Frailty is associated with poor outcomes in critical illness. However, it is unclear whether frailty screening on admission to the ICU can be conducted routinely at the population level and whether ...it has prognostic importance.
Can population-scale frailty screening with the Clinical Frailty Scale (CFS) be implemented for critically ill adults in Australia and New Zealand (ANZ) and can it identify patients at risk of negative outcomes?
We conducted a binational prospective cohort study of critically ill adult patients admitted between July 1, 2018, and June 30, 2020, in 175 ICUs in ANZ. We classified frailty with the CFS on admission to the ICU. The primary outcome was in-hospital mortality; secondary outcomes were length of stay (LOS), discharge destination, complications (delirium, pressure injury), and duration of survival.
We included 234,568 critically ill patients; 45,245 (19%) were diagnosed as living with frailty before ICU admission. Patients with vs without frailty had higher in-hospital mortality (16% vs 5%; P < .001), delirium (10% vs 4%; P < .001), longer LOS in the ICU and hospital, and increased new chronic care discharge (3% vs 1%; P < .001), with worse outcomes associated with increasing CFS category. Of patients with very severe frailty (CFS score, 8), 39% died in hospital vs 2% of very fit patients (CFS score, 1; multivariate categorical CFS score, 8 reference, 1; OR, 7.83 95% CI, 6.39–9.59; P < .001). After adjustment for illness severity, frailty remained highly significantly predictive of mortality, including among patients younger than 50 years, with improvement in the area under the receiver operating characteristic curve of the Acute Physiology and Chronic Health Evaluation III-j score to 0.882 (95% CI, 0.879–0.885) from 0.868 (95% CI, 0.866–0.871) with the addition of frailty (P < .001).
Large-scale population screening for frailty degree in critical illness was possible and prognostically important, with greater frailty (especially CFS score of ≥ 6) associated with worse outcomes, including among younger patients.
Display omitted
Finding representative samples is important for predicting cancer risk. In particular, it is crucial to identify each representative sample as responsible for the prediction performance. In this ...article, we present a general framework for finding representative samples by explicitly estimating their inherit contribution levels (or scores). By leveraging explainable models as our score functions such as Shapley value, LIME and influence function, our framework can quantitatively identify the representative level of each sample in cancer risk prediction. Furthermore, a score ensembler is introduced to integrate these scores obtained from various score functions with an additional vector of weight variables optimized by the Fast Iterative Shrinkage-Thresholding Algorithm. Empirical evaluations on four cancer risk datasets with different challenges by using five classifiers suggest that our approach significantly outperforms the state-of-the-art methods.
•A general score-based framework is presented to explicitly perform representative sampling tasks.•The framework ensembles score functions to assess representative levels for each sample.•Advanced explainable models are leveraged to find representative samples.•Performances can be improved by weight optimization using FISTA Algorithm on cancer risk prediction.•Our approach outperforms the state-of-the-arts on four cancer risk datasets with different challenges.
Puberty is a time of intense reorganization of brain structure and a high-risk period for the onset of mental health problems, with variations in pubertal timing and tempo intensifying this risk. We ...conducted two systematic reviews of papers published up to 1st February 2024 focusing on (1) the role of brain structure in the relationship between puberty and mental health, and (2) precision psychiatry research evaluating the utility of puberty in making individualized predictions of mental health in young people. The first review provides inconsistent evidence on whether and how pubertal and psychopathological processes could interact in relation to brain development. While most studies found an association between early puberty and mental health difficulties in adolescents, evidence on whether brain structure mediates this relationship is mixed. The pituitary gland was found to be associated with mental health status during this time, possibly through its central role in regulating puberty and its function in the hypothalamic- pituitary-gonadal (HPG) and hypothalamic-pituitary-adrenal (HPA) axes. In the second review, the design of studies that have explored puberty in predictive models did not allow for a quantification of its predictive power. However, when puberty was evaluated through physically observable characteristics rather than hormonal measures, it was more commonly identified as a predictor of depression, anxiety, and suicidality in adolescence. Social processes might be more relevant than biological ones in the link between puberty and mental health problems, and represent an important target for educational strategies.
Predicting temporal changes in PAH concentrations in urban soils and their corresponding health risk is essential for developing appropriate management measures to prevent those risks. Concentrations ...of PAHs in soils of residential areas with different building ages in three metropolitan cities were determined to estimate the accumulation rates of PAHs in soil. The mean concentrations of total PAHs (∑PAHs) were 1297 ng/g in Shanghai, 865 ng/g in Beijing, and 228 ng/g in Shenzhen. The primary sources of the PAHs were traffic and coal combustion for industrial activity and space heating. The high PAH concentrations in Shanghai were attributed to the relatively high average building age of the sampled residential areas and the low annual temperature in the city. The overall annual accumulation rates of PAHs in the soils were estimated from linear regressions between the PAH concentrations and building age of the residential areas. The annual accumulation rate of PAHs in the soils was 64.7 ng/g in Beijing, 24.2 ng/g in Shanghai, and 3.3 ng/g in Shenzhen. The higher rate in Beijing was due to the higher intensity of PAH emissions and the lower temperature. The regression estimations suggest that health risks posed by PAHs in residential soils of the metropolitan cities increase considerably with time.
