Clinical Prediction Tool Research Articles

A machine learning approach to predicting 30-day mortality following paediatric cardiac surgery: findings from the Australia New Zealand Congenital Outcomes Registry for Surgery (ANZCORS).

We aim to develop the first risk prediction model for 30-day mortality for the Australian and New Zealand patient populations and examine whether machine learning (ML) algorithms outperform traditional statistical approaches. Data from the Australia New Zealand Congenital Outcomes Registry for Surgery, which contains information on every paediatric cardiac surgical encounter in Australian and New Zealand for patients aged <18 years between January 2013 and December 2021, were analysed (n = 14343). The outcome was mortality within the 30-day period following a surgical encounter, with ∼30% of the observations randomly selected to be used for validation of the final model. Three different ML methods were used, all of which employed five-fold cross-validation to prevent overfitting, with model performance judged primarily by the area under the receiver operating curve (AUC). Among the 14343 30-day periods, there were 188 deaths (1.3%). In the validation data, the gradient-boosted tree obtained the best performance [AUC = 0.87, 95% confidence interval = (0.82, 0.92); calibration = 0.97, 95% confidence interval = (0.72, 1.27)], outperforming penalized logistic regression and artificial neural networks (AUC of 0.82 and 0.81, respectively). The strongest predictors of mortality in the gradient boosting trees were patient weight, STAT score, age and gender. Our risk prediction model outperformed logistic regression and achieved a level of discrimination comparable to the PRAiS2 and Society of Thoracic Surgery Congenital Heart Surgery Database mortality risk models (both which obtained AUC = 0.86). Non-linear ML methods can be used to construct accurate clinical risk prediction tools.

Predicting suicide risk in 137,112 people with severe mental illness in Finland: external validation of the Oxford Mental Illness and Suicide tool (OxMIS)

Oxford Mental Illness and Suicide tool (OxMIS) is a standardised, scalable, and transparent instrument for suicide risk assessment in people with severe mental illness (SMI) based on 17 sociodemographic, criminal history, familial, and clinical risk factors. However, alongside most prediction models in psychiatry, external validations are currently lacking. We utilised a Finnish population sample of all persons diagnosed by mental health services with SMI (schizophrenia-spectrum and bipolar disorders) between 1996 and 2017 (n = 137,112). To evaluate the performance of OxMIS, we initially calculated the predicted 12-month suicide risk for each individual by weighting risk factors by effect sizes reported in the original OxMIS prediction model and converted to a probability. This probability was then used to assess the discrimination and calibration of the OxMIS model in this external sample. Within a year of assessment, 1.1% of people with SMI (n = 1475) had died by suicide. The overall discrimination of the tool was good, with an area under the curve of 0.70 (95% confidence interval: 0.69–0.71). The model initially overestimated suicide risks in those with elevated predicted risks of >5% over 12 months (Harrell’s Emax = 0.114), which applied to 1.3% (n = 1780) of the cohort. However, when we used a 5% maximum predicted suicide risk threshold as is recommended clinically, the calibration was excellent (ICI = 0.002; Emax = 0.005). Validating clinical prediction tools using routinely collected data can address research gaps in prediction psychiatry and is a necessary step to translating such models into clinical practice.

Factors Associated with Recurrence in Chronic Subdural Hematoma following Surgery

Abstract Background Recurrence is a frequent complication after surgery in a chronic subdural hematoma (CSDH). This study aimed to describe the recurrent rate of CSDH after surgery. In addition, a secondary objective aimed to explore factors associated with the recurrence of CSDH after surgery. Methods A total of 141 surgical CSDH patients were analyzed in this retrospective study. The Cox regression method was used to conduct both univariate and multivariate analyses of variables associated with recurrence. As a result, the cumulative incidence of recurrence for each covariate survival curve was built after the final model. Results Twenty-two percent of the patients showed evidence of recurrence. Initially, four variables (Glasgow coma scale score 3–8, clopidogrel, operative time, and amount of irrigated saline) had potential factors in univariate analysis but only clopidogrel and amount of saline irrigation were significantly associated with CSDH recurrence. Conclusion Preoperative clopidogrel and the amount of saline irrigation were found to be associated with the recurrence rate. Factors associated with CSDH recurrence should be developed and validated as the clinical prediction tool for implication in general practice.

