Prediction Score Research Articles

Magnetic Resonance Imaging-Based Vertebral Bone Quality Score for Prediction of Cage Subsidence and Screw Loosening in Patients Undergoing Degenerative Lumbar Surgery: A Meta-analysis.

Poor bone quality is a risk factor for postoperative complications after degenerative lumbar fusion surgery. The magnetic resonance imaging-based vertebral bone quality (VBQ) score is a good tool for assessing bone quality, and this is the first meta-analysis performed to summarize the predictive value of the VBQ score for cage subsidence and screw loosening in patients undergoing degenerative lumbar surgery. Studies were comprehensively searched in electronic databases. The quality of the studies was assessed. The pooled sensitivity, specificity and summary receiver operating characteristic curve were calculated. Publication bias was assessed and meta-regression was conducted. We ultimately included 9 studies with a total of 1,404 patients with a mean age of 60.4 years and a percentage of females of 57.0%. According to the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to assess methodological quality, the quality of the included studies was relatively low and risks of bias might exist. Results showed that a high VBQ was significantly associated with cage subsidence and screw loosening, and risk factor analysis revealed that the merged odds ratio was 5.37 for cage subsidence and 3.87 for screw loosening. With a VBQ cutoff value of 3.34±0.45, the pooled sensitivity and specificity for the diagnosis of postoperative complications were 0.75 and 0.75, respectively, and the area under the curve was 0.82 (95% confidence interval, 0.78-0.85). A high VBQ was associated with a high risk of cage subsidence and screw loosening in patients who underwent degenerative lumbar surgery. The VBQ score could be considered for identifying high-risk patients for further evaluation.

Venous Thromboembolism Risk Assessment and Thromboprophylaxis Practice in Hospitalized Medical Patients: The Experience of a Singapore Teaching Hospital

AbstractDespite the availability of institutional guidelines, the practice of venous thromboembolism (VTE) risk assessment and thromboprophylaxis remains inadequate in Singapore. With hospital-associated VTE (HA-VTE) being a common cause of preventable mortality for medical patients, it is vital for prompt, appropriate prescription of thromboprophylaxis after VTE risk assessment. This study aimed to (1) assess the local practice of VTE risk assessment and prophylaxis according to institutional guidelines, (2) study the risk factors of potential preventable HA-VTE among hospitalized medical patients, and (3) improve the quality of care with respect to early prevention of HA-VTE. An audit was performed on daily new admissions to two general medical wards in a teaching hospital in Singapore (total capacity of 76 beds) over 2 weeks. Each new admission's medical records were reviewed to examine whether (1) VTE risk assessment was performed by the managing medical teams, (2) thromboprophylaxis was prescribed during admission in high VTE risk patients, and (3) any contraindications to pharmacological thromboprophylaxis for cases with high VTE risk but no pharmacological thromboprophylaxis prescribed was present. Only 1 out of 52 cases had VTE risk assessment performed. Thirty-one cases (59.1%) were identified to have high VTE risk using the Padua Prediction Score. However, only 1 out of the 31 cases (3.2%) had VTE prophylaxis prescribed. Adherence to local institutional guidelines remains poor despite increasing awareness of the importance of VTE risk assessment and prophylaxis in the prevention of associated morbidity and mortality. Certain patient profiles should prompt clinicians to perform VTE risk assessment.

Development of a predictive scoring system for vitamin D deficiency 'Vitamin D Deficiency Predicting Scoring (ViDDPreS)' based on the vitamin D status in young Japanese women: a nationwide cross-sectional study.

