UNASSIGNED: Fetal growth restriction is associated with perinatal morbidity and mortality. Early identification of women having at-risk fetuses can reduce perinatal adverse outcomes.
UNASSIGNED: To assess the predictive performance of existing models predicting fetal growth restriction and birthweight, and if needed, to develop and validate new multivariable models using individual participant data.
UNASSIGNED: Individual participant data meta-analyses of cohorts in International Prediction of Pregnancy Complications network, decision curve analysis and health economics analysis.
UNASSIGNED: Pregnant women at booking. External validation of existing models (9 cohorts, 441,415 pregnancies); International Prediction of Pregnancy Complications model development and validation (4 cohorts, 237,228 pregnancies).
UNASSIGNED: Maternal clinical characteristics, biochemical and ultrasound markers.
UNASSIGNED: fetal growth restriction defined as birthweight <10th centile adjusted for gestational age and with stillbirth, neonatal death or delivery before 32 weeks\' gestation birthweight.
UNASSIGNED: First, we externally validated existing models using individual participant data meta-analysis. If needed, we developed and validated new International Prediction of Pregnancy Complications models using random-intercept regression models with backward elimination for variable selection and undertook internal-external cross-validation. We estimated the study-specific performance (c-statistic, calibration slope, calibration-in-the-large) for each model and pooled using random-effects meta-analysis. Heterogeneity was quantified using τ2 and 95% prediction intervals. We assessed the clinical utility of the fetal growth restriction model using decision curve analysis, and health economics analysis based on National Institute for Health and Care Excellence 2008 model.
UNASSIGNED: Of the 119 published models, one birthweight model (Poon) could be validated. None reported fetal growth restriction using our definition. Across all cohorts, the Poon model had good summary calibration slope of 0.93 (95% confidence interval 0.90 to 0.96) with slight overfitting, and underpredicted birthweight by 90.4 g on average (95% confidence interval 37.9 g to 142.9 g). The newly developed International Prediction of Pregnancy Complications-fetal growth restriction model included maternal age, height, parity, smoking status, ethnicity, and any history of hypertension, pre-eclampsia, previous stillbirth or small for gestational age baby and gestational age at delivery. This allowed predictions conditional on a range of assumed gestational ages at delivery. The pooled apparent c-statistic and calibration were 0.96 (95% confidence interval 0.51 to 1.0), and 0.95 (95% confidence interval 0.67 to 1.23), respectively. The model showed positive net benefit for predicted probability thresholds between 1% and 90%. In addition to the predictors in the International Prediction of Pregnancy Complications-fetal growth restriction model, the International Prediction of Pregnancy Complications-birthweight model included maternal weight, history of diabetes and mode of conception. Average calibration slope across cohorts in the internal-external cross-validation was 1.00 (95% confidence interval 0.78 to 1.23) with no evidence of overfitting. Birthweight was underestimated by 9.7 g on average (95% confidence interval -154.3 g to 173.8 g).
UNASSIGNED: We could not externally validate most of the published models due to variations in the definitions of outcomes. Internal-external cross-validation of our International Prediction of Pregnancy Complications-fetal growth restriction model was limited by the paucity of events in the included cohorts. The economic evaluation using the published National Institute for Health and Care Excellence 2008 model may not reflect current practice, and full economic evaluation was not possible due to paucity of data.
UNASSIGNED: International Prediction of Pregnancy Complications models\' performance needs to be assessed in routine practice, and their impact on decision-making and clinical outcomes needs evaluation.
UNASSIGNED: The International Prediction of Pregnancy Complications-fetal growth restriction and International Prediction of Pregnancy Complications-birthweight models accurately predict fetal growth restriction and birthweight for various assumed gestational ages at delivery. These can be used to stratify the risk status at booking, plan monitoring and management.
UNASSIGNED: This study is registered as PROSPERO CRD42019135045.
UNASSIGNED: This award was funded by the National Institute for Health and Care Research (NIHR) Health Technology Assessment programme (NIHR award ref: 17/148/07) and is published in full in Health Technology Assessment; Vol. 28, No. 14. See the NIHR Funding and Awards website for further award information.
One in ten babies is born small for their age. A third of such small babies are considered to be ‘growth-restricted’ as they have complications such as dying in the womb (stillbirth) or after birth (newborn death), cerebral palsy, or needing long stays in hospital. When growth restriction is suspected in fetuses, they are closely monitored and often delivered early to avoid complications. Hence, it is important that we identify growth-restricted babies early to plan care. Our goal was to provide personalised and accurate estimates of the mother’s chances of having a growth-restricted baby and predict the baby’s weight if delivered at various time points in pregnancy. To do so, first we tested how accurate existing risk calculators (‘prediction models’) were in predicting growth restriction and birthweight. We then developed new risk-calculators and studied their clinical and economic benefits. We did so by accessing the data from individual pregnant women and their babies in our large database library (International Prediction of Pregnancy Complications). Published risk-calculators had various definitions of growth restriction and none predicted the chances of having a growth-restricted baby using our definition. One predicted baby’s birthweight. This risk-calculator performed well, but underpredicted the birthweight by up to 143 g. We developed two new risk-calculators to predict growth-restricted babies (International Prediction of Pregnancy Complications-fetal growth restriction) and birthweight (International Prediction of Pregnancy Complications-birthweight). Both calculators accurately predicted the chances of the baby being born with growth restriction, and its birthweight. The birthweight was underpredicted by <9.7 g. The calculators performed well in both mothers predicted to be low and high risk. Further research is needed to determine the impact of using these calculators in practice, and challenges to implementing them in practice. Both International Prediction of Pregnancy Complications-fetal growth restriction and International Prediction of Pregnancy Complications-birthweight risk calculators will inform healthcare professionals and empower parents make informed decisions on monitoring and timing of delivery.

