diabetes, significantly improving patient outcomes and quality of life. Abbreviations AUPRC area under the precision-recall curve AUROC area under the receiver-operating characteristic curve BMI body mass index CI confidence interval CKD chronic kidney disease CPCSSN Canadian Primary Care Sentinel Surveillance Network EMR electronic medical record Declarations Ethics approval and consent to participate Our study was approved by the University of Calgary Conjoint Health Research Ethics Board under study ID REB21-1741. All patients provided consent to contribute their records to CPCSSN. Consent for publication Not applicable. Availability of data and materials The dataset supporting the conclusions of this article is available in the CPCSSN repository upon reasonable request, https://cpcssn.ca/dar/. Competing interests The authors declare that they have no competing interests. Funding This research partly comprises Jason E. Black’s doctoral work, which is supported by the Achievers in Medical Sciences, Alberta Innovates, and Artificial Intelligence for Public Health scholarships. Authors’ contributions JEB and TSW conceptualized and formalized the research and developed the methodology. All authors reviewed and approved the proposed methodology. JEB performed all statistical analyses and drafted the manuscript. All authors (JEB, DJTC, PER, KAM, and TSW) substantively reviewed and edited the manuscript and approved the submitted version. Acknowledgements Not applicable References Gross JL, de Azevedo MJ, Silveiro SP, Canani LH, Caramori ML, Zelmanovitz T (2005) Diabetic Nephropathy: Diagnosis, Prevention, and Treatment. Diabetes Care 28. Bello AK, Ronksley PE, Tangri N, et al (2019) Prevalence and Demographics of CKD in Canadian Primary Care Practices: A Cross-sectional Study. Kidney Int Rep 4. McFarlane P, Cherney D, Gilbert R, Senior P (2018) Diabetes Canada 2018 Clinical Practice Guidelines for the Prevention and Management of Diabetes in Canada: Chronic Kidney Disease in Diabetes. Can J Diabetes Drzewoski J, Kasznicki J, Trojanowski Z (2009) The role of “metabolic memory” in the natural history of diabetes mellitus. Pol Arch Med Wewn 119. Copur S, Rossing P, Afsar B, Sag AA, Siriopol D, Kuwabara M, Ortiz A, Kanbay M (2021) A primer on metabolic memory: why existing diabesity treatments fail. Clin Kidney J 14. Ndjaboue R, Ngueta G, Rochefort-Brihay C, et al (2022) Prediction models of diabetes complications: a scoping review. J Epidemiol Community Health. https://doi.org/10.1136/jech-2021-217793 Slieker RC, van der Heijden AAWA, Siddiqui MK, et al (2021) Performance of prediction models for nephropathy in people with type 2 diabetes: systematic review and external validation study. BMJ 374. Sperrin M, Riley RD, Collins GS, Martin GP (2022) Targeted validation: validating clinical prediction models in their intended population and setting. Diagn Progn Res 6. Rajkomar A, Hardt M, Howell MD, Corrado G, Chin MH (2018) Ensuring Fairness in Machine Learning to Advance Health Equity. Ann Intern Med 169. Chen IY, Pierson E, Rose S, Joshi S, Ferryman K, Ghassemi M (2021) Ethical Machine Learning in Healthcare. Annu Rev Biomed Data Sci 4. Moons KGM, Altman DG, Vergouwe Y, Royston P (2009) Prognosis and prognostic research: Application and impact of prognostic models in clinical practice. BMJ Online 338. Barda N, Yona G, Rothblum GN, Greenland P, Leibowitz M, Balicer R, Bachmat E, Dagan N (2021) Addressing bias in prediction models by improving subpopulation calibration. J Am Med Inform Assoc JAMIA 28. Garies S, Birtwhistle R, Drummond N, Queenan J, Williamson T (2017) Data Resource Profile: National electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Int J Epidemiol 46. Queenan JA, Williamson T, Khan S, Drummond N, Garies S, Morkem R, Birtwhistle R (2016) Representativeness of patients and providers in the Canadian Primary Care Sentinel Surveillance Network: a cross-sectional study. CMAJ Open 4. Nie JX, Wang L, Tracy CS, Moineddin R, Upshur RE (2008) Health care service utilization among the elderly: findings from the Study to Understand the Chronic Condition Experience of the Elderly and the Disabled (SUCCEED project). J Eval Clin Pract 14. Morkem R, Salman A, Herman C, Shah R, Wong S, Barber D (2023) CPCSSN Data Quality: An Opportunity for Enhancing Canadian Primary Care Data. Williamson T, Green ME, Birtwhistle R, Khan S, Garies S, Wong ST, Natarajan N, Manca D, Drummond N (2014) Validating the 8 CPCSSN Case Definitions for Chronic Disease Surveillance in a Primary Care Database of Electronic Health Records. Ann Fam Med 12. Lethebe BC, Williamson T, Garies S, McBrien K, Leduc C, Butalia S, Soos B, Shaw M, Drummond N (2019) Developing a case definition for type 1 diabetes mellitus in a primary care electronic medical record database: an exploratory study. Can Med Assoc Open Access J 7. Boer IH de, Caramori ML, Chan JCN, et al (2020) KDIGO 2020 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease. Kidney Int 98. Committee; CDACPGE, Cheng AYY (2013) Canadian Diabetes Association 2013 clinical practice guidelines for the prevention and management of diabetes in Canada. Can J Diabetes 37. Kazancioğlu R (2013) Risk factors for chronic kidney disease: an update. Kidney Int Suppl 3. Thomas RD, Kosowan L, Rabey M, Bell A, Connelly KA, Hawkins NM, Casey CG, Singer AG (2023) Validation of a case definition to identify patients diagnosed with cardiovascular disease in Canadian primary care practices. CJC Open. https://doi.org/10.1016/j.cjco.2023.04.003 Faisal N, Kosowan L, Zafari H, Zulkernine F, Lix L, Mahar A, Singh H, Renner E, Singer A (2023) Development and validation of a case definition to estimate the prevalence and incidence of cirrhosis in pan-Canadian primary care databases. Can Liver J Rigobon AV, Birtwhistle R, Khan S, Barber D, Biro S, Morkem R, Janssen I, Williamson T (2015) Adult obesity prevalence in primary care users: An exploration using Canadian Primary Care Sentinel Surveillance Network (CPCSSN) data. Can J Public Health Rev Can Sante Publique 106. Spohn O, Morkem R, Singer AG, Barber D (2024) Prevalence and management of dyslipidemia in primary care practices in Canada. Can Fam Physician 70. Pampalon R, Hamel D, Gamache P, Raymond G (2009) A deprivation index for health planning in Canada. Chronic Dis Can 29. Nguyen CD, Carlin JB, Lee KJ (2017) Model checking in multiple imputation: an overview and case study. Emerg Themes Epidemiol 14. R Core Team (2023) R: A Language and Environment for Statistical Computing. Martin GP, Jenkins D, Sperrin M (2023) predRupdate: Prediction model validation and updating. Pavlou M, Qu C, Omar RZ, Seaman SR, Steyerberg EW, White IR, Ambler G (2021) Estimation of required sample size for external validation of risk models for binary outcomes. Stat Methods Med Res 30. Vergouwe Y, Soedamah-Muthu SS, Zgibor J, et al (2010) Progression to microalbuminuria in type 1 diabetes: development and validation of a prediction rule. Diabetologia 53. Dagliati A, Marini S, Sacchi L, Cogni G, Teliti M, Tibollo V, De Cata P, Chiovato L, Bellazzi R (2018) Machine Learning Methods to Predict Diabetes Complications. J Diabetes Sci Technol 12. Afghahi H, Cederholm J, Eliasson B, Zethelius B, Gudbjörnsdottir S, Hadimeri H, Svensson MK (2011) Risk factors for the development of albuminuria and renal impairment in type 2 diabetes–the Swedish National Diabetes Register (NDR). Nephrol Dial Transplant Off Publ Eur Dial Transpl Assoc - Eur Ren Assoc 26. Nelson RG, Grams ME, Ballew SH, et al (2019) Development of Risk Prediction Equations for Incident Chronic Kidney Disease. JAMA 322. Basu S, Sussman JB, Berkowitz SA, Hayward RA, Yudkin JS (2017) Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials. Lancet Diabetes Endocrinol 5. Dorajoo SR, Ng JSL, Goh JHF, Lim SC, Yap CW, Chan A, Lee JYC (2017) HbA1c variability in type 2 diabetes is associated with the occurrence of new-onset albuminuria within three years. Diabetes Res Clin Pract 128. Dunkler D, Gao P, Lee SF, et al (2015) Risk Prediction for Early CKD in Type 2 Diabetes. Clin J Am Soc Nephrol CJASN 10. Hu Y, Shi R, Mo R, Hu F (2020) Nomogram for the prediction of diabetic nephropathy risk among patients with type 2 diabetes mellitus based on a questionnaire and biochemical indicators: a retrospective study. Aging 12. Jardine MJ, Hata J, Woodward M, et al (2012) Prediction of kidney-related outcomes in patients with type 2 diabetes. Am J Kidney Dis Off J Natl Kidney Found 60. Low S, Lim SC, Zhang X, Zhou S, Yeoh LY, Liu YL, Tavintharan S, Sum CF (2017) Development and validation of a predictive model for Chronic Kidney Disease progression in Type 2 Diabetes Mellitus based on a 13-year study in Singapore. Diabetes Res Clin Pract 123. Miao DD, Pan EC, Zhang Q, Sun ZM, Qin Y, Wu M (2017) Development and Validation of a Model for Predicting Diabetic Nephropathy in Chinese People. Biomed Environ Sci BES 30. Riphagen IJ, Kleefstra N, Drion I, et al (2015) Comparison of Methods for Renal Risk Prediction in Patients with Type 2 Diabetes (ZODIAC-36). PLOS ONE 10. Tanaka S, Tanaka S, Iimuro S, et al (2013) Predicting macro- and microvascular complications in type 2 diabetes: the Japan Diabetes Complications Study/the Japanese Elderly Diabetes Intervention Trial risk engine. Diabetes Care 36. Ozenne B, Subtil F, Maucort-Boulch D (2015) The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol 68. Ontario Renal Network (2018) KidneyWise Toolkit. https://www.ontariorenalnetwork.ca/en/kidney-care-resources/clinical-tools/primary-care-tools/kidneywise/toolkit . Accessed 8 Jan 2024 Brimble KS, Boll P, Grill AK, Molnar A, Nash DM, Garg A, Akbari A, Blake PG, Perkins D (2020) Impact of the KidneyWise toolkit on chronic kidney disease referral practices in Ontario primary care: a prospective evaluation. BMJ Open 10. Lee TC, Shah NU, Haack A, Baxter SL (2020) Clinical Implementation of Predictive Models Embedded within Electronic Health Record Systems: A Systematic Review. Inform MDPI 7. Patzer RE, McClellan WM (2012) Influence of race, ethnicity and socioeconomic status on kidney disease. Nat Rev Nephrol 8. Polikar R (2012) Ensemble Learning. In: Zhang C, Ma Y (eds) Ensemble Mach. Learn. Methods Appl. Springer US, Boston, MA, pp 1–34 Hu X, Madden LV, Edwards S, Xu X (2015) Combining Models is More Likely to Give Better Predictions than Single Models. Httpdxdoiorg101094PHYTO-11-14-0315-R 105. Additional Declarations No competing interests reported. Supplementary Files AdditionalFile1.docx Supplementary results can be found in Additional file 1 (Word document; Additional file 1.docx). This file includes the case definitions for diabetes and type 1 diabetes, measurement of predictors for incident CKD, regression coefficients for each selected CKD model, baseline characteristics for development cohorts of each selected CKD model, subgroup performance of each CKD model, and results from our sensitivity analysis. AdditionalFile2.pdf The TRIPOD+AI reported checklist can be found in Additional File 2 (pdf; Additional file 2.pdf). This