Association of clinical prediction scores with hospital mortality in an adult medical and surgical intensive care unit in Kenya.

Mortality prediction among critically ill patients in resource limited settings is difficult. Identifying the best mortality prediction tool is important for counseling patients and families, benchmarking quality improvement efforts, and defining severity of illness for clinical research studies. Compare predictive capacity of the Modified Early Warning Score (MEWS), Universal Vital Assessment (UVA), Tropical Intensive Care Score (TropICS), Rwanda Mortality Probability Model (R-MPM), and quick Sequential Organ Failure Assessment (qSOFA) for hospital mortality among adults admitted to a medical-surgical intensive care unit (ICU) in rural Kenya. We performed a pre-planned subgroup analysis among ICU patients with suspected infection. Prospective single-center cohort study at a tertiary care, academic hospital in Kenya. All adults 18 years and older admitted to the ICU January 2018-June 2019 were included. The primary outcome was association of clinical prediction tool score with hospital mortality, as defined by area under the receiver operating characteristic curve (AUROC). Demographic, physiologic, laboratory, therapeutic, and mortality data were collected. 338 patients were included, none were excluded. Median age was 42 years (IQR 33-62) and 61% (n = 207) were male. Fifty-nine percent (n = 199) required mechanical ventilation and 35% (n = 118) received vasopressors upon ICU admission. Overall hospital mortality was 31% (n = 104). 323 patients had all component variables recorded for R-MPM, 261 for MEWS, and 253 for UVA. The AUROC was highest for MEWS (0.76), followed by R-MPM (0.75), qSOFA (0.70), and UVA (0.69) (p < 0.001). Predictive capacity was similar among patients with suspected infection. All tools had acceptable predictive capacity for hospital mortality, with variable observed availability of the component data. R-MPM and MEWS had high rates of variable availability as well as good AUROC, suggesting these tools may prove useful in low resource ICUs.

Clinical Predictive Tool for Pediatric Cardiac Patients on Extracorporeal Membrane Oxygenation Therapy and Ultrafiltration.

Fluid overload is common among pediatric cardiac patients receiving extracorporeal membrane oxygenation (ECMO) and is often treated with in-line ultrafiltration (UF) or continuous renal replacement therapy (CRRT). We assessed whether CRRT was associated with poor outcomes versus UF alone. Additionally, we identified characteristics associated with progression from UF to CRRT. Retrospective chart review of 131 patients age ≤18 years treated with ECMO at a single quaternary center. Data were collected to compare patient demographics, characteristics, and outcomes. A receiver operator curve (ROC) was used to create a tool predictive of the need for CRRT at the time of UF initiation. Patients who required CRRT had a higher creatinine and blood urea nitrogen at time of UF initiation (p = 0.03 and p < 0.01), longer total ECMO duration (p < 0.01), lower renal recovery incidence (p = 0.02), and higher mortality (p ≤ 0.01). Using ROC analysis, presence of ≤3 of 7 risk variables had a positive predictive value of 87.5% and negative predictive value of 50.0% for use of UF alone (area under the curve 0.801; 95% CI: 0.638-0.965, p = 0.002). Pediatric cardiac patients treated with ECMO and UF who require CRRT demonstrate worse outcomes versus UF alone. A novel clinical tool may assist in stratifying patients at UF initiation.

A novel model for predicting prolonged stay of patients with type-2 diabetes mellitus: a 13-year (2010–2022) multicenter retrospective case–control study