OBJECTIVE: Can a simplified ovarian hyperstimulation syndrome (OHSS) risk assessment index be developed and validated with sufficient discrimination of moderate/severe OHSS from those without OHSS?
CONCLUSIONS: This easy-to-use OHSS risk assessment index shows good discriminative power and high calibration accuracy in internal and external validation cohorts.
BACKGROUND: An early alert and risk stratification is critical to prevent the occurrence of OHSS. We have previously developed a multi-stage smartphone app-based prediction model to evaluate the risk of OHSS, but app use might not be so convenient in many primary institutions. A simplified OHSS risk assessment index has been required.
METHODS: This training and internal validation of an OHSS risk assessment index used retrospective cohort data from January 2016 to December 2020. External validation was performed with a prospective cohort database from January 2021 to May 2022. There were 15 066 cycles in the training cohort, 6502 cycles in the internal validation cohort, and 8097 cycles in the external validation cohort.
METHODS: This study was performed in the reproductive medicine center of a tertiary hospital. Infertile women who underwent ovarian stimulation were included. Data were extracted from the local database with detailed medical records. A multi-stage risk assessment index was constructed at multiple stages. The first stage was before the initiation of ovarian stimulation, the second was before the ovulation trigger, the third was after oocyte retrieval, and the last stage was on the embryo transfer day if fresh embryo transfer was scheduled.
RESULTS: We established a simplified multi-stage risk assessment index for moderate/severe OHSS, the performance of which was further evaluated with discrimination and calibration abilities in training and internal and external validation cohorts. The discrimination abilities of the OHSS risk assessment index were determined with C-statistics. C-statistics in training (Stages 1-4: 0.631, 0.692, 0.751, 0.788, respectively) and internal (Stages 1-4: 0.626, 0.642, 0.755, 0.771, respectively) and external validation (Stages 1-4: 0.668, 0.670, 0.754, 0.773, respectively) cohorts were all increased from Stage 1 to 3 with similar trends, and were comparable between Stages 3 and 4. Calibration plots showed high agreement between observed and predicted cases in all three cohorts. Incidences of OHSS based on diverse risk stratification (negligible risk, low risk, medium risk, and high risk) were 0%, 0.6%, 2.7%, and 8.3% in the training cohort, 0%, 0.6%, 3.3%, and 8.5% in the internal validation cohort, and 0.1%, 1.1%, 4.1%, and 7.2% in the external validation cohort.
CONCLUSIONS: The influence from clinical interventions including cryopreservation of all embryos cannot be eliminated and thus certain risk factors like estrogen level on trigger day might be assigned with a lower risk score. Another weakness of the study is that several preventive treatments, for instance oral aspirin and letrozole, were not recorded and evaluated in the model. Despite the robust reliability of OHSS assessment index, this tool cannot be used directly for clinical decision-making or as a diagnostic tool. Its value lies in its capacity to evaluate the prognosis of various interventions and to facilitate clinician-patient communication. The combination of this tool and further symptoms and examinations should be all taken into consideration for accurate and personalized management of OHSS.
CONCLUSIONS: The OHSS risk assessment index can be implemented to facilitate personalized counseling and management of OHSS.
BACKGROUND: This study was supported by National Key R&D Program of China (2022YFC2702504), Medical Research Fund Guangdong Provincial (A2024003), and Xinjiang Support Rural Science and Technology (Special Correspondent) Program in Guangdong Province (KTPYJ 2023014). All authors had nothing to disclose.
BACKGROUND: N/A.

