Aging is a multifaceted and intricate physiological process characterized by a gradual decline in functional capacity, leading to increased susceptibility to diseases and mortality. While chronological age serves as a strong risk factor for age-related health conditions, considerable heterogeneity exists in the aging trajectories of individuals, suggesting that biological age may provide a more nuanced understanding of the aging process. However, the concept of biological age lacks a clear operationalization, leading to the development of various biological age predictors without a solid statistical foundation. This paper addresses these limitations by proposing a comprehensive operationalization of biological age, introducing the “AccelerAge” framework for predicting biological age, and introducing previously underutilized evaluation measures for assessing the performance of biological age predictors. The AccelerAge framework, based on Accelerated Failure Time (AFT) models, directly models the effect of candidate predictors of aging on an individual’s survival time, aligning with the prevalent metaphor of aging as a clock. We compare predictors based on the AccelerAge framework to a predictor based on the GrimAge predictor, which is considered one of the best-performing biological age predictors, using simulated data as well as data from the UK Biobank and the Leiden Longevity Study. Our approach seeks to establish a robust statistical foundation for biological age clocks, enabling a more accurate and interpretable assessment of an individual’s aging status.

@en

Background
Estimating the risk of revision after arthroplasty could inform patient and surgeon decision-making. However, there is a lack of well-performing prediction models assisting in this task, which may be due to current conventional modeling approaches such as traditional survivorship estimators (such as Kaplan-Meier) or competing risk estimators. Recent advances in machine learning survival analysis might improve decision support tools in this setting. Therefore, this study aimed to assess the performance of machine learning compared with that of conventional modeling to predict revision after arthroplasty.

Question/purpose
Does machine learning perform better than traditional regression models for estimating the risk of revision for patients undergoing hip or knee arthroplasty?

Methods
Eleven datasets from published studies from the Dutch Arthroplasty Register reporting on factors associated with revision or survival after partial or total knee and hip arthroplasty between 2018 and 2022 were included in our study. The 11 datasets were observational registry studies, with a sample size ranging from 3038 to 218,214 procedures. We developed a set of time-to-event models for each dataset, leading to 11 comparisons. A set of predictors (factors associated with revision surgery) was identified based on the variables that were selected in the included studies. We assessed the predictive performance of two state-of-the-art statistical time-to-event models for 1-, 2-, and 3-year follow-up: a Fine and Gray model (which models the cumulative incidence of revision) and a cause-specific Cox model (which models the hazard of revision). These were compared with a machine-learning approach (a random survival forest model, which is a decision tree–based machine-learning algorithm for time-to-event analysis). Performance was assessed according to discriminative ability (time-dependent area under the receiver operating curve), calibration (slope and intercept), and overall prediction error (scaled Brier score). Discrimination, known as the area under the receiver operating characteristic curve, measures the model’s ability to distinguish patients who achieved the outcomes from those who did not and ranges from 0.5 to 1.0, with 1.0 indicating the highest discrimination score and 0.50 the lowest. Calibration plots the predicted versus the observed probabilities; a perfect plot has an intercept of 0 and a slope of 1. The Brier score calculates a composite of discrimination and calibration, with 0 indicating perfect prediction and 1 the poorest. A scaled version of the Brier score, 1 – (model Brier score/null model Brier score), can be interpreted as the amount of overall prediction error.

Results
Using machine learning survivorship analysis, we found no differences between the competing risks estimator and traditional regression models for patients undergoing arthroplasty in terms of discriminative ability (patients who received a revision compared with those who did not). We found no consistent differences between the validated performance (time-dependent area under the receiver operating characteristic curve) of different modeling approaches because these values ranged between -0.04 and 0.03 across the 11 datasets (the time-dependent area under the receiver operating characteristic curve of the models across 11 datasets ranged between 0.52 to 0.68). In addition, the calibration metrics and scaled Brier scores produced comparable estimates, showing no advantage of machine learning over traditional regression models.

Conclusion
Machine learning did not outperform traditional regression models.

Clinical Relevance
Neither machine learning modeling nor traditional regression methods were sufficiently accurate in order to offer prognostic information when predicting revision arthroplasty. The benefit of these modeling approaches may be limited in this context.