file includes a completed version of the TRIPOD+AI reporting checklist for this study. Cite Share Download PDF Status: Published Journal Publication published 11 Nov, 2025 Read the published version in Diagnostic and Prognostic Research → Version 1 posted Editorial decision: Revision requested 09 Jul, 2025 Reviews received at journal 09 Jul, 2025 Reviewers agreed at journal 03 Jul, 2025 Reviews received at journal 20 May, 2025 Reviewers agreed at journal 12 May, 2025 Reviewers invited by journal 09 May, 2025 Editor assigned by journal 04 Feb, 2025 Submission checks completed at journal 04 Feb, 2025 First submitted to journal 31 Jan, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5937923","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":411049995,"identity":"3b2ddc42-7af6-4eeb-a0c3-b46b07bc9154","order_by":0,"name":"Jason E. Black","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAUlEQVRIie3PMWrDMBSA4WdU1OWZrioJ9hUkDKFT1l7DYFCWDIUuBRuiKVkKXjP0MIGAvKS7IRkSAuqSwUeooqlQZDwGon+QhOBDegCh0A0WKbdtxgA0OtrTeDBBSwi3Jxz6mCOUDSJk1ZzOb3DAp5WWJVZTTF+/DYNq6v/Y5zzL1mCQ7aTeoy5Q7GYTBrromWVORwhbhPZxuY8VQaEkZZEiflL/GEdSS95jtUBRmytZ+Mk6nzjCW6pJrKxl7pVtD7lkGXJjR5DF85dukDNDXnLdeImoZ6czfhySpNGiu1RlktYyaruq9BN1XfmfG76BB5Z7AUD6/0YB6XpEKBQK3V+/sMFLzG/+oFsAAAAASUVORK5CYII=","orcid":"","institution":"University of Calgary","correspondingAuthor":true,"prefix":"","firstName":"Jason","middleName":"E.","lastName":"Black","suffix":""},{"id":411049996,"identity":"88dd51fc-bd68-4046-a4ed-f9b8441be06b","order_by":1,"name":"David JT. Campbell","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"JT.","lastName":"Campbell","suffix":""},{"id":411049997,"identity":"1f5fcaa8-2b12-4745-988b-eeb214a42477","order_by":2,"name":"Paul E. Ronksley","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Paul","middleName":"E.","lastName":"Ronksley","suffix":""},{"id":411049998,"identity":"7bfab569-1afa-46c4-80c7-fbce9154950c","order_by":3,"name":"Kerry A. McBrien","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Kerry","middleName":"A.","lastName":"McBrien","suffix":""},{"id":411049999,"identity":"45940a88-4671-4470-a33d-76cdec4a1389","order_by":4,"name":"Tyler S. Williamson","email":"","orcid":"","institution":"University of Calgary","correspondingAuthor":false,"prefix":"","firstName":"Tyler","middleName":"S.","lastName":"Williamson","suffix":""}],"badges":[],"createdAt":"2025-01-31 17:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5937923/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5937923/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s41512-025-00208-5","type":"published","date":"2025-11-11T15:56:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":75600309,"identity":"5603c646-cf01-4a0a-b690-1f270cf9a3a0","added_by":"auto","created_at":"2025-02-06 08:40:48","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":68307,"visible":true,"origin":"","legend":"\u003cp\u003eCKD models included in analysis, including availability of predictors and CKD definition.\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/5cc6a1434f04e8937b3a7851.png"},{"id":75600686,"identity":"4441c8f9-8a6f-41c1-9b36-b29e86c894c5","added_by":"auto","created_at":"2025-02-06 08:48:48","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":220075,"visible":true,"origin":"","legend":"\u003cp\u003eCPCSSN patients included in analysis, including reason for exclusion\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/0fbfbc1af1d90fcd20169355.png"},{"id":75600311,"identity":"75ab1c57-6030-4ee7-9677-9a07b0023e8c","added_by":"auto","created_at":"2025-02-06 08:40:48","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":410035,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration plots of selected prediction models for incident CKD after model updating among CPCSSN patients with diabetes. Each plot shows the predicted probability compared to the observed probability (solid blue line); the dashed line represents ideal calibration.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/e3b3b98d4e357de3f4bc87d5.png"},{"id":96104915,"identity":"ba39163f-89df-486d-950b-2fc8f972fef0","added_by":"auto","created_at":"2025-11-17 15:59:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1454599,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/50cf8d2e-5f12-43d2-82d7-4900cdb4b027.pdf"},{"id":75600313,"identity":"7e8874c0-c712-4d78-b898-6623a6aa2d61","added_by":"auto","created_at":"2025-02-06 08:40:48","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":167987,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary results can be found in Additional file 1 (Word document; Additional file 1.docx). This file includes the case definitions for diabetes and type 1 diabetes, measurement of predictors for incident CKD, regression coefficients for each selected CKD model, baseline characteristics for development cohorts of each selected CKD model, subgroup performance of each CKD model, and results from our sensitivity analysis.\u003c/p\u003e","description":"","filename":"AdditionalFile1.docx","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/565d77d7f7db9485d8d18ad7.docx"},{"id":75600312,"identity":"2708608a-c45a-48d3-87fa-97b1de1e7715","added_by":"auto","created_at":"2025-02-06 08:40:48","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":2070777,"visible":true,"origin":"","legend":"\u003cp\u003eThe TRIPOD+AI reported checklist can be found in Additional File 2 (pdf; Additional file 2.pdf). This file includes a completed version of the TRIPOD+AI reporting checklist for this study.\u003c/p\u003e","description":"","filename":"AdditionalFile2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5937923/v1/e531ec30ac5691e64c9d7a48.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Performance of clinical prediction models for chronic kidney disease among people with diabetes: External validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN)","fulltext":[{"header":"Background","content":"\u003cp\u003eDiabetes is associated with the development of several micro- and macrovascular complications, including diabetic nephropathy and chronic kidney disease (CKD) [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. In Canada, CKD remains common among people with diabetes despite established therapies and clinical guidelines aimed at preventing diabetes complications [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Early identification of patients with diabetes who are at increased risk of CKD may enable targeted risk-reducing strategies to help prevent or delay the onset of CKD. Such strategies include intensification of standard therapy; addition of novel kidney protective agents; closer monitoring of patient adherence to treatments and therapeutic efficacy; and referral for specialized renal or diabetes services [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. For example, traditional approaches to managing a patient with newly diagnosed type 2 diabetes may involve gradually introducing therapies to reduce blood glucose levels. However, this initial period following diabetes diagnosis is critical in pathophysiological processes that partly determine a patient\u0026rsquo;s progression towards microvascular complications, including nephropathy [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Patients at increased risk of CKD may benefit from rapidly achieving target glycemic levels through intensive therapies that may be less impactful in low-risk patients.\u003c/p\u003e \u003cp\u003eClinical prediction models can identify patients who are at increased risk of CKD based on patient factors, including demographic, health behaviour, clinical and diabetes-related characteristics. Many clinical prediction models that predict the risk of incident CKD (i.e., probability ranging from 0 to 1) in people with diabetes have been developed based on such patient factors [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. In Canada, opportunities exist to deploy a CKD clinical prediction model in primary care settings\u0026mdash;where patients with diabetes are most commonly managed; however, these models lack external validation demonstrating accurate predictions in this setting [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Indeed, clinical prediction models are prone to inadequate performance among subgroups, which may introduce or exacerbate inequities in care [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Only upon confirmation of robust performance in Canadian primary care should a CKD prediction model be implemented in clinical practice and subsequently evaluated for its ability to modify practitioner and patient behaviours and prevent CKD [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWe sought to externally validate existing clinical prediction models for incident CKD in Canadian primary care data. We assessed the performance of CKD prediction models overall and among specific subgroups known to be associated with incident CKD [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] (i.e., sex/gender, age group, number of comorbidities, and social and material deprivation quintile).\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy setting and data source\u003c/h2\u003e \u003cp\u003eWe conducted a retrospective cohort study using data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN), a pan-Canadian collection of electronic medical record (EMR) data for more than 2\u0026nbsp;million primary care patients [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Primary care practices contribute patient data describing diagnoses, procedures, laboratory tests, medication prescriptions, and referrals, as recorded by participating practitioners in the EMR. CPCSSN was established in 2008 regularly receives EMR data extracted by 14 contributing networks. Female and older patients are overrepresented in CPCSSN compared to the general Canadian population [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]; this is expected, as female and older patients are more likely to visit primary care practitioners [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. CPCSSN uses robust processing to clean and standardize patient records (e.g., assigning diagnostic codes to free-text diagnoses) to facilitate research use [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eModels\u003c/h3\u003e\n\u003cp\u003eTwo recent systematic reviews identified and characterized clinical prediction models for CKD [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Models were developed using longitudinal data from people with pre-diabetes or type 1 or 2 diabetes. We considered 47 models published in 33 research articles, largely developed in people with type 2 diabetes. To ensure each model could feasibly be implemented within CPCSSN, we considered the availability of predictors within CPCSSN and how CKD was defined. We restricted to models where most predictors were available within CPCSSN (\u0026le;1 unavailable) and CKD was defined based on an eGFR threshold (i.e., excluding CKD definitions based on albuminuria or documentation of kidney failure), consistent with our CPCSSN incident CKD definition (see \u003cem\u003e\u0026sect;Measures\u003c/em\u003e). Selected model coefficients are presented in Supplementary Table\u0026nbsp;1, Additional File 1.