UNASSIGNED: Protein Energy Wasting (PEW) has high incidence in adult hemodialysis patients and refers to a state of decreased protein and energy substance. It has been demonstrated that PEW highly affects the quality of survival and increases the risk of death. Nevertheless, its diagnostic criteria are complex in clinic. To simplify the diagnosis method of PEW in adult hemodialysis patients, we previously established a novel clinical prediction model that was well-validated internally using bootstrapping. In this multicenter cross-sectional study, we aimed to externally validate this nomogram in a new cohort of adult hemodialysis patients.
UNASSIGNED: The novel prediction model was built by combining four independent variables with part of the International Society of Renal Nutrition and Metabolism (ISRNM) diagnostic criteria including albumin, total cholesterol, and body mass index (BMI). We evaluated the performance of the new model using discrimination (Concordance Index), calibration plots, and Clinical Impact Curve to assess its predictive utility.
UNASSIGNED: From September 1st, 2022 to August 31st, 2023, 1,158 patients were screened in five medical centers in Shanghai. 622 (53.7%) hemodialysis patients were included for analysis. The PEW predictive model was acceptable discrimination with the area under the curve of 0.777 (95% CI 0.741-0.814). Additionally, the model revealed well-fitted calibration curves. The McNemar test showed the novel model had similar diagnostic efficacy with the gold standard diagnostic method (p > 0.05).
UNASSIGNED: Our results from this cross-sectional external validation study further demonstrate that the novel model is a valid tool to identify PEW in adult hemodialysis patients effectively.

A scoring system to discriminate between uncomplicated and complicated appendicitis is beneficial to determine the optimal treatment for acute appendicitis. We developed a scoring system to discriminate between uncomplicated and complicated appendicitis and assessed the clinical usefulness of the scoring system using external validation. A total of 299 patients with acute appendicitis were retrospectively reviewed. One hundred and ninety-nine patients were assigned to the model development group, while the other 100 patients were assigned to an external validation group. A scoring system for complicated appendicitis was created using a final multivariate logistic regression model with six independent predictors. The area under the receiver operating characteristic curve of the scoring system was 0.882 (95% confidence interval: 0.835-0.929). The cutoff point of the scoring system was 12, and the sensitivity and specificity were 82.9% and 86.2%, respectively. In the external validation group, the area under the receiver operating characteristic curve of the scoring system was 0.868 (95% confidence interval 0.794-0.942), and there was no significant difference between the groups in the area under the receiver operating characteristic curve (P = 0.750). Our newly developed scoring system may contribute to prompt determination of the optimal treatment for acute appendicitis.

BACKGROUND: Severe maternal morbidity is increasing in the United States. Several tools and scores exist to stratify an individual\'s risk of severe maternal morbidity.
OBJECTIVE: We sought to examine and compare the validity of four scoring systems for predicting severe maternal morbidity.
METHODS: This was a retrospective cohort study of all individuals in the Consortium on Safe Labor dataset, which was conducted from 2002 to 2008. Individuals were excluded if they had missing information on risk factors. Severe maternal morbidity was defined based on the Centers for Disease Control and Prevention excluding blood transfusion. Blood transfusion was excluded due to concerns regarding the specificity of ICD codes for this indicator and its variable clinical significance. Risk scores were calculated for each participant using the Assessment of Perinatal Excellence, California Maternal Quality Care Collaborative, Obstetric Comorbidity Index, and Modified Obstetric Comorbidity Index. We calculated the probability of severe maternal morbidity according to the risk scores. The discriminative performance of the prediction score was examined by the areas under receiver operating characteristic curves and their 95% confidence intervals. The area under the curve for each score was compared using the bootstrap resampling. Calibration plots were developed for each score to examine the goodness-of-fit. The concordance probability method was used to define an optimal cutoff point for the best-performing score.
RESULTS: Of 153, 463 individuals, 1,115 (0.7%) had severe maternal morbidity. The California Maternal Quality Care Collaborative scoring system had a significantly higher area under the curve [95% confidence interval] (0.78 [0.77-0.80]) compared to the Assessment of Perinatal Excellence scoring system, Obstetric Comorbidity Index and Modified Obstetric Comorbidity Index scoring systems 0.75 [0.73-0.76],. 0.67 [0.65-0.68], 0.66 [0.70-0.73]; P < 0.001). Calibration plots showed excellent concordance between the predicted and actual severe maternal morbidity for the Assessment of Perinatal Excellence scoring system and Obstetric Comorbidity Index (both Hosmer-Lemeshow test P-values = 1.00, suggesting goodness-of-fit).
CONCLUSIONS: This study validated four risk-scoring systems to predict severe maternal morbidity. Both California Maternal Quality Care Collaborative and Assessment of Perinatal Excellence scoring systems had good discrimination to predict severe maternal morbidity. The Assessment of Perinatal Excellence score and the Obstetric Comorbidity Index had goodness-of-fit. At ideal calculated cut-off points, the Assessment of Perinatal Excellence score had the highest sensitivity of the four scores at 71%, indicating that better scoring systems are still needed for predicting severe maternal morbidity.