Vitamin D deficiency (VDD) is common among young women and causes various health problems, including those that occur during pregnancy and childbirth. Thus, we investigated the risk factors for VDD in young Japanese women and developed a simple risk scoring system called Vitamin D Deficiency Predicting Scoring (ViDDPreS). A cross-sectional study, using the following factors for multivariate logistic regression analysis to create the ViDDPreS score: residential area, season, cumulative ambient ultraviolet-B irradiation, BMI, vitamin D supplement use, sun exposure habits, frequency of habitual food intake and eating habits. The subjects were randomly divided into development and test sets for analysis. Serum 25-hydroxivitamin D concentration of less than 20 ng/ml was defined as VDD. Four regions (Hokkaido/Tohoku, Kanto, Chubu/Kinki/Shikoku and Kyushu/Okinawa) in Japan. Five hundred and eighty-three healthy women aged 18-40 years. In the development set, the VDD group (68·4 %) had higher proportions of the following variables than the non-VDD group: residential area outside the Kanto region; blood samples obtained in winter; low BMI (<18·5 kg/m2); vitamin D supplement non-users; short time regularly spent outside on weekdays; intake of fish, vitamin D-abundant fish, dried fish and redfish less than once a week. VDD risk was classified as low, medium or high according to the ViDDPreS scores including these contributing factors, with a test set C-index of 0·671. We identified the risk factors for VDD in young Japanese women and developed a simple risk scoring system that enables us to assess VDD risk and aid in the development of appropriate prevention and treatment strategies for this population.

Machine Learning-Based Prediction of Clinical Outcomes in Microsurgical Clipping Treatments of Cerebral Aneurysms.

Background: This study investigates the application of Machine Learning techniques to predict clinical outcomes in microsurgical clipping treatments of cerebral aneurysms, aiming to enhance healthcare processes through informed clinical decision making. Methods: Relying on a dataset of 344 patients' preoperative characteristics, various ML classifiers were trained to predict outcomes measured by the Glasgow Outcome Scale (GOS). The study's results were reported through the means of ROC-AUC scores for outcome prediction and the identification of key predictors using SHAP analysis. Results: The trained models achieved ROC-AUC scores of 0.72 ± 0.03 for specific GOS outcome prediction and 0.78 ± 0.02 for binary classification of outcomes. The SHAP explanation analysis identified intubation as the most impactful factor influencing treatment outcomes' predictions for the trained models. Conclusions: The study demonstrates the potential of ML for predicting surgical outcomes of ruptured cerebral aneurysm treatments. It acknowledged the need for high-quality datasets and external validation to enhance model accuracy and generalizability.

Right Ventricular Longitudinal Strain-Related Indices in Acute Pulmonary Embolism.

Pulmonary embolism (PE) is correlated with serious morbidity and mortality. Efforts have been made to establish and validate mortality predictive scores based mainly on clinical parameters. Patients with PE and traditional indices of echocardiographic right ventricular (RV) dysfunction or pressure overload have a higher probability of a worse outcome. During the last two decades, studies regarding the use of two-dimensional speckle-tracking echocardiography (2DSTE) and its derived indices in the setting of acute PE have been conducted. In this comprehensive review of the literature, we aimed to summarize these studies. Safe conclusions and comparisons among the reviewed studies are prone to statistical errors, mainly because the studies published were heterogenous in design, different 2DSTE-derived parameters were tested, and different clinical outcomes were used as endpoints. Nonetheless, RV strain indices and, more commonly, regional longitudinal strain of the RV free wall have shown a promising correlation with mortality, assisting in the differential diagnosis between PE and other acute or chronic disorders.

Development, assessment and validation of a novel nomogram model for predicting stroke mimics in stroke center：A single-center observational study