\u003c/p\u003e\n\u003ch3\u003eParticipants\u003c/h3\u003e\n\u003cp\u003eWe used a validated case definition [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] (i.e., a combination of diagnostic codes, medication prescriptions, or laboratory test results; see Supplementary Table\u0026nbsp;2, Additional File 1) to identify adult patients (18+) with diabetes in CPCSSN. We excluded patients from Quebec and Manitoba because eGFR laboratory test results were not reliably available in CPCSSN. We identified a unique baseline visit for each patient as their first visit with a participating primary care practitioner in 2014. We included patients diagnosed with diabetes prior to or at baseline, but excluded patients diagnosed with probable type 1 diabetes (based on a combination of free-text terms, insulin prescriptions, and age [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]; see Supplementary Table\u0026nbsp;3, Additional File 1) within 5 years before their baseline visit, as guidelines recommend screening for CKD should commence 5 years following diagnosis for patients with type 1 diabetes [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. We included patients without an existing diagnosis of CKD (see \u0026sect;Measures) prior to baseline; with at least 3 visits in the 2 years prior to baseline; and with at least one visit within 5 years after baseline. We followed patients for up to 5 years (2014 through 2019) to examine patterns of incident CKD over time. We censored patients at their last visit during the study period to account for patients lacking further follow-up (e.g., due to moving or changing primary care providers).\u003c/p\u003e\n\u003ch3\u003eMeasures\u003c/h3\u003e\n\u003cp\u003eFor each CKD model considered, we attempted to identify all predictors using CPCSSN data. We first assessed whether the predictor was directly measured (e.g., laboratory results such as HbA1c) or whether a CPCSSN-validated case definition was available (e.g., hypertension and chronic obstructive pulmonary disease [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]). Lacking these, we searched for other case definitions validated in primary care EMR data or previous research identifying the predictor in CPCSSN. If no case definition existed, we consulted clinical colleagues to develop a case definition via a set of criteria that identify the predictor in CPCSSN. We were unable to measure predictors without any information in CPCSSN, such as most health behaviors (e.g., physical activity or alcohol use) and several laboratory tests that are not extracted by CPCSSN processing (e.g., cystatin C or serum uric acid). Details on how we identified each predictor in CPCSSN are described in Supplementary Table\u0026nbsp;4, Additional File 1.\u003c/p\u003e \u003cp\u003eWe identified diagnoses of CKD during the 5-year study period based on clinical guidelines: two or more laboratory values corresponding to an eGFR\u0026thinsp;\u0026lt;\u0026thinsp;60 mL/min/1.73 m\u003csup\u003e2\u003c/sup\u003e that were separated by \u0026ge;90 days to \u0026lt;\u0026thinsp;1 year [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSome subgroups are known to be at increased risk of CKD compared to other primary care patients with diabetes [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. We considered subgroups defined by sex/gender (female/woman and male/man), age group (18 to 39, 40 to 64, and 65 and older), number of comorbidities (none, one, two, or three or more), and social and material deprivation quintile as these subgroups could be identified within CPCSSN; other important subgroups, such as Black patients, could not be identified in CPCSSN. We determined sex/gender as recorded in the EMR\u0026mdash;as practitioners entered this information, we cannot be certain whether sex or gender was recorded. We calculated age based on patient birth dates. We identified patient comorbidities at baseline for diseases with case definitions validated in CPCSSN data: cardiovascular disease; liver cirrhosis; chronic obstructive pulmonary disease; dementia; depression; epilepsy; hypertension; osteoarthritis; Parkinson\u0026rsquo;s disease; obesity; and dyslipidemia [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan additionalcitationids=\"CR23 CR24\" citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. We estimated patients\u0026rsquo; deprivation quintile by mapping their full postal code to neighbourhood-level Pampalon indices [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. The Pampalon deprivation index estimates the neighbourhood social and material deprivation based on the level of education, employment, income, living situation, marital status, and single-parent status of individuals within that dissemination area according to the Census of Canada [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Higher Pampalon deprivation index scores indicate greater deprivation.\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eWe described baseline continuous predictors using means with standard deviations [SD] or medians with first and third quartiles and categorical predictors using frequencies with percentages.\u003c/p\u003e \u003cp\u003eWe characterized the amount of missing data for predictors at baseline. Where eGFR laboratory testing was absent over follow-up, we assumed normal kidney function (i.e., the patient had not developed CKD). To evaluate the impact of this assumption, we performed a sensitivity analysis where patients without eGFR laboratory over follow-up were excluded.\u003c/p\u003e \u003cp\u003eTo compare performances between different models, we used single imputation to address missing data rather than a more complex, computationally intensive method such as multiple imputation. As a result, confidence intervals around measures of performance are artificially more precise; however, comparisons between point estimates of model performance remain valid. To ensure the imputed values were reasonable, we graphically compared imputed values against observed values using density plots [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWe evaluated the performance of existing models within CPCSSN data using well-established validation measures: discrimination, precision, recall, and calibration. Based on the updated regression equation for each CKD prediction model (Supplementary Table\u0026nbsp;5, Additional File 1), we calculated the predicted risk of CKD within 5 years for all patients in our cohort and compared these with their observed outcome (i.e., incident CKD within 5 years). We used the receiver-operating characteristic curve and corresponding AUROC to assess the model\u0026rsquo;s ability to correctly discern between high- and low-risk patients (discrimination). We used the precision-recall curve and corresponding area under the precision-recall curve (AUPRC) to understand the balance between precision and recall for each model. Finally, we used calibration curves to assess the agreement between the predicted and observed risks (calibration) for each model. To create calibration curves, we regressed observed CKD diagnoses against the linear predictor calculated from each model using natural cubic splines. From this model, we obtained the observed probability for each patient that we then plotted against their predicted risk. We conducted all analyses in R 4.3.2 [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e], including model validation using the \u003cem\u003epredRupdate\u003c/em\u003e package [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWe updated models by re-estimating the model intercept and scaling the model coefficients (i.e., reducing or increasing the magnitude of all coefficients by some factor). This process yields risk estimates better suited to CPCSSN's characteristics and accounts for the varying prediction horizons of different models (e.g., models predicting 3-year vs. 5-year CKD risks). We assume that 3-year and 5-year risk estimates should rank patients similarly, even if their absolute values differ. By re-estimating intercepts and scaling coefficients, we adjust for differences in the mean and distribution of risks while preserving their ranking.\u003c/p\u003e \u003cp\u003e We evaluated performance among key groups served by primary care defined by sex/gender, age group, number of comorbidities, and deprivation quintile.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eSample size\u003c/h2\u003e \u003cp\u003eWe computed the minimum sample size required for external validation to estimate a 95% confidence interval (CI) for the AUROC with a width of approximately 0.04, and 95% CIs for the calibration intercept and slope both with widths of approximately 0.2 [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. We considered multiple scenarios, varying the anticipated AUROC and prevalence of CKD based on the previous models we identified and their development datasets. Based on these specifications, the required minimum sample size ranged from 689 to 21,925.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eEthics approval\u003c/h3\u003e\n\u003cp\u003e Our study was approved by the University of Calgary Conjoint Health Research Ethics Board under study ID REB21-1741. All patients provided consent to contribute their records to CPCSSN.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eOf the 47 prediction models for CKD we considered, only 6 had information available on all predictors and 7 had information available for all but one predictor available within CPCSSN (Fig.\u0026nbsp;1). Many excluded models required predictors such as demographic (e.g., race or ethnicity) or health behavior factors (e.g., diet or physical activity) that are unavailable within CPCSSN. The 13 selected models were developed in various European, Asian, and North American countries using logistic, multinomial logistic, Cox proportional hazards, or Weibull regression based on a range of data sources, including registries, administrative databases, electronic medical records, prospective observational studies, and randomized controlled trials. The included models were published between 2010 and 2020; however, development data for these models spanned time periods from 1990 to 2019. Most models were developed exclusively among people with type 2 diabetes; however, the Vergouwe et al. model [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e] was developed among people with type 1 diabetes. The included models displayed moderate to strong internal performance based on their development data (AUROCs ranged from 0.65 to 0.87).\u003c/p\u003e\n\u003cp\u003eFigure 1: CKD models included in analysis, including availability of predictors and CKD definition.