BACKGROUND: This study aimed to develop prognostic models for predicting the need for invasive mechanical ventilation (IMV) in intensive care unit (ICU) patients with COVID-19 and compare their performance with the Respiratory rate-OXygenation (ROX) index.
METHODS: A retrospective cohort study was conducted using data collected between March 2020 and August 2021 at three hospitals in Rio de Janeiro, Brazil. ICU patients aged 18 years and older with a diagnosis of COVID-19 were screened. The exclusion criteria were patients who received IMV within the first 24 h of ICU admission, pregnancy, clinical decision for minimal end-of-life care and missing primary outcome data. Clinical and laboratory variables were collected. Multiple logistic regression analysis was performed to select predictor variables. Models were based on the lowest Akaike Information Criteria (AIC) and lowest AIC with significant p values. Assessment of predictive performance was done for discrimination and calibration. Areas under the curves (AUC)s were compared using DeLong\'s algorithm. Models were validated externally using an international database.
RESULTS: Of 656 patients screened, 346 patients were included; 155 required IMV (44.8%), 191 did not (55.2%), and 207 patients were male (59.8%). According to the lowest AIC, arterial hypertension, diabetes mellitus, obesity, Sequential Organ Failure Assessment (SOFA) score, heart rate, respiratory rate, peripheral oxygen saturation (SpO2), temperature, respiratory effort signals, and leukocytes were identified as predictors of IMV at hospital admission. According to AIC with significant p values, SOFA score, SpO2, and respiratory effort signals were the best predictors of IMV; odds ratios (95% confidence interval): 1.46 (1.07-2.05), 0.81 (0.72-0.90), 9.13 (3.29-28.67), respectively. The ROX index at admission was lower in the IMV group than in the non-IMV group (7.3 [5.2-9.8] versus 9.6 [6.8-12.9], p < 0.001, respectively). In the external validation population, the area under the curve (AUC) of the ROX index was 0.683 (accuracy 63%), the AIC model showed an AUC of 0.703 (accuracy 69%), and the lowest AIC model with significant p values had an AUC of 0.725 (accuracy 79%).
CONCLUSIONS: In the development population of ICU patients with COVID-19, SOFA score, SpO2, and respiratory effort signals predicted the need for IMV better than the ROX index. In the external validation population, although the AUCs did not differ significantly, the accuracy was higher when using SOFA score, SpO2, and respiratory effort signals compared to the ROX index. This suggests that these variables may be more useful in predicting the need for IMV in ICU patients with COVID-19.
RESULTS:
UNASSIGNED: NCT05663528.