BackgroundLength of stay (LOS) is an important metric for evaluating the management of inpatients. This study aimed to explore the factors impacting the LOS of inpatients with type-2 diabetes mellitus (T2DM) and develop a predictive model for the early identification of inpatients with prolonged LOS.MethodsA 13-year multicenter retrospective study was conducted on 83,776 patients with T2DM to develop and validate a clinical predictive tool for prolonged LOS. Least absolute shrinkage and selection operator regression model and multivariable logistic regression analysis were adopted to build the risk model for prolonged LOS, and a nomogram was taken to visualize the model. Furthermore, receiver operating characteristic curves, calibration curves, and decision curve analysis and clinical impact curves were used to respectively validate the discrimination, calibration, and clinical applicability of the model.ResultsThe result showed that age, cerebral infarction, antihypertensive drug use, antiplatelet and anticoagulant use, past surgical history, past medical history, smoking, drinking, and neutrophil percentage-to-albumin ratio were closely related to the prolonged LOS. Area under the curve values of the nomogram in the training, internal validation, external validation set 1, and external validation set 2 were 0.803 (95% CI [confidence interval] 0.799–0.808), 0.794 (95% CI 0.788–0.800), 0.754 (95% CI 0.739–0.770), and 0.743 (95% CI 0.722–0.763), respectively. The calibration curves indicated that the nomogram had a strong calibration. Besides, decision curve analysis, and clinical impact curves exhibited that the nomogram had favorable clinical practical value. Besides, an online interface (https://cytjt007.shinyapps.io/prolonged_los/) was developed to provide convenient access for users.ConclusionIn sum, the proposed model could predict the possible prolonged LOS of inpatients with T2DM and help the clinicians to improve efficiency in bed management.

Developing a machine learning algorithm to predict probability of retear and functional outcomes in patients undergoing rotator cuff repair surgery: protocol for a retrospective, multicentre study

IntroductionThe effectiveness of rotator cuff tear repair surgery is influenced by multiple patient-related, pathology-centred and technical factors, which is thought to contribute to the reported retear rates between 17% and...

Development of a clinical model to predict vagus nerve stimulation response in pediatric patients with drug-resistant epilepsy.

Epilepsy impacts 470,000 children in the United States. For patients with drug-resistant epilepsy (DRE) and unresectable seizure foci, vagus nerve stimulation (VNS) is a treatment option. Predicting response to VNS has been historically challenging. The objective of this study was to create a clinical VNS prediction tool for use in an outpatient setting. The authors performed an 11-year retrospective cohort analysis with 1-year follow-up. Patients < 21 years of age with DRE who underwent VNS (n = 365) were included. Logistic regressions were performed to assess clinical factors associated with VNS response (≥ 50% seizure frequency reduction after 1 year); 70% and 30% of the sample were used to train and validate the multivariable model, respectively. A prediction score was subsequently developed. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Variables associated with VNS response were < 4-year epilepsy duration before VNS (p = 0.008) and focal motor seizures (p = 0.037). The variables included in the clinical prediction score were epilepsy duration before VNS, age at seizure onset, number of pre-VNS antiseizure medications, if VNS was the patient's first therapeutic epilepsy surgery, and predominant seizure semiology. The final AUCs were 0.7013 for the "fitted" sample and 0.6159 for the "validation" sample. The authors developed a clinical model to predict VNS response in a large sample of pediatric patients treated with VNS. Despite the large sample size, clinical variables alone were not able to accurately predict VNS response. This score may be useful after further validation, although its predictive ability underscores the need for more robust biomarkers to predict treatment response.

Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review.

Malignant brain tumors pose a substantial burden on morbidity and mortality. As clinical data collection improves, along with the capacity to analyze it, novel predictive clinical tools may improve prognosis prediction. Deep learning (DL) holds promise for integrating clinical data of various modalities. A systematic review of the DL-based prognostication of gliomas was performed using the Embase (Elsevier), PubMed MEDLINE (National library of Medicine), and Scopus (Elsevier) databases, in accordance with PRISMA guidelines. All included studies focused on the prognostication of gliomas, and predicted overall survival (13 studies, 81%), overall survival as well as genotype (2 studies, 12.5%), and response to immunotherapy (1 study, 6.2%). Multimodal analyses were varied, with 6 studies (37.5%) combining MRI with clinical data; 6 studies (37.5%) integrating MRI with histologic, clinical, and biomarker data; 3 studies (18.8%) combining MRI with genomic data; and 1 study (6.2%) combining histologic imaging with clinical data. Studies that compared multimodal models to unimodal-only models demonstrated improved predictive performance. The risk of bias was mixed, most commonly due to inconsistent methodological reporting. Overall, the use of multimodal data in DL assessments of gliomas leads to a more accurate overall survival prediction. However, due to data limitations and a lack of transparency in model and code reporting, the full extent of multimodal DL as a resource for brain tumor patients has not yet been realized.