\u003c/p\u003e\n\u003cp\u003eWe identified 37,604 patients with diabetes for external validation of CKD prediction models (Fig. 2); this CPCSSN diabetes cohort exceeded all minimum sample size estimates. Cohort characteristics are summarized in Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. Supplementary Table\u0026nbsp;6, Additional File 1 compares characteristics of our validation cohort with characteristics of the development cohorts for the selected models. One model did not report any characteristics for their cohort (Dagliati et al. [\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e]). The mean age of the CPCSSN diabetes cohort (63.4 years) approximated those of the development cohorts, except Vergouwe et al. [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e] which used a much younger cohort (mean age: 33 years). There was considerable heterogeneity in the sex/gender distribution of the development cohorts we considered; the CPCSSN diabetes cohort had slightly more males/men than females/women, similar to some development cohorts with approximately equal sex/gender distributions but dissimilar from those that were disproportionately split (e.g., nearly two-thirds of the Afghahi et al. cohort [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e] and 87% of the Nelson [\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e] cohort were male/men). The CPCSSN diabetes cohort had a lower mean HbA1c values than the development cohorts. Similarly, systolic and diastolic blood pressures were lower among the CPCSSN diabetes cohort than the development cohorts. However, the CPCSSN diabetes cohort had a higher average body mass index (BMI) compared to the development cohorts.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eCharacteristics of CPCSSN diabetes cohort for external validation.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"2\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eN\u0026thinsp;=\u0026thinsp;37,604\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eDemographic variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge (years), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e63.4\u0026thinsp;\u0026plusmn;\u0026thinsp;12.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge group, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18 to 39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,073 (2.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e40 to 64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18,370 (48.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e65 and older\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18,161 (48.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSex/gender, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMale/men\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23,174 (53.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFemale/women\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e20,516 (47.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSocial and material deprivation, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1st quintile (least deprived)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6,564 (17.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2nd quintile\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7,521 (20.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3rd quintile\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7,032 (18.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4th quintile\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7,123 (18.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5th quintile (most deprived)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7,039 (18.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eMissing\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2,325 (6.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRurality (urban), n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e29,088 (77.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eHealth behaviour variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSmoking, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNot current\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,111 (3.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNon-smoker\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,080 (2.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEx-smoker\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,344 (3.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCurrent smoker\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,417 (3.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eMissing\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32,652 (86.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eDiabetes-related variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFasting blood glucose (mg/dL), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e136.3\u0026thinsp;\u0026plusmn;\u0026thinsp;45.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHbA1c (%), median (first\u0026ndash;third quartiles)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.7 (6.3\u0026mdash;7.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiabetes duration (years), median (first\u0026ndash;third quartiles)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.8 (1.3\u0026mdash;5.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiabetes duration \u0026ge;7 years, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5,018 (13.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOral diabetes drugs, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e21,460 (57.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInsulin, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4,128 (11.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOral diabetes drugs or insulin, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e22,477 (59.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eAnthropometric variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWeight (kg), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e91.0\u0026thinsp;\u0026plusmn;\u0026thinsp;24.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBMI (kg/m\u003csup\u003e2\u003c/sup\u003e), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.3\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003ePhysical examination variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSystolic blood pressure (mmHg), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e131\u0026thinsp;\u0026plusmn;\u0026thinsp;16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiastolic blood pressure (mmHg), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e76\u0026thinsp;\u0026plusmn;\u0026thinsp;10\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePulse pressure (mmHg), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e55\u0026thinsp;\u0026plusmn;\u0026thinsp;14\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eLaboratory variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eeGFR (mL/min/1.73 m2), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e84\u0026thinsp;\u0026plusmn;\u0026thinsp;18\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUrine albumin (mg/dL), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.2\u0026thinsp;\u0026plusmn;\u0026thinsp;5.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUrine creatinine (mg/dL), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e127.8\u0026thinsp;\u0026plusmn;\u0026thinsp;70.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUrinary ACR (mg/mmol), median (first\u0026ndash;third quartiles/IQR)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.3 (0.6\u0026mdash;2.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSerum creatinine (\u0026micro;mol/L), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e73\u0026thinsp;\u0026plusmn;\u0026thinsp;17\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTriglycerides (mmol/L), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.7\u0026thinsp;\u0026plusmn;\u0026thinsp;1.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLDL cholesterol (mmol/L), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHDL cholesterol (mmol/L), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.2\u0026thinsp;\u0026plusmn;\u0026thinsp;0.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTotal cholesterol (mmol/L), mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCholesterol-HDL ratio, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3.7\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eMedical history variables\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAntihypertensive medication, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24,855 (66.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRAS-antagonist, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e21,198 (56.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLipid-lowering drugs, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e21,745 (57.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAnticoagulants, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7,840 (20.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHypertension, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19,121 (50.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDyslipidemia, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17,434 (46.4)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHypertension or dyslipidemia, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e27,657 (73.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiabetic retinopathy, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e643 (1.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCerebrovascular disease, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1,137 (3.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePrevious atrial fibrillation, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e668 (1.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMacrovascular complications, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3,238 (8.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePrevious cardiovascular disease, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5,631 (15.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eComorbidities, n (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNone\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3,692 (9.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOne\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9,062 (24.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTwo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10,826 (28.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThree or more\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14,024 (37.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eRAS-antagonist: renin\u0026ndash;angiotensin system antagonist.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eFigure 2: CPCSSN patients included in analysis, including reason for exclusion.