OBJECTIVE: Stockholm3 is a comprehensive blood test amalgamating protein biomarkers, genetic indicators, and clinical data to predict clinically significant prostate cancer risk (International Society of Urological Pathology grade ≥2 upon biopsy). Our study aims to externally validate Stockholm3 and compare its performance with the use of prostate-specific antigen (PSA) and the Rotterdam Prostate Cancer Risk Calculator (RPCRC) for clinically significant prostate cancer detection.
METHODS: We gathered data from men subjected to prostate biopsies at the Martini-Klinik, Germany, between 2014 and 2017. Participants were selected based on elevated PSA levels or suspicious digital rectal examinations, all undergoing a 10-12-core systematic biopsy without a magnetic resonance imaging-targeted biopsy. We assessed Stockholm3 and RPCRC performance for clinically significant prostate cancer detection. Furthermore, we compared the proportion of men recommended for biopsy and biopsy outcomes with Stockholm3 and RPCRC against PSA ≥3 ng/ml.
UNASSIGNED: Our study encompassed 405 biopsied men, with a median age of 66 yr (interquartile range [IQR]: 60-72), PSA levels at 7 ng/ml (IQR: 5.2-10.8), and Stockholm3 scores at 18 (IQR: 10-34). Among them, 128 men (31%) received clinically significant prostate cancer diagnoses. Employing the recommended Stockholm3 threshold (≥15) could have reduced unnecessary biopsies by 52%, while detecting 92% of clinically significant cases compared with using PSA ≥3 ng/ml as a biopsy criterion. Both Stockholm3 and RPCRC exhibited strong discrimination, with area under the curve values of 0.80 (95% confidence interval [CI]: 0.76-0.85) and 0.75 (95% CI: 0.70-0.80), respectively. Stockholm3 demonstrated good calibration, while RPCRC underestimated the risk compared with observed outcomes. Moreover, Stockholm3 yielded positive clinical net benefits, whereas RPCRC yielded negative net benefits for clinically relevant thresholds.
CONCLUSIONS: Stockholm3 utilization could detect 92% of clinically significant prostate cancer cases while simultaneously reducing unnecessary biopsies by 52%, compared with the PSA ≥3 ng/ml criterion, based on our analysis within a cohort of men who underwent systematic biopsies.
RESULTS: In a German clinical cohort of 405 men, Stockholm3, a blood test for early prostate cancer detection, exhibited favorable clinical benefits. It identified a substantial number of clinically significant cases while reducing unnecessary biopsies by over half in men without the disease and those with clinically nonsignificant prostate cancer.

BACKGROUND: Atrial fibrillation (AF) is common among intensive care unit (ICU) patients and significantly raises the in-hospital mortality rate. Existing scoring systems or models have limited predictive capabilities for AF patients in ICU. Our study developed and validated machine learning models to predict the risk of in-hospital mortality in ICU patients with AF.
RESULTS: Medical Information Mart for Intensive Care (MIMIC)-IV dataset and eICU Collaborative Research Database (eICU-CRD) were analyzed. Among ten classifiers compared, adaptive boosting (AdaBoost) showed better performance in predicting all-cause mortality in AF patients. A compact model with 15 features was developed and validated. Both the all variable and compact models exhibited excellent performance with area under the receiver operating characteristic curves (AUCs) of 1(95%confidence interval [CI]: 1.0-1.0) in the training set. In the MIMIC-IV testing set, the AUCs of the all variable and compact models were 0.978 (95% CI: 0.973-0.982) and 0.977 (95% CI: 0.972-0.982), respectively. In the external validation set, the AUCs of all variable and compact models were 0.825 (95% CI: 0.815-0.834) and 0.807 (95% CI: 0.796-0.817), respectively.
CONCLUSIONS: An AdaBoost-based predictive model was subjected to internal and external validation, highlighting its strong predictive capacity for assessing the risk of in-hospital mortality in ICU patients with AF.

暂无摘要。

Sleep-wake (SW) cycle detection is a key step for extracting temporal sleep metrics from actigraphy. Various supervised learning algorithms have been developed, yet their generalizability from sensor to sensor or study to study is questionable. In this paper, we detail and validate an unsupervised algorithm-CircaCP-for detecting SW cycles from actigraphy. It first uses a robust cosinor model to estimate circadian rhythm, then searches for a single change point (CP) within each circadian cycle. Using CircaCP, we estimated sleep/wake onset times (S/WOTs) from 2125 individuals\' data in the MESA sleep study and compared the estimated S/WOTs against self-reported S/WOT event markers, using Bland-Altman analysis as well as variance component analysis. On average, SOTs estimated by CircaCP were 3.6 min behind those reported by event markers, and WOTs by CircaCP were less than 1 min behind those reported by markers. These differences accounted for less than 0.2% variability in S/WOTs, considering other sources of between-subject variations. Rooted in first principles of human circadian rhythms, our algorithm transferred seamlessly from children\'s hip-worn ActiGraph data to ageing adults\' wrist-worn Actiwatch data. The generalizability of our algorithm suggests that it can be widely applied to actigraphy collected by other sensors and studies.