A novel autophagy-related long non-coding RNAs prognostic risk score for clear cell renal cell carcinoma.

As the main histological subtype of renal cell carcinoma, clear cell renal cell carcinoma (ccRCC) places a heavy burden on health worldwide. Autophagy-related long non-coding RNAs (ARlncRs) have shown tremendous potential as prognostic signatures in several studies, but the relationship between them and ccRCC still has to be demonstrated. The RNA-sequencing and clinical characteristics of 483 ccRCC patients were downloaded download from the Cancer Genome Atlas and International Cancer Genome Consortium. ARlncRs were determined by Pearson correlation analysis. Univariate and multivariate Cox regression analyses were applied to establish a risk score model. A nomogram was constructed considering independent prognostic factors. The Harrell concordance index calibration curve and the receiver operating characteristic analysis were utilized to evaluate the nomogram. Furthermore, functional enrichment analysis was used for differentially expressed genes between the two groups of high- and low-risk scores. A total of 9 SARlncRs were established as a risk score model. The Kaplan-Meier survival curve, principal component analysis, and subgroup analysis showed that low overall survival of patients was associated with high-risk scores. Age, M stage, and risk score were identified as independent prognostic factors to establish a nomogram, whose concordance index in the training cohort, internal validation, and external ICGC cohort was 0.793, 0.671, and 0.668 respectively. The area under the curve for 5-year OS prediction in the training cohort, internal validation, and external ICGC cohort was 0.840, 0.706, and 0.708, respectively. GO analysis and KEGG analysis of DEGs demonstrated that immune- and inflammatory-related pathways are likely to be critically involved in the progress of ccRCC. We established and validated a novel ARlncRs prognostic risk model which is valuable as a potential therapeutic target and prognosis indicator for ccRCC. A nomogram including the risk model is a promising clinical tool for outcomes prediction of ccRCC patients and further formulation of individualized strategy.

Prediction of all-cause mortality for chronic kidney disease patients using four models of machine learning.

The prediction tools developed from general population data to predict all-cause mortality are not adapted to chronic kidney disease (CKD) patients, because this population displays a higher mortality risk. This study aimed to create a clinical prediction tool with good predictive performance to predict the 2-year all-cause mortality of stage 4 or stage 5 CKD patients. The performance of four different models (deep learning, random forest, Bayesian network, logistic regression) to create four prediction tools was compared using a 10-fold cross validation. The model that offered the best performance for predicting mortality in the Photo-Graphe 3 cohort was selected and then optimized using synthetic data and a selected number of explanatory variables. The performance of the optimized prediction tool to correctly predict the 2-year mortality of the patients included in the Photo-Graphe 3 database were then assessed. Prediction tools developed using the Bayesian network and logistic regression tended to have the best performances. Although not significantly different from logistic regression, the prediction tool developed using the Bayesian network was chosen because of its advantages and then optimized. The optimized prediction tool that was developed using synthetic data and the seven variables with the best predictive value (age, erythropoietin-stimulating agent, cardiovascular history, smoking status, 25-hydroxy vitamin D, parathyroid hormone and ferritin levels) had satisfactory internal performance. A Bayesian network was used to create a seven-variable prediction tool to predict the 2-year all-cause mortality in patients with stage 4-5 CKD. Prior to external validation, the proposed prediction tool can be used at: https://dev.hed.cc/?a=jpfauvel&n=2022-05%20Modele%20Bayesien%2020000%20Mortalite%207%20variables%20Naif%20Zou%20online(1).neta for research purposes.

An alternative model for assessing mortality risk in Stevens Johnson syndrome/toxic epidermal necrolysis using a random forests classifier: A pilot study.