Display omitted
•The mean concentrations of soil PAHs in descending order: Shanghai, Beijing, Shenzhen.•Urban industry, annual temperature, and building age affected soil PAH concentrations.•The accumulation rate of PAHs was estimated by regressing concentration on building age.•The annual accumulation rates of PAHs in the soils ranged between 3.3 and 64.7 ng g−1.•The health risks to children from accumulated PAHs will be greater in future.
The life expectancy of patients treated with maintenance hemodialysis (MHD) is heterogeneous. Knowledge of life-expectancy may focus care decisions on near-term versus long-term goals. The current ...tools are limited and focus on near-term mortality. Here, we develop and assess potential utility for predicting near-term mortality and long-term survival on MHD.
Predictive modeling study.
42,351 patients contributing 997,381 patient months over 11 years, abstracted from the electronic health record (EHR) system of midsize, nonprofit dialysis providers.
Demographics, laboratory results, vital signs, and service utilization data available within dialysis EHR.
For each patient month, we ascertained death within the next 6 months (ie, near-term mortality) and survival over more than 5 years during receipt of MHD or after kidney transplantation (ie, long-term survival).
We used least absolute shrinkage and selection operator logistic regression and gradient-boosting machines to predict each outcome. We compared these to time-to-event models spanning both time horizons. We explored the performance of decision rules at different cut points.
All models achieved an area under the receiver operator characteristic curve of≥0.80 and optimal calibration metrics in the test set. The long-term survival models had significantly better performance than the near-term mortality models. The time-to-event models performed similarly to binary models. Applying different cut points spanning from the 1st to 90th percentile of the predictions, a positive predictive value (PPV) of 54% could be achieved for near-term mortality, but with poor sensitivity of 6%. A PPV of 71% could be achieved for long-term survival with a sensitivity of 67%.
The retrospective models would need to be prospectively validated before they could be appropriately used as clinical decision aids.
A model built with readily available clinical variables to support easy implementation can predict clinically important life expectancy thresholds and shows promise as a clinical decision support tool for patients on MHD. Predicting long-term survival has better decision rule performance than predicting near-term mortality.
Clinical prediction models (CPMs) are not widely used for patients undergoing maintenance hemodialysis (MHD). Although a variety of CPMs have been reported in the literature, many of these were not well-designed to be easily implementable. We consider the performance of an implementable CPM for both near-term mortality and long-term survival for patients undergoing MHD. Both near-term and long-term models have similar predictive performance, but the long-term models have greater clinical utility. We further consider how the differential performance of predicting over different time horizons may be used to impact clinical decision making. Although predictive modeling is not regularly used for MHD patients, such tools may help promote individualized care planning and foster shared decision making.
Purpose
Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis ...(TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning.
Methods
Fifty-two patients who underwent multi-parametric dual-tracer
18
FFMC and
68
GaGa-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the
68
GaGa-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (M
LH
). Furthermore, M
BCR
and M
OPR
predictive model schemes were built by combining M
LH
, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional
68
GaGa-PSMA-11 standardized uptake value (SUV) analyses.
Results
The area under the receiver operator characteristic curve (AUC) of the M
LH
model (0.86) was higher than the AUC of the
68
GaGa-PSMA-11 SUV
max
analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the M
BCR
and M
OPR
models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively.
Conclusion
Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.
Patients who develop chronic fibrotic liver disease, caused by viral or metabolic aetiologies, are at a high risk of developing hepatocellular carcinoma (HCC). Even after complete HCC tumour ...resection or ablation, the carcinogenic tissue microenvironment in the remnant liver can give rise to recurrent de novo HCC tumours, which progress into incurable, advanced-stage disease in most patients. Thus, early detection and prevention of HCC development is, in principle, the most impactful strategy to improve patient prognosis. However, a “one-size-fits-all” approach to HCC screening for early tumour detection, as recommended by clinical practice guidelines, is utilised in less than 20% of the target population, and the performance of screening modalities, including ultrasound and alpha-fetoprotein, is suboptimal. Furthermore, optimal screening strategies for emerging at-risk patient populations, such as those with chronic hepatitis C after viral cure, or those with non-cirrhotic, non-alcoholic fatty liver disease remain controversial. New HCC biomarkers and imaging modalities may improve the sensitivity and specificity of HCC detection. Clinical and molecular HCC risk scores will enable precise HCC risk prediction followed by tailoured HCC screening of individual patients, maximising cost-effectiveness and optimising allocation of limited medical resources. Several aetiology-specific and generic HCC chemoprevention strategies are evolving. Epidemiological and experimental studies have identified candidate chemoprevention targets and therapies, including statins, anti-diabetic drugs, and selective molecular targeted agents, although their clinical testing has been limited by the lengthy process of cancer development that requires long-term, costly studies. Individual HCC risk prediction is expected to overcome the challenge by enabling personalised chemoprevention, targeting high-risk patients for precision HCC prevention and substantially improving the dismal prognosis of HCC.