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eIncidence proportion and rate of incident CKD over follow-up* (n\u0026thinsp;=\u0026thinsp;37,604).\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"3\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIncidence proportion,\u003c/p\u003e\n \u003cp\u003e% (95% CI)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eIncidence rate,\u003c/p\u003e\n \u003cp\u003eper 1000 person-years (95% CI)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eOverall\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.6 (14.3 to 15.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e33.1 (32.2 to 34.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSex/gender\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eFemale/Woman\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e15.0 (14.5 to 15.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e33.9 (32.6 to 35.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eMale/Man\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.3 (13.8 to 14.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.3 (31.2 to 33.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge at baseline\u003c/p\u003e\n \u003cp\u003e\u003cem\u003e18 to 39\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1.2 (0.7 to 2.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.8 (1.6 to 4.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e40 to 64\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6.2 (5.9 to 6.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13.7 (12.9 to 14.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e65 and older\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24.0 (23.4 to 24.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e55.1 (53.5 to 56.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eComorbidities\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eNone\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.1 (11.0 to 13.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e27.0 (24.5 to 29.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eOne\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12.5 (11.8 to 13.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e28.0 (26.4 to 29.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eTwo\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.3 (13.7 to 15.0)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.2 (30.7 to 33.9)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003eThree or more\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17.0 (16.3 to 17.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e38.7 (37.2 to 40.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSocial and material deprivation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e1st quintile (least deprived)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.4 (13.5 to 15.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.2 (30.2 to 34.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e2nd quintile\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.4 (13.6 to 15.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32.3 (30.3 to 34.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e3rd quintile\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.0 (13.2 to 14.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31.5 (29.6 to 33.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e4th quintile\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.9 (14.1 to 15.7)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e33.6 (31.6 to 35.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cem\u003e5th quintile (most deprived)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14.8 (14.0 to 15.6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e33.4 (31.4 to 35.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"3\"\u003e\n \u003cp\u003eCKD: chronic kidney disease; CI: confidence interval.\u003c/p\u003e\n \u003cp\u003e\u003csup\u003e*\u003c/sup\u003eTwo or more laboratory values separated by at least 90 days but not more than 1 year apart reporting an eGFR less than 60 mL/min/1.73 m\u003csup\u003e2\u003c/sup\u003e.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eOver the 5-year follow-up period, we found that 14.6% of patients with diabetes developed incident CKD with an incidence rate of 33.1 cases per 1000 person-years (Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e). Though CKD incidence proportions and rates were similar between males/men and females/women, we observed increased proportions and rates among older patients, patients with more comorbidities, and patients living in areas with higher deprivation.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab3\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eDiscrimination of selected prediction models for incident CKD among CPCSSN patients with diabetes.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"6\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eFirst author\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003ePublication year\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eModel\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eReported development AUROC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eCPCSSN AUROC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eCPCSSN AUPRC\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAfghahi [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2011\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.67 to 0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.822 (0.817 to 0.822)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.445 (0.44 to 0.45)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBasu [\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2017\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCox\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.621 (0.613 to 0.621)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.211 (0.206 to 0.215)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDagliati [\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2018\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.701\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.515 (0.507 to 0.515)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.149 (0.146 to 0.153)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDorajoo [\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2017\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.572 (0.564 to 0.572)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.185 (0.181 to 0.189)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDunkler [\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2015\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMultinomial logistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.524 (0.516 to 0.524)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.149 (0.146 to 0.153)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHu [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2020\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.492 (0.483 to 0.492)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.171 (0.168 to 0.175)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eJardine [\u003cspan class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2012\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCox\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.752 (0.745 to 0.752)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.359 (0.354 to 0.364)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLow [\u003cspan class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2017\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.661 (0.654 to 0.661)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.235 (0.231 to 0.24)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMiao [\u003cspan class=\"CitationRef\"\u003e41\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2017\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCox\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.526 (0.518 to 0.526)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.152 (0.149 to 0.156)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNelson [\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2019\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWeibull\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.826 (0.82 to 0.826)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.467 (0.462 to 0.472)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRiphagen [\u003cspan class=\"CitationRef\"\u003e42\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2015\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCox\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.679 (0.672 to 0.679)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.248 (0.244 to 0.253)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTanaka [\u003cspan class=\"CitationRef\"\u003e43\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2013\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCox\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.571 (0.562 to 0.571)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.18 (0.176 to 0.184)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eVergouwe [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2010\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLogistic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.549 (0.54 to 0.549)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.178 (0.175 to 0.182)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colspan=\"6\"\u003e\n \u003cp\u003eAUROC: area under the receiver-operating characteristic curve; AUPRC: area under the precision-recall curve.