Mortality risk prediction is an important part of the clinical assessment in the Stevens-Johnson syndrome and toxic epidermal necrolysis (SJS/TEN) patient. The SCORTEN and ABCD-10 scoring systems have been used as predictive clinical tools for assessing this risk. However, some of the metrics required in calculating these scores, such as the total body surface area (TBSA) involvement, are difficult to calculate. In addition, TBSA involvement is calculated in a variety of ways and is observer dependent and subjective. The goal of this study was to develop an alternative method to predict mortality in patients with SJS/TEN. Data was split into training and test datasets and preprocessed. Models were trained using five-fold cross validation. Out of several possible candidates, a random forests model was evaluated as being the most robust in predictive power for this dataset. Upon feature selection, a final random forests model was developed which was used for comparison against SCORTEN. The differences in both accuracy (p = 0.324) and area under the receiver operating characteristic curve (AUROC) (p = 0.318) between the final random forests model and the SCORTEN and ABCD-10 models were not statistically significant. As such, this alternative method performs similarly to SCORTEN while only requiring simple laboratory tests from the day of admission. This new alternative can make the mortality prediction process more efficient, along with providing a seamless implementation of the patient laboratory tests directly into the model from existing electronic health record (EHR) systems. Once the model was developed, a web application was built to deploy the model which integrates with the Epic EHR system on the Fast Healthcare Interoperability Resources (FHIR) Application Programming Interface (API); this only requires the patient medical record number and a date of the lab tests as parameters. This model ultimately allows clinicians to calculate patient mortality risk with only a few clicks. Further studies are needed for validation of this tool.

Machine learning for the prediction of minor amputation in University of Texas grade 3 diabetic foot ulcers.

Minor amputations are performed in a large proportion of patients with diabetic foot ulcers (DFU) and early identification of the outcome of minor amputations facilitates medical decision-making and ultimately reduces major amputations and deaths. However, there are currently no clinical predictive tools for minor amputations in patients with DFU. We aim to establish a predictive model based on machine learning to quickly identify patients requiring minor amputation among newly admitted patients with DFU. Overall, 362 cases with University of Texas grade (UT) 3 DFU were screened from tertiary care hospitals in East China. We utilized the synthetic minority oversampling strategy to compensate for the disparity in the initial dataset. A univariable analysis revealed nine variables to be included in the model: random blood glucose, years with diabetes, cardiovascular diseases, peripheral arterial diseases, DFU history, smoking history, albumin, creatinine, and C-reactive protein. Then, risk prediction models based on five machine learning algorithms: decision tree, random forest, logistic regression, support vector machine, and extreme gradient boosting (XGBoost) were independently developed with these variables. After evaluation, XGBoost earned the highest score (accuracy 0.814, precision 0.846, recall 0.767, F1-score 0.805, and AUC 0.881). For convenience, a web-based calculator based on our data and the XGBoost algorithm was established (https://dfuprediction.azurewebsites.net/). These findings imply that XGBoost can be used to develop a reliable prediction model for minor amputations in patients with UT3 DFU, and that our online calculator will make it easier for clinicians to assess the risk of minor amputations and make proactive decisions.

Endovascular versus neurosurgical aneurysm treatment: study protocol for the development and validation of a clinical prediction tool for individualised decision making

IntroductionTreatment decisions for aneurysmal subarachnoid haemorrhage patients should be supported by individualised predictions of the effects of aneurysm treatment. We present a study protocol and analysis plan for the development...

Biopsychosocial Approach in Identifying Risk Factors of Kinesiophobia in Persons with Subacromial Pain Syndrome and Developing a Clinical Prediction Tool.

