Diagnostic and prognostic research最新文献

Background: Recent advances in machine learning combined with the growing availability of digitized health records offer new opportunities for improving early diagnosis of depression. An emerging body of research shows that Electronic Health Records can be used to accurately predict cases of depression on the basis of individual's primary care records. The successes of these studies are undeniable, but there is a growing concern that their results may not be replicable, which could cast doubt on their clinical usefulness.

Methods: To address this issue in the present paper, we set out to reproduce and replicate the work by Nichols et al. (2018), who trained predictive models of depression among young adults using Electronic Healthcare Records. Our contribution consists of three parts. First, we attempt to replicate the methodology used by the original authors, acquiring a more up-to-date set of primary health care records to the same specification and reproducing their data processing and analysis. Second, we test models presented in the original paper on our own data, thus providing out-of-sample prediction of the predictive models. Third, we extend past work by considering several novel machine-learning approaches in an attempt to improve the predictive accuracy achieved in the original work.

Results: In summary, our results demonstrate that the work of Nichols et al. is largely reproducible and replicable. This was the case both for the replication of the original model and the out-of-sample replication applying NRCBM coefficients to our new EHRs data. Although alternative predictive models did not improve model performance over standard logistic regression, our results indicate that stepwise variable selection is not stable even in the case of large data sets.

Conclusion: We discuss the challenges associated with the research on mental health and Electronic Health Records, including the need to produce interpretable and robust models. We demonstrated some potential issues associated with the reliance on EHRs, including changes in the regulations and guidelines (such as the QOF guidelines in the UK) and reliance on visits to GP as a predictor of specific disorders.

Background: Transplantation represents the optimal treatment for many patients with end-stage kidney disease. When a donor kidney is available to a waitlisted patient, clinicians responsible for the care of the potential recipient must make the decision to accept or decline the offer based upon complex and variable information about the donor, the recipient and the transplant process. A clinical prediction model may be able to support clinicians in their decision-making. The Kidney Donor Risk Index (KDRI) was developed in the United States to predict graft failure following kidney transplantation. The survival process following transplantation consists of semi-competing events where death precludes graft failure, but not vice-versa.

Methods: We externally validated the KDRI in the UK kidney transplant population and assessed whether validation under a semi-competing risks framework impacted predictive performance. Additionally, we explored whether the KDRI requires updating. We included 20,035 adult recipients of first, deceased donor, single, kidney-only transplants between January 1, 2004, and December 31, 2018, collected by the UK Transplant Registry and held by NHS Blood and Transplant. The outcomes of interest were 1- and 5-year graft failure following transplantation. In light of the semi-competing events, recipient death was handled in two ways: censoring patients at the time of death and modelling death as a competing event. Cox proportional hazard models were used to validate the KDRI when censoring graft failure by death, and cause-specific Cox models were used to account for death as a competing event.

Results: The KDRI underestimated event probabilities for those at higher risk of graft failure. For 5-year graft failure, discrimination was poorer in the semi-competing risks model (0.625, 95% CI 0.611 to 0.640;0.611, 95% CI 0.597 to 0.625), but predictions were more accurate (Brier score 0.117, 95% CI 0.112 to 0.121; 0.114, 95% CI 0.109 to 0.118). Calibration plots were similar regardless of whether the death was modelled as a competing event or not. Updating the KDRI worsened calibration, but marginally improved discrimination.

Conclusions: Predictive performance for 1-year graft failure was similar between death-censored and competing event graft failure, but differences appeared when predicting 5-year graft failure. The updated index did not have superior performance and we conclude that updating the KDRI in the present form is not required.

Background: Prediction models for outcomes after orthopedic surgery provide patients with evidence-based postoperative outcome expectations. Our objectives were (1) to identify prognostic factors associated with the postoperative shoulder function outcome (the Oxford Shoulder Score (OSS)) and (2) to develop and validate a prediction model for postoperative OSS.

Methods: Patients undergoing arthroscopic rotator cuff repair (ARCR) were prospectively documented at a Swiss orthopedic tertiary care center. The first primary ARCR in adult patients with a partial or complete rotator cuff tear were included between October 2013 and June 2021. Thirty-two potential prognostic factors were used for prediction model development. Two sets of factors identified using the knowledge from three experienced surgeons (Set 1) and Bayesian projection predictive variable selection (Set 2) were compared in terms of model performance using R squared and root-mean-squared error (RMSE) across 45 multiple imputed data sets using chained equations and complete case data.