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eOverall performance of the CKD prediction models in CPCCSN was mixed (Table \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e), with AUROCs (discrimination) ranging from 0.492 to 0.826. The models developed by Nelson et al. [\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e] and Afghahi et al. [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e] had the best discrimination, whereas several models performed only slightly better or no better than chance (AUROC\u0026thinsp;\u0026lt;\u0026thinsp;0.60), including models developed by Dagliati et al. [\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e], Dorajoo et al. [\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e], Dunkler et al. [\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e], Hu et al. [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e], Miao et al. [\u003cspan class=\"CitationRef\"\u003e41\u003c/span\u003e], Tanaka et al. [\u003cspan class=\"CitationRef\"\u003e43\u003c/span\u003e], and Vergouwe et al. [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e] The model developed by Jardine et al. [\u003cspan class=\"CitationRef\"\u003e39\u003c/span\u003e] also performed strongly, with an AUROC of 0.752 (95% CI: 0.745 to 0.752). We found similar patterns in performance considering the AUPRC: the Nelson et al. model had the highest AUPRC (0.467 [95% CI: 0.462 to 0.472]) while the Dagliati et al. and Dunkler et al. models had the lowest (0.149 [95% CI: 0.146 to 0.153]). All models displayed poor agreement between predicted and observed risks (calibration), though in some cases calibration improved after updating (via intercept re-estimation and coefficient scaling). Even after model updating, calibrations were heterogeneous with most models displaying some miscalibration (Fig. \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e). We found predicted risks from the Afghahi et al. model closely approximated observed risks, except for a small proportion (less than 5%) of predicted risks that exceeded values of 50% and overestimated observed risks. The Jardine et al. model had severe underestimation of risk among a small group of predicted low risk patients but good calibration thereafter. The Nelson et al. model overestimated lower risk patients and underestimated higher risk patients, though to a maximum error of approximately 10%. In some cases, coefficient scaling applied to models with poor predictive performance resulted in extremely poor calibration, with predicted values closely clustered together to minimize error in the model; however, these models do not provide meaningful predicted values. For example, the calibration plot for the Dagliati et al. model shows predicted risks clustered around one value, providing little to no valuable risk information as all patients were assigned almost the same predicted risk.\u003c/p\u003e\n\u003cp\u003eFigure \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e: Calibration plots of selected prediction models for incident CKD after model updating among CPCSSN patients with diabetes. Each plot shows the predicted probability compared to the observed probability (solid blue line); the dashed line represents ideal calibration.\u003c/p\u003e\n\u003cp\u003eConsidering subgroups defined by sex/gender, age group at baseline, number of comorbidities, and deprivation quintile, we observed considerable differences in performance across some subgroups. For most models, discriminative performance (AUROC) declined with increasing age (Supplementary Table\u0026nbsp;7, Additional File 1); however, according to the AUPRC, performance improved with increasing age (Supplementary Table\u0026nbsp;8, Additional File 1). After model updating, patients aged 65 and older displayed the best calibration intercepts compared to younger patients, though calibration slopes were heterogeneous across age groups (Supplementary Table\u0026nbsp;9, Additional File 1). Like the patterns we observed by age group, we found decreasing discriminative performance (AUROC) with increasing numbers of comorbidities but increasing AUPRC with increasing numbers of comorbidities. However, we observed no patterns in calibration (intercept or slope) depending on the number of comorbidities. We observed no difference in performance according to sex/gender or deprivation quintile.\u003c/p\u003e\n\u003cp\u003eIn our sensitivity analysis, we found models performed similarly after excluding 2,030 patients (5.4%) who had no eGFR testing over follow-up (Supplementary Tables 10 to 13, Additional File 1): overall AUROCs were slightly higher due to the increased incidence of CKD in this cohort.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003ePrincipal findings\u003c/h2\u003e \u003cp\u003e We externally validated several CKD clinical prediction models for use in Canadian primary care using EMR data, considering performance within specific subgroups. Of the CKD prediction models previously identified in the literature [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e], we found only 13 models where most predictors could be successfully characterized using CPCSSN data (\u0026le;1 unavailable). We found performance of these models within CPCSSN was mixed, though some models demonstrated strong performance, namely the models developed by Afghahi et al., Jardine et al. and Nelson et al. Comparing subgroups defined by sex/gender, age, number of comorbidities, and deprivation quintile, we found similar model performance across sex/genders and deprivation quintiles; however, greater discrimination (AUROC) was observed among younger patients with fewer comorbidities, yet greater precision and recall (AUPRC) was observed among older patients with more comorbidities. This pattern may be explained as AUROC is prone to optimism when the outcome is rare, whereas AUPRC is not subject to this optimism [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. Age- and comorbidity-specific patterns were similar across all the models we assessed.\u003c/p\u003e \u003cp\u003eModel performance in CPCSSN may have differed from performance in their development cohorts for various reasons. Differences in case-mix between the development cohort and the CPCSSN diabetes cohort may contribute to the performance differences we observed; Supplementary Table\u0026nbsp;6, Additional File 1 presents the baseline characteristic for the CPCSSN diabetes cohort and all development cohorts. For example, the mean age among the Vergouwe et al. development cohort was much younger than that of the CPCSSN diabetes cohort (33 years vs. 63.4 years). Further, differences in how predictors and/or incident CKD were measured may have also contributed to differences in model performance. For some models, performance in the CPCSSN diabetes cohort was markedly worse than the development cohort (i.e., models developed by Dagliati et al., Dorajoo et al., Dunkler et al., Hu et al., Miao et al., Tanaka et al., and Vergouwe et al.). Excluding Dunker et al. and Miao et al., these models did not include age as a predictor, despite known increases in incident CKD risk associated with age [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. In general, models that had fewer predictors available in CPCSSN tended to have poorer performance in the CPCSSN diabetes cohort compared to models with more predictors. For example, the model with the best performance in the CPCSSN diabetes cohort developed by Nelson et al. included 14 available predictors, whereas the models developed by Dagliati et al., Dorajoo et al., Dunkler et al., Tanaka et al., and Vergouwe et al. used only 5 or fewer predictors.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eImplications\u003c/h2\u003e \u003cp\u003eThe CKD models developed by Afghahi et al. and Nelson et al. demonstrated robust performance using Canadian primary care data. All predictors necessary for the Afghahi et al. model are routinely collected and stored in CPCSSN, facilitating straightforward integration into clinical practice; whereas the Nelson et al. model includes one predictor that was not available in CPCSSN data (i.e., race) but demonstrated strong performance nonetheless. Collecting race information could improve the performance of the Nelson et al. model. Another strong performing model was developed by Jardine et al.; however, it displayed greater miscalibration, especially among predicted low risk patients. Next, these models should be implemented and evaluated in clinical practice to determine how to best support practitioner decision-making to improve patient health behaviours and reduce risk of incident CKD.\u003c/p\u003e \u003cp\u003eClinical prediction models for incident CKD have not been used widely in Canadian primary care; however, similar tools have had some adoption, such as the KidneyWise toolkit that was implemented in primary care practices by the Ontario Renal Network. This toolkit includes the Kidney Failure Risk Equation that predicts the risk of end-stage kidney disease among patients with CKD based on their age, sex, eGFR and urine ACR [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]. While KidneyWise did not improve the appropriateness of primary care referrals to nephrology, it was successful in modifying practitioner behaviours such as including a urine ACR result referrals [\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. Existing tools like the KidneyWise toolkit could be modified to include a clinical prediction model for incident CKD among patients with diabetes, such as the strongly performing models we identified.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eStrengths and limitations\u003c/h2\u003e \u003cp\u003eWe analysed a large, Canada-wide cohort of representative patients from primary care practices using EMRs to measure and detect differences in the performance of CKD prediction models. Indeed, our cohort size exceeded the largest estimate of required sample size by more than 15,000 patients. Further, our external validation involved numerous primary care practices across Canada where a CKD clinical prediction model could be implemented, offering crucial performance data to support its use in this context [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. We only validated models that had information for most predictors available in CPCSSN; thus, models that relied heavily on factors such as ethnicity, education, physical activity, and alcohol use were excluded. Although this limited the range of models we evaluated, the models we considered can be integrated into an EMR system to facilitate model uptake and generate risk predictions using only the data contained within the EMR [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWe recognize that our study has some limitations. Missing data was common among some predictors; however, we used a robust process to impute missing data and found that imputed predictor distributions closely approximated those observed. Similarly, eGFR values were not collected for some patients. In this case, we assumed that missing eGFR values did not indicate incident CKD. Sensitivity analyses suggested the impact of this assumption on our results was minimal. Blinding to mitigate unbiased outcome assessment was not possible; however, CKD diagnoses were based on laboratory measurements that were not influenced by practitioner bias. We could not distinguish between people with type 1 and 2 diabetes; thus, we could not confirm whether model performance differed by diabetes type. Given most of the models we evaluated were developed in patients with type 2 diabetes, models should be applied with caution among patients with type 1 diabetes as we cannot be certain that performance will be consistent between patients with type 1 diabetes and patients with type 2 diabetes. Additionally, we had no information describing patients\u0026rsquo; race or ethnicity\u0026mdash;despite known associations between these factors and risk of incident CKD [\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]\u0026mdash;precluding our ability to use these factors as predictors or confirm model performance among groups defined by these characteristics. Finally, our validation was limited to patients managed by their primary care practitioner; model performance may differ for patients managed by endocrinologists or other specialists where predictive relationships may differ.