Although the negative effects of kinesiophobia on functional status in subacromial pain syndrome (SAPS) patients are clearly demonstrated, no study examines the risk factors of kinesiophobia in individuals with SAPS from a biopsychosocial perspective. The present study aims to determine the risk factors of kinesiophobia in individuals with SAPS using a biopsychosocial approach. This study also aims to explore the compounding effects of multiple associative risk factors by developing a clinical prediction tool to identify SAPS patients at higher risk for kinesiophobia. This cross-sectional study included 549 patients who were diagnosed with SAPS. The Tampa-Scale of Kinesiophobia (TSK) was used to assess kinesiophobia. Visual analog scale (VAS), The Shoulder Pain and Disability Index (SPADI), Disabilities of the Arm, Shoulder, and Hand (DASH) questionnaire, the presence of metabolic syndrome, using any non-steroidal anti-inflammatory drugs, Pain Catastrophizing Scale (PCS), Illness Perception Questionnaire-revised (IPQ-R), Hospital Anxiety and Depression Scale (HADS), behavioral pattern of the patient, sociodemographic characteristics, and treatment expectancy were outcome measures. Thirteen significant risk factors of having kinesiophobia were: VASat rest (≥ 5.2), VASduring activity (≥ 7.1), DASH (≥ 72.1), presence of metabolic syndrome, PCShelplessness (≥ 16.1), IPQ-Rpersonal control (≤ 17.1), IPQ-Rtreatment control (≤ 16.3), HADSdepression (≥ 7.9), avoidance behavior type, being female, educational level (≤ high school), average hours of sleep (≤ 6.8), and treatment expectancy (≤ 6.6). The presence of seven or more risk factors increased the probability of having high level of kinesiophobia from 34.3 to 51%. It seems necessary to address these factors, increase awareness of health practitioners and individuals. Level IV.

Development of a Clinical Risk Score Prediction Tool for 5-, 9-, and 13-Year Risk of Dementia

Although researchers have devoted substantial efforts, money, and time to studying the causes of dementia and the means to prevent it, no effective treatment exists yet. Identifying preclinical risk factors of dementia could help prevent or delay its progression. To develop a point risk score prediction model of dementia. This study used a large UK population-based prospective cohort study conducted between March 13, 2006, and October 1, 2010. Data analysis was performed from June 7 to September 15, 2021. Individual analyses of time end points were concluded at the first dementia diagnosis during the follow-up period. The data were split into training and testing data sets to separately establish and validate a prediction model. Outcomes of interest included 5-, 9-, and 13-year dementia risk. Least absolute shrinkage and selection operator and multivariate Cox proportional hazards regression models were used to identify available and practical dementia predictors. A point risk score model was developed for the individual prediction of 5-, 9-, and 13-year dementia risk. A total of 502 505 participants were selected; the population after exclusions for missing data and dementia diagnosis at baseline was 444 695 (205 187 men; mean [SD] age, 56.74 [8.18] years; 239 508 women; mean [SD] age, 56.20 [8.01] years). Dementia occurrence during the 13 years of follow-up was 0.7% for men and 0.5% for women. The C statistic of the final multivariate Cox proportional hazards regression model was 0.86 for men and 0.85 for women in the training data set, and 0.85 for men and 0.87 for women in the testing data set. Men and women shared some modifiable risk and protective factors, but they also presented independent risk factors that accounted for 31.7% of men developing dementia and 53.35% of women developing dementia according to the weighted population-attributable fraction. The total point score of the risk score model ranged from -18 to 30 in men and -17 to 30 in women. The risk score model yielded nearly 100% prediction accuracy of 13-year dementia risk both in men and women. In this diagnostic study, a practical risk score tool was developed for individual prediction of dementia risk, which may help individuals identify their potential risk profile and provide guidance on precise and timely actions to promote dementia delay or prevention.

Validation of Existing Clinical Prediction Tools for Primary Aldosteronism Subtyping.

The new clinical prediction score (SCORE) has been recently proposed for primary aldosteronism (PA) subtyping prior to adrenal vein sampling (AVS). This study aimed to compare that SCORE with previously published scores and their validation using a cohort of patients at our center who had had positive SIT confirming PA and had been diagnosed with either bilateral PA according to AVS or unilateral PA if biochemically cured after an adrenalectomy. Final diagnoses were used to evaluate the diagnostic performance of the proposed clinical prediction tools. Only Kamemura's model (with a maximum score of 4 points) and Kobayashi's score (with a maximum score of 12 points) reached 100% reliability for prediction of bilateral PA; however, with sensitivity of only 3%. On the other hand, the values of SCORE = 3 (with sensitivity of 48%), the SPACE score ≥18 (with sensitivity of 35%), the Kobayashi's score ≤2 (with sensitivity of 28%), and the Kocjan's score = 3 (with sensitivity of 28%) were able to predict unilateral PA with 100% probability. Furthermore, Umakoshi's and Young's models both reached 100% reliability for a unilateral PA with score = 4 and both predictive factors together respectively; however, the sensitivity was lower compared with previous models; 4% and 14%, respectively. None of the clinical prediction tools applied to our cohort predicted unilateral and bilateral subtypes together with the expected high diagnostic performance, and therefore can only be used for precisely defined cases.