Results: Multiple imputation using data from 1510 patients was performed. Set 2 retained the following factors: American Society of Anesthesiologists (ASA) classification, baseline level of depression and anxiety, baseline OSS, operation duration, tear severity, and biceps status and treatment. Apparent model performance was R-squared = 0.174 and RMSE = 7.514, dropping to R-squared = 0.156, and RMSE = 7.603 after correction for optimism.

Conclusion: A prediction model for patients undergoing ARCR was developed using solely baseline and operative data in order to provide patients and surgeons with individualized expectations for postoperative shoulder function outcomes. Yet, model performance should be improved before being used in clinical routine.

Background: The kidney failure risk equation (KFRE) predicts the 2- and 5-year risk of needing kidney replacement therapy (KRT) using four risk factors - age, sex, urine albumin-to-creatinine ratio (ACR) and creatinine-based estimated glomerular filtration rate (eGFR). Although the KFRE has been recalibrated in a UK cohort, this did not consider minority ethnic groups. Further validation of the KFRE in different ethnicities is a research priority. The KFRE also does not consider the competing risk of death, which may lead to overestimation of KRT risk. This study externally validates the KFRE for patients of South Asian ethnicity and compares methods for accounting for ethnicity and the competing event of death.

Methods: Data were gathered from an established UK cohort containing 35,539 individuals diagnosed with chronic kidney disease. The KFRE was externally validated and updated in several ways taking into account ethnicity, using recognised methods for time-to-event data, including the competing risk of death. A clinical impact assessment compared the updated models through consideration of referrals made to secondary care.

Results: The external validation showed the risk of KRT differed by ethnicity. Model validation performance improved when incorporating ethnicity and its interactions with ACR and eGFR as additional risk factors. Furthermore, accounting for the competing risk of death improved prediction. Using criteria of 5 years ≥ 5% predicted KRT risk, the competing risks model resulted in an extra 3 unnecessary referrals (0.59% increase) but identified an extra 1 KRT case (1.92% decrease) compared to the previous best model. Hybrid criteria of predicted risk using the competing risks model and ACR ≥ 70 mg/mmol should be used in referrals to secondary care.

Conclusions: The accuracy of KFRE prediction improves when updated to consider South Asian ethnicity and to account for the competing risk of death. This may reduce unnecessary referrals whilst identifying risks of KRT and could further individualise the KFRE and improve its clinical utility. Further research should consider other ethnicities.

Background: Osteoporosis poses a growing healthcare challenge owing to its rising prevalence and a significant treatment gap, as patients are widely underdiagnosed and consequently undertreated, leaving them at high risk of osteoporotic fracture. Several tools aim to improve case-finding in osteoporosis. One such tool is the Fracture Risk Evaluation Model (FREM), which in contrast to other tools focuses on imminent fracture risk and holds potential for automation as it relies solely on data that is routinely collected via the Danish healthcare registers. The present article is an analysis protocol for a prediction model that is to be used as a modified version of FREM, with the intention of improving the identification of subjects at high imminent risk of fracture by including pharmacological exposures and using more advanced statistical methods compared to the original FREM. Its main purposes are to document and motivate various aspects and choices of data management and statistical analyses.

Methods: The model will be developed by employing logistic regression with grouped LASSO regularization as the primary statistical approach and gradient-boosted classification trees as a secondary statistical modality. Hyperparameter choices as well as computational considerations on these two approaches are investigated by an unsupervised data review (i.e., blinded to the outcome), which also investigates and handles multicollinarity among the included exposures. Further, we present an unsupervised review of the data and testing of analysis code with respect to speed and robustness on a remote analysis environment. The data review and code tests are used to adjust the analysis plans in a blinded manner, so as not to increase the risk of overfitting in the proposed methods.

Discussion: This protocol specifies the planned tool development to ensure transparency in the modeling approach, hence improving the validity of the enhanced tool to be developed. Through an unsupervised data review, it is further documented that the planned statistical approaches are feasible and compatible with the data employed.