\u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusions","content":"\u003cp\u003eOur study externally validated several models for CKD among patients with diabetes in Canadian primary care. Performance of these models was mixed, though the models developed by Afghahi et al., Jardine et al. and Nelson et al. displayed strong discrimination and calibration in the CPCSSN diabetes cohort overall and across a variety of subgroups. Despite strong performance, these models displayed opportunities for improved performance. Additionally, a single model must be selected for use to predict CKD in clinical settings, ignoring all other models. Ensemble methods (a type of machine learning) could be used to combine multiple prediction models for CKD to hopefully improve the performance in predicting CKD [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e]. In future research, we will explore the use of ensemble methods to integrate risk information across multiple models and improve CKD prediction.\u003c/p\u003e \u003cp\u003ePrior to regular clinical use, these models should be implemented in clinical practice and evaluated for their impact on practitioner and patient outcomes, such as use of risk-lowering therapies or incident CKD. If successful, these models hold promise in achieving widespread adoption to help prevent or delay CKD and related sequelae (e.g., end-stage renal disease) among people with diabetes, significantly improving patient outcomes and quality of life.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAUPRC\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003earea under the precision-recall curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAUROC\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003earea under the receiver-operating characteristic curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eBMI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ebody mass index\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003econfidence interval\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCKD\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003echronic kidney disease\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCPCSSN\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCanadian Primary Care Sentinel Surveillance Network\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eEMR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eelectronic medical record\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cem\u003eEthics approval and consent to participate\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eOur study was approved by the University of Calgary Conjoint Health Research Ethics Board under study ID REB21-1741. All patients provided consent to contribute their records to CPCSSN.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eConsent for publication\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAvailability of data and materials\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe dataset supporting the conclusions of this article is available in the CPCSSN repository upon reasonable request, https://cpcssn.ca/dar/. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eCompeting interests\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eFunding\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThis research partly comprises Jason E. Black\u0026rsquo;s doctoral work, which is supported by the Achievers in Medical Sciences, Alberta Innovates, and Artificial Intelligence for Public Health scholarships.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAuthors\u0026rsquo; contributions\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eJEB and TSW conceptualized and formalized the research and developed the methodology. All authors reviewed and approved the proposed methodology. JEB performed all statistical analyses and drafted the manuscript. All authors (JEB, DJTC, PER, KAM, and TSW) substantively reviewed and edited the manuscript and approved the submitted version.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAcknowledgements\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eGross JL, de Azevedo MJ, Silveiro SP, Canani LH, Caramori ML, Zelmanovitz T (2005) Diabetic Nephropathy: Diagnosis, Prevention, and Treatment. Diabetes Care 28.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBello AK, Ronksley PE, Tangri N, et al (2019) Prevalence and Demographics of CKD in Canadian Primary Care Practices: A Cross-sectional Study. Kidney Int Rep 4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcFarlane P, Cherney D, Gilbert R, Senior P (2018) Diabetes Canada 2018 Clinical Practice Guidelines for the Prevention and Management of Diabetes in Canada: Chronic Kidney Disease in Diabetes. Can J Diabetes\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDrzewoski J, Kasznicki J, Trojanowski Z (2009) The role of \u0026ldquo;metabolic memory\u0026rdquo; in the natural history of diabetes mellitus. Pol Arch Med Wewn 119.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCopur S, Rossing P, Afsar B, Sag AA, Siriopol D, Kuwabara M, Ortiz A, Kanbay M (2021) A primer on metabolic memory: why existing diabesity treatments fail. Clin Kidney J 14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNdjaboue R, Ngueta G, Rochefort-Brihay C, et al (2022) Prediction models of diabetes complications: a scoping review. J Epidemiol Community Health. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/jech-2021-217793\u003c/span\u003e\u003cspan address=\"10.1136/jech-2021-217793\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSlieker RC, van der Heijden AAWA, Siddiqui MK, et al (2021) Performance of prediction models for nephropathy in people with type 2 diabetes: systematic review and external validation study. BMJ 374.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSperrin M, Riley RD, Collins GS, Martin GP (2022) Targeted validation: validating clinical prediction models in their intended population and setting. Diagn Progn Res 6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRajkomar A, Hardt M, Howell MD, Corrado G, Chin MH (2018) Ensuring Fairness in Machine Learning to Advance Health Equity. Ann Intern Med 169.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen IY, Pierson E, Rose S, Joshi S, Ferryman K, Ghassemi M (2021) Ethical Machine Learning in Healthcare. Annu Rev Biomed Data Sci 4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoons KGM, Altman DG, Vergouwe Y, Royston P (2009) Prognosis and prognostic research: Application and impact of prognostic models in clinical practice. BMJ Online 338.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarda N, Yona G, Rothblum GN, Greenland P, Leibowitz M, Balicer R, Bachmat E, Dagan N (2021) Addressing bias in prediction models by improving subpopulation calibration. J Am Med Inform Assoc JAMIA 28.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaries S, Birtwhistle R, Drummond N, Queenan J, Williamson T (2017) Data Resource Profile: National electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Int J Epidemiol 46.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQueenan JA, Williamson T, Khan S, Drummond N, Garies S, Morkem R, Birtwhistle R (2016) Representativeness of patients and providers in the Canadian Primary Care Sentinel Surveillance Network: a cross-sectional study. CMAJ Open 4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNie JX, Wang L, Tracy CS, Moineddin R, Upshur RE (2008) Health care service utilization among the elderly: findings from the Study to Understand the Chronic Condition Experience of the Elderly and the Disabled (SUCCEED project). J Eval Clin Pract 14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMorkem R, Salman A, Herman C, Shah R, Wong S, Barber D (2023) CPCSSN Data Quality: An Opportunity for Enhancing Canadian Primary Care Data.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWilliamson T, Green ME, Birtwhistle R, Khan S, Garies S, Wong ST, Natarajan N, Manca D, Drummond N (2014) Validating the 8 CPCSSN Case Definitions for Chronic Disease Surveillance in a Primary Care Database of Electronic Health Records. Ann Fam Med 12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLethebe BC, Williamson T, Garies S, McBrien K, Leduc C, Butalia S, Soos B, Shaw M, Drummond N (2019) Developing a case definition for type 1 diabetes mellitus in a primary care electronic medical record database: an exploratory study. Can Med Assoc Open Access J 7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoer IH de, Caramori ML, Chan JCN, et al (2020) KDIGO 2020 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease. Kidney Int 98.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCommittee; CDACPGE, Cheng AYY (2013) Canadian Diabetes Association 2013 clinical practice guidelines for the prevention and management of diabetes in Canada. Can J Diabetes 37.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKazancioğlu R (2013) Risk factors for chronic kidney disease: an update. Kidney Int Suppl 3.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThomas RD, Kosowan L, Rabey M, Bell A, Connelly KA, Hawkins NM, Casey CG, Singer AG (2023) Validation of a case definition to identify patients diagnosed with cardiovascular disease in Canadian primary care practices. CJC Open. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.cjco.2023.04.003\u003c/span\u003e\u003cspan address=\"10.1016/j.cjco.2023.04.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFaisal N, Kosowan L, Zafari H, Zulkernine F, Lix L, Mahar A, Singh H, Renner E, Singer A (2023) Development and validation of a case definition to estimate the prevalence and incidence of cirrhosis in pan-Canadian primary care databases. Can Liver J\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRigobon AV, Birtwhistle R, Khan S, Barber D, Biro S, Morkem R, Janssen I, Williamson T (2015) Adult obesity prevalence in primary care users: An exploration using Canadian Primary Care Sentinel Surveillance Network (CPCSSN) data. Can J Public Health Rev Can Sante Publique 106.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSpohn O, Morkem R, Singer AG, Barber D (2024) Prevalence and management of dyslipidemia in primary care practices in Canada. Can Fam Physician 70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePampalon R, Hamel D, Gamache P, Raymond G (2009) A deprivation index for health planning in Canada. Chronic Dis Can 29.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNguyen CD, Carlin JB, Lee KJ (2017) Model checking in multiple imputation: an overview and case study. Emerg Themes Epidemiol 14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eR Core Team (2023) R: A Language and Environment for Statistical Computing.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMartin GP, Jenkins D, Sperrin M (2023) predRupdate: Prediction model validation and updating.