@en

OBJECTIVE: In this pilot study, we investigated the feasibility of response prediction using digital [ 18 F]FDG PET/computed tomography (CT) and multiparametric MRI before, during, and after neoadjuvant chemoradiation therapy in locally advanced rectal cancer (LARC) patients and aimed to select the most promising imaging modalities and timepoints for further investigation in a larger trial. METHODS: Rectal cancer patients scheduled to undergo neoadjuvant chemoradiation therapy were prospectively included in this trial, and underwent multiparametric MRI and [ 18 F]FDG PET/CT before, 2 weeks into, and 6-8 weeks after chemoradiation therapy. Two groups were created based on pathological tumor regression grade, that is, good responders (TRG1-2) and poor responders (TRG3-5). Using binary logistic regression analysis with a cutoff value of P  ≤ 0.2, promising predictive features for response were selected. RESULTS: Nineteen patients were included. Of these, 5 were good responders, and 14 were poor responders. Patient characteristics of these groups were similar at baseline. Fifty-seven features were extracted, of which 13 were found to be promising predictors of response. Baseline [T2: volume, diffusion-weighted imaging (DWI): apparent diffusion coefficient (ADC) mean, DWI: difference entropy], early response (T2: volume change, DWI: ADC mean change) and end-of-treatment presurgical evaluation MRI (T2: gray level nonuniformity, DWI: inverse difference normalized, DWI: gray level nonuniformity normalized), as well as baseline (metabolic tumor volume, total lesion glycolysis) and early response PET/CT (Δ maximum standardized uptake value, Δ peak standardized uptake value corrected for lean body mass), were promising features. CONCLUSION: Both multiparametric MRI and [ 18 F]FDG PET/CT contain promising imaging features to predict response to neoadjuvant chemoradiotherapy in LARC patients. A future larger trial should investigate baseline, early response, and end-of-treatment presurgical evaluation MRI and baseline and early response PET/CT.

@en

When comparing hospitals on their readmission rates as currently done in the Hospital Readmission and Reduction Program (HRRP) in the USA, should we include the competing risk of mortality after discharge, which precludes the readmission, in the analysis? Not including competing risks in current HRRP metrics was raised recently as a limitation with possible unintended consequences, as financial penalties for higher readmission rates are more severe than for higher mortality rates. Incorrectly including or ignoring competing risks can both induce bias. In this paper, we present a framework to clarify situations when competing risks should be taken into account and when they should not. We argue that the research question and the perspective from which it is asked determine whether the competing risk is also of interest and should be included in the analysis, or if only the event of interest should be considered. This information is often not explicitly reported but is needed to interpret whether the results are valid. Using the examples of readmissions and cancer, we show how different research questions fit different perspectives from which these are asked (patient, system, regulatory/insurance). Slightly changing the research question or perspective may thus change the analysis. Even though some may argue that any introduced bias is likely to be small, in the context of the HRRP, even small changes may mean that a hospital will face (higher) financial penalties. The impact of getting it wrong matters.@en

Background: Individualized treatment in older patients with breast cancer can be improved by including comorbidity and other-cause mortality in prediction tools, as the other-cause mortality risk strongly increases with age. However, no optimal comorbidity score is established for this purpose. Therefore, this study aimed to compare the predictive value of the Charlson comorbidity index for other-cause mortality with the use of a simple comorbidity count and to assess the impact of frequently occurring comorbidities. Methods: Surgically treated patients with stages I-III breast cancer aged ≥70 years diagnosed between 2003 and 2009 were selected from the Netherlands Cancer Registry. Competing risk analysis was performed to associate 5-year other-cause mortality with the Charlson index, comorbidity count, and specific comorbidities. Discrimination and calibration were assessed. Results: Overall, 7511 patients were included. Twenty-nine percent had no comorbidities, and 59% had a Charlson score of 0. After five years, in 1974, patients had died (26%), of which 1450 patients without a distant recurrence (19%). Besides comorbidities included in the Charlson index, the psychiatric disease was strongly associated with other-cause mortality (sHR 2.44 (95%-CI 1.70-3.50)). The c-statistics of the Charlson index and comorbidity count were similar (0.65 (95%-CI 0.64-0.65) and 0.64 (95%-CI 0.64-0.65)). Conclusions: The predictive value of the Charlson index for 5-year other-cause mortality was similar to using comorbidity count. As it is easier to use in clinical practice, our findings indicate that comorbidity count can aid in improving individualizing treatment in older patients with breast cancer. Future studies should elicit whether geriatric parameters could improve prediction.@en

Background and purpose — It is unknown whether different trajectories of pain or function are associated with timing of total hip or knee arthroplasty (THA/TKA) in osteoarthritis (OA) patients. We investigated this association in early symptomatic OA patients. Patients and methods — Data from the prospective Dutch CHECK cohort (patients with early hip/knee OA complaints) covering 9 years of follow-up were used. Pain and function were measured annually using the WOMAC questionnaires. Changes in pain/function over time were estimated using a linear mixed model adjusted for baseline age, sex, BMI, maximal Kellgren and Lawrence score, number of painful joints, and comorbidities. The same covariates were included in a Cox regression model, with time to first arthroplasty as event. Both were combined in a joint model to assess the association between changes in pain/function and time to arthroplasty. Results — Of the 868 eligible patients, 84 received a TKA/THA during follow-up. Patients receiving arthroplasty were somewhat older, had a higher Kellgren and Lawrence score and worse WOMAC scores at baseline. Irrespective of receiving arthroplasty, about two-thirds of the patients showed at least 1 period of deterioration of pain/function (≥ 10 points WOMAC subscale). In approximately two fifths this deterioration was followed by another deterioration in the following year. Worse pain and function levels increased the hazard of receiving THA/TKA (1.08 [95% CI 1.06–1.10] for pain and 1.07 [CI 1.05–1.08] for function). Changes in pain or function over time were not associated with timing of THA/TKA Interpretation — Worse pain and function levels rather than long-term changes are associated with timing of THA/TKA.@en