A lack of biomarkers that detect drug-induced liver injury (DILI) accurately continues to hinder early- and late-stage drug development and remains a challenge in clinical practice. The Innovative Medicines Initiative's TransBioLine consortium comprising academic and industry partners is developing a prospective repository of deeply phenotyped cases and controls with biological samples during liver injury progression to facilitate biomarker discovery, evaluation, validation and qualification.In a nested case-control design, patients who meet one of these criteria, alanine transaminase (ALT) ≥ 5 × the upper limit of normal (ULN), alkaline phosphatase ≥ 2 × ULN or ALT ≥ 3 ULN with total bilirubin > 2 × ULN, are enrolled. After completed clinical investigations, Roussel Uclaf Causality Assessment and expert panel review are used to adjudicate episodes as DILI or alternative liver diseases (acute non-DILI controls). Two blood samples are taken: at recruitment and follow-up. Sample size is as follows: 300 cases of DILI and 130 acute non-DILI controls. Additional cross-sectional cohorts (1 visit) are as follows: Healthy volunteers (n = 120), controls with chronic alcohol-related or non-alcoholic fatty liver disease (n = 100 each) and patients with psoriasis or rheumatoid arthritis (n = 100, 50 treated with methotrexate) are enrolled. Candidate biomarkers prioritised for evaluation include osteopontin, glutamate dehydrogenase, cytokeratin-18 (full length and caspase cleaved), macrophage-colony-stimulating factor 1 receptor and high mobility group protein B1 as well as bile acids, sphingolipids and microRNAs. The TransBioLine project is enabling biomarker discovery and validation that could improve detection, diagnostic accuracy and prognostication of DILI in premarketing clinical trials and for clinical healthcare application.

Background: A previous individual participant data meta-analysis (IPD-MA) of antibiotics for adults with clinically diagnosed acute rhinosinusitis (ARS) showed a marginal overall effect of antibiotics, but was unable to identify patients that are most likely to benefit from antibiotics when applying conventional (i.e. univariable or one-variable-at-a-time) subgroup analysis. We updated the systematic review and investigated whether multivariable prediction of patient-level prognosis and antibiotic treatment effect may lead to more tailored treatment assignment in adults presenting to primary care with ARS.

Methods: An IPD-MA of nine double-blind placebo-controlled trials of antibiotic treatment (n=2539) was conducted, with the probability of being cured at 8-15 days as the primary outcome. A logistic mixed effects model was developed to predict the probability of being cured based on demographic characteristics, signs and symptoms, and antibiotic treatment assignment. Predictive performance was quantified based on internal-external cross-validation in terms of calibration and discrimination performance, overall model fit, and the accuracy of individual predictions.

Results: Results indicate that the prognosis with respect to risk of cure could not be reliably predicted (c-statistic 0.58 and Brier score 0.24). Similarly, patient-level treatment effect predictions did not reliably distinguish between those that did and did not benefit from antibiotics (c-for-benefit 0.50).

Conclusions: In conclusion, multivariable prediction based on patient demographics and common signs and symptoms did not reliably predict the patient-level probability of cure and antibiotic effect in this IPD-MA. Therefore, these characteristics cannot be expected to reliably distinguish those that do and do not benefit from antibiotics in adults presenting to primary care with ARS.

Background: In a pandemic setting, it is critical to evaluate and deploy accurate diagnostic tests rapidly. This relies heavily on the sample size chosen to assess the test accuracy (e.g. sensitivity and specificity) during the diagnostic accuracy study. Too small a sample size will lead to imprecise estimates of the accuracy measures, whereas too large a sample size may delay the development process unnecessarily. This study considers use of a Bayesian method to guide sample size determination for diagnostic accuracy studies, with application to COVID-19 rapid viral detection tests. Specifically, we investigate whether utilising existing information (e.g. from preceding laboratory studies) within a Bayesian framework can reduce the required sample size, whilst maintaining test accuracy to the desired precision.

Methods: The method presented is based on the Bayesian concept of assurance which, in this context, represents the unconditional probability that a diagnostic accuracy study yields sensitivity and/or specificity intervals with the desired precision. We conduct a simulation study to evaluate the performance of this approach in a variety of COVID-19 settings, and compare it to commonly used power-based methods. An accompanying interactive web application is available, which can be used by researchers to perform the sample size calculations.

Results: Results show that the Bayesian assurance method can reduce the required sample size for COVID-19 diagnostic accuracy studies, compared to standard methods, by making better use of laboratory data, without loss of performance. Increasing the size of the laboratory study can further reduce the required sample size in the diagnostic accuracy study.

Conclusions: The method considered in this paper is an important advancement for increasing the efficiency of the evidence development pathway. It has highlighted that the trade-off between lab study sample size and diagnostic accuracy study sample size should be carefully considered, since establishing an adequate lab sample size can bring longer-term gains. Although emphasis is on its use in the COVID-19 pandemic setting, where we envisage it will have the most impact, it can be usefully applied in other clinical areas.