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePavlou M, Qu C, Omar RZ, Seaman SR, Steyerberg EW, White IR, Ambler G (2021) Estimation of required sample size for external validation of risk models for binary outcomes. Stat Methods Med Res 30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVergouwe Y, Soedamah-Muthu SS, Zgibor J, et al (2010) Progression to microalbuminuria in type 1 diabetes: development and validation of a prediction rule. Diabetologia 53.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDagliati A, Marini S, Sacchi L, Cogni G, Teliti M, Tibollo V, De Cata P, Chiovato L, Bellazzi R (2018) Machine Learning Methods to Predict Diabetes Complications. J Diabetes Sci Technol 12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAfghahi H, Cederholm J, Eliasson B, Zethelius B, Gudbj\u0026ouml;rnsdottir S, Hadimeri H, Svensson MK (2011) Risk factors for the development of albuminuria and renal impairment in type 2 diabetes\u0026ndash;the Swedish National Diabetes Register (NDR). Nephrol Dial Transplant Off Publ Eur Dial Transpl Assoc - Eur Ren Assoc 26.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNelson RG, Grams ME, Ballew SH, et al (2019) Development of Risk Prediction Equations for Incident Chronic Kidney Disease. JAMA 322.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBasu S, Sussman JB, Berkowitz SA, Hayward RA, Yudkin JS (2017) Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials. Lancet Diabetes Endocrinol 5.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDorajoo SR, Ng JSL, Goh JHF, Lim SC, Yap CW, Chan A, Lee JYC (2017) HbA1c variability in type 2 diabetes is associated with the occurrence of new-onset albuminuria within three years. Diabetes Res Clin Pract 128.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDunkler D, Gao P, Lee SF, et al (2015) Risk Prediction for Early CKD in Type 2 Diabetes. Clin J Am Soc Nephrol CJASN 10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu Y, Shi R, Mo R, Hu F (2020) Nomogram for the prediction of diabetic nephropathy risk among patients with type 2 diabetes mellitus based on a questionnaire and biochemical indicators: a retrospective study. Aging 12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJardine MJ, Hata J, Woodward M, et al (2012) Prediction of kidney-related outcomes in patients with type 2 diabetes. Am J Kidney Dis Off J Natl Kidney Found 60.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLow S, Lim SC, Zhang X, Zhou S, Yeoh LY, Liu YL, Tavintharan S, Sum CF (2017) Development and validation of a predictive model for Chronic Kidney Disease progression in Type 2 Diabetes Mellitus based on a 13-year study in Singapore. Diabetes Res Clin Pract 123.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMiao DD, Pan EC, Zhang Q, Sun ZM, Qin Y, Wu M (2017) Development and Validation of a Model for Predicting Diabetic Nephropathy in Chinese People. Biomed Environ Sci BES 30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRiphagen IJ, Kleefstra N, Drion I, et al (2015) Comparison of Methods for Renal Risk Prediction in Patients with Type 2 Diabetes (ZODIAC-36). PLOS ONE 10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTanaka S, Tanaka S, Iimuro S, et al (2013) Predicting macro- and microvascular complications in type 2 diabetes: the Japan Diabetes Complications Study/the Japanese Elderly Diabetes Intervention Trial risk engine. Diabetes Care 36.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOzenne B, Subtil F, Maucort-Boulch D (2015) The precision\u0026ndash;recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol 68.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOntario Renal Network (2018) KidneyWise Toolkit. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ontariorenalnetwork.ca/en/kidney-care-resources/clinical-tools/primary-care-tools/kidneywise/toolkit\u003c/span\u003e\u003cspan address=\"https://www.ontariorenalnetwork.ca/en/kidney-care-resources/clinical-tools/primary-care-tools/kidneywise/toolkit\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 8 Jan 2024\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrimble KS, Boll P, Grill AK, Molnar A, Nash DM, Garg A, Akbari A, Blake PG, Perkins D (2020) Impact of the KidneyWise toolkit on chronic kidney disease referral practices in Ontario primary care: a prospective evaluation. BMJ Open 10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee TC, Shah NU, Haack A, Baxter SL (2020) Clinical Implementation of Predictive Models Embedded within Electronic Health Record Systems: A Systematic Review. Inform MDPI 7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePatzer RE, McClellan WM (2012) Influence of race, ethnicity and socioeconomic status on kidney disease. Nat Rev Nephrol 8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePolikar R (2012) Ensemble Learning. In: Zhang C, Ma Y (eds) Ensemble Mach. Learn. Methods Appl. Springer US, Boston, MA, pp 1\u0026ndash;34\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu X, Madden LV, Edwards S, Xu X (2015) Combining Models is More Likely to Give Better Predictions than Single Models. Httpdxdoiorg101094PHYTO-11-14-0315-R 105.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"diagnostic-and-prognostic-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"dapr","sideBox":"Learn more about [Diagnostic and Prognostic Research](https://diagnprognres.biomedcentral.com/)","snPcode":"41512","submissionUrl":"https://submission.springernature.com/new-submission/41512/3","title":"Diagnostic and Prognostic Research","twitterHandle":"@MedicalEvidence","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"clinical prediction models, external validation, chronic kidney disease, diabetes, primary care, CPCSSN","lastPublishedDoi":"10.21203/rs.3.rs-5937923/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5937923/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eSeveral clinical prediction models that predict the risk of chronic kidney disease (CKD) in people with diabetes have been developed; however, these models lack external validation demonstrating accurate predictions in Canadian primary care. We externally validated existing clinical prediction models for CKD in Canadian primary care data, overall and across subgroups defined by sex/gender, age, comorbidities, and neighbourhood-level deprivation.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe conducted a retrospective cohort study using data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN) electronic medical record database (2014\u0026ndash;2019). We identified models that use demographic, health behaviour, clinical and diabetes-related characteristics to predict incident CKD based on two recent systematic reviews and included models with sufficient predictors in CPCSSN (\u0026le;1 unavailable) and eGFR-based CKD definitions. We included adult patients (18+) with diabetes without an existing diagnosis of CKD. We identified incident cases of CKD within 5 years based on \u0026ge;2 laboratory values corresponding to eGFR\u0026thinsp;\u0026lt;\u0026thinsp;60 mL/min/1.73 m\u003csup\u003e2\u003c/sup\u003e separated by \u0026ge;90 days and \u0026le;1 year. For each model, we estimated the discrimination, precision, recall, and calibration within CPCSSN.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eAmong 37,604 patients with diabetes, 14.6% met diagnostic criteria for CKD within 5 years. Overall performance of the 13 included CKD prediction models in CPCCSN was mixed: three models displayed moderate to strong discrimination (areas under the receiver-operating characteristic curves [AUROCs]\u0026thinsp;\u0026gt;\u0026thinsp;0.70), whereas other AUROCs were as low as 0.508. After model updating, calibrations were heterogeneous with most models displaying some miscalibration. Some subgroups displayed considerable differences in performance: discriminative performance (AUROC) declined with increasing age and number of comorbidities, whereas the precision and recall improved with increasing age and number of comorbidities. We observed no difference in performance according to sex/gender or deprivation quintile.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eThree models displayed moderate to strong performance predicting CKD among CPCSSN patients. Next, these models should be evaluated for their impact on practitioner and patient outcomes when implemented in clinical practice. If successful, these models hold promise in achieving widespread adoption to help identify those at highest risk of CKD and guide therapies that may prevent or delay CKD and related sequelae (e.g., end-stage renal disease) among people with diabetes.\u003c/p\u003e","manuscriptTitle":"Performance of clinical prediction models for chronic kidney disease among people with diabetes: External validation using the Canadian Primary Care Sentinel Surveillance Network (CPCSSN)","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-06 08:40:43","doi":"10.21203/rs.3.rs-5937923/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-09T11:38:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-09T11:30:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"288437388892042926270786913726750361325","date":"2025-07-03T08:25:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-20T19:51:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"10003778297945253669172036885053898433","date":"2025-05-12T13:56:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-09T09:15:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-04T09:40:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-04T09:37:47+00:00","index":"","fulltext":""},{"type":"submitted","content":"Diagnostic and Prognostic Research","date":"2025-01-31T17:00:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"diagnostic-and-prognostic-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"dapr","sideBox":"Learn more about [Diagnostic and Prognostic Research](https://diagnprognres.biomedcentral.com/)","snPcode":"41512","submissionUrl":"https://submission.springernature.com/new-submission/41512/3","title":"Diagnostic and Prognostic Research","twitterHandle":"@MedicalEvidence","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"289a6afe-a67b-4f3c-8d9b-7f8c0d3b0136","owner":[],"postedDate":"February 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-17T15:58:56+00:00","versionOfRecord":{"articleIdentity":"rs-5937923","link":"https://doi.org/10.1186/s41512-025-00208-5","journal":{"identity":"diagnostic-and-prognostic-research","isVorOnly":false,"title":"Diagnostic and Prognostic Research"},"publishedOn":"2025-11-11 15:56:49","publishedOnDateReadable":"November 11th, 2025"},"versionCreatedAt":"2025-02-06 08:40:43","video":"","vorDoi":"10.1186/s41512-025-00208-5","vorDoiUrl":"https://doi.org/10.1186/s41512-025-00208-5","workflowStages":[]},"version":"v1","identity":"rs-5937923","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5937923","identity":"rs-5937923","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}