Contemporary Clinical Definitions, Differential Diagnosis, and Novel Predictive Tools for Renal Cell Carcinoma.

Despite significant progress regarding clinical detection/imaging evaluation modalities and genetic/molecular characterization of pathogenesis, advanced renal cell carcinoma (RCC) remains an incurable disease and overall RCC mortality has been steadily rising for decades. Concomitantly, clinical definitions have been greatly nuanced and refined. RCCs are currently viewed as a heterogeneous series of cancers, with the same anatomical origin, but fundamentally different metabolisms and clinical behaviors. Thus, RCC pathological diagnosis/subtyping guidelines have become increasingly intricate and cumbersome, routinely requiring ancillary studies, mainly immunohistochemistry. Meanwhile, RCC-associated-antigen targeted systemic therapy has been greatly diversified and emerging, novel clinical applications for RCC immunotherapy have already reported significant survival benefits, at least in the adjuvant setting. Even so, systemically disseminated RCCs still associate very poor clinical outcomes, with currently available therapeutic modalities only being able to prolong survival. In lack of a definitive cure for advanced RCCs, integration of the amounting scientific knowledge regarding RCC pathogenesis into RCC clinical management has been paramount for improving patient outcomes. The current review aims to offer an integrative perspective regarding contemporary RCC clinical definitions, proper RCC clinical work-up at initial diagnosis (semiology and multimodal imaging), RCC pathological evaluation, differential diagnosis/subtyping protocols, and novel clinical tools for RCC screening, risk stratification and therapeutic response prediction.

A Clinical Tool for Prediction of Bleeding Complications After Percutaneous Renal Biopsy

A Clinical Tool for Prediction of Bleeding Complications After Percutaneous Renal Biopsy

63 Translational Research Capacity in Canadian Pediatric Emergency Departments Participating in the Precision Medicine for Improving the Diagnosis of Pediatric Appendicitis in the Emergency Department (PRIMED) Study

Abstract Background Pediatric clinical and translational research are essential to acquire effective diagnostic and treatment options for children, but they are underfunded and under prioritized in comparison to research focused on treatments for adults. The Precision Medicine for Improving the Diagnosis of Pediatric Appendicitis in the Emergency Department (PRIMED) study aimed to characterize the proteomic and metabolic bio-profiles of children with appendicitis and to investigate these bio-profiles as a clinical prediction tool. Objectives In this current work, we aimed to evaluate translational research capacity at Canadian pediatric Emergency Departments (EDs) and to describe some of the challenges experienced in the implementation of the PRIMED study and various strategies used to improve local research capacity. Design/Methods Participating sites provided basic demographic and administrative data along with laboratory- and human-resource availability during enrolment for the PRIMED study. Data was summarized using descriptive statistics. Eleven pediatric EDs participated in the PRIMED study. Results Six study hospitals (54.5%) used on-site clinical laboratories to process research samples; the remaining hospitals (5/11, 45.5%) required access to research facilities, of which two (18.2%) were off-site. Fewer than two thirds of the study sites (7/11, 63.6%) had any laboratory that would process samples 24 hours per day. Four study sites (36.4%) only enrolled patients during business hours and over half of the sites (6/11, 54.5%) were unable to collect samples for the entire 17:00 to 21:00 peak when the greatest number of pediatric patients present to the ED (Figure 1). There was no nighttime coverage for patient enrollment and sample collection and only three study sites (3/11, 27.3%) had enrollment hours that captured over 75% of the potential study participants. Over half (6/11, 54.5%) of the PRIMED study sites developed novel processes to enable study success, for example creating graduate student on-call schedules and hiring bioscience trained site coordinators to perform sample processing requirements. Conclusion Despite site-specific efforts to overcome resource barriers, the gap in translational research capacity at academic pediatric emergency departments remains a significant concern. University research institutes and pediatric hospitals should invest in infrastructure and human resources to increase after-hours clinical and translational research capacity to optimize child health and wellness outcomes.