BackgroundEarly recognition and prediction of stroke mimics (SM) can avoid inappropriate recanalization therapy and delay in the management of SM etiology. The purpose of this study is to screen the predictors for SM and develop a novel predictive nomogram model for predicting SM. Meanwhile, the diagnostic performance of the nomogram model was evaluated and validated. The diagnostic efficacy of the nomogram model was also compared with four other SM structured scales. MethodsThe clinical data of eligible patients were retrospectively enrolled as training datasets from January 2020 to December 2021; and the clinical data of eligible patients were prospectively enrolled as validation datasets from February to December 2022 in stroke center, Shengjing hospital, respectively. Univariate analysis and Lasso regression were used to select the optimal predictors for the training set, and a nomogram model was constructed by multivariate logistics regression, predictive scoring based on nomogram model is performed for each subject suffering from suspected acute ischemic stroke. Area under the curve (AUC), Hosmer-Lemeshow goodness-of-fit test, Calibration curve, decision curve analysis (DCA), clinical impact curve (CIC) analysis and bootstrap sampling were performed to assess and validate the predictive performance and clinical utility of the nomogram model, and the DeLong test was used to compare the overall diagnostic performance of the nomogram model with the other four structured SM scales. The Delong test was also conducted to assess the external reliability of the SM nomogram model by comparing the predictive diagnostic performance of the validation set with the training set. Additionally, the Calibration curve was utilized to evaluate the diagnostic calibration capability of the SM nomogram model in the validation set. Results703 eligible patients (68 with SM, accounting for 9.7 %) were assigned to the training set, while 301 patients (26 with SM, accounting for 8.6 %) were assigned to the validation set. A nomogram model was then developed using these six parameters (SBP, history of epilepsy, isolated dizziness, isolated sensory impairment, headache, and absence of speech impairment symptoms), a dynamic web-based version of the nomogram was subsequently created. Comparing with four other scales, the nomogram model showed the highest overall diagnostic performance (AUC = 0.929, 95%CI = 0.908–0.947). The Hosmer-Lemeshow goodness-of-fit test was conducted to assess the agreement between the predicted SM values from the model and the observed SM values. The results of the test indicated a favorable consistency (χ2 = 9.299, P = 0.3177) between the predicted and observed SM. The results obtained from the analysis of the Calibration curve, DCA curve, and CIC analysis suggested that the nomogram possesses a favorable predictive capacity and superior clinical usefulness. Furthermore, the external validation demonstrated that there is no significant difference in the overall predictive diagnostic performance between the validation set and training set (0.929 vs 0.910, P > 0.05), thereby confirming the favorable stability of the nomogram model. ConclusionOur study firstly proposed a nomogram prediction approach based on the clinical features of SM, which could effectively predict the occurrence of SM. The utilization of the nomogram in stroke center proves advantageous for the identification and evaluation of SM, thereby enhancing diagnostic decision-making and strategies employed for suspected acute stroke patients.

Padua Prediction Score and Hospital-Acquired Proximal and Isolated Distal Deep Vein Thrombosis in Symptomatic Patients.

Hospital-acquired deep vein thrombosis (DVT) is an important cause of morbidity and mortality. The purpose of this study was to evaluate the prevalence of proximal lower limb DVT and isolated distal DVT (IDDVT) and their relationship to the Padua Prediction Score (PPS) in acutely ill, hospitalized patients. In a single-center cross-sectional study, all inpatients from medical departments with suspected lower-extremity DVT were evaluated with whole-leg ultrasonography during 183 days from 2016 to 2017. Among the 505 inpatients (age 78.0 ± 13.3, females 59.2%) from medical departments, 204 (40.2%) had PPS ≥ 4, but only 54.4% of them underwent pharmacological thrombo-prophylaxis. Whole-leg ultrasonography detected 47 proximal DVTs (9.3%) and 65 IDDVTs (12.8%). Proximal DVT prevalence was higher in patients with high PPS vs. those with low PPS (12.7% vs. 7.0% p = 0.029, respectively), whereas IDDVT prevalence was similar in patients with high and low PPS (14.7% vs. 11.6% p = 0.311, respectively). The area under the receiver operating curve (AUC) for the PPS was 0.62 ± 0.03 for all DVTs, 0.64 ± 0.04 for proximal DVTs, and 0.58 ± 0.04 for IDDVTs. In hospitalized patients, IDDVT had similar prevalence regardless of PPS risk stratification. Adherence to thrombo-prophylaxis in patients was still far from optimal.

A Novel Score to Predict Individual Risk for Future Alzheimer’s Disease: A Longitudinal Study of the ADNI Cohort

Background: Identifying high-risk individuals with mild cognitive impairment (MCI) who are likely to progress to Alzheimer’s disease (AD) is crucial for early intervention. Objective: This study aimed to develop and validate a novel clinical score for personalized estimation of MCI-to-AD conversion. Methods: The data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study were analyzed. Two-thirds of the MCI patients were randomly assigned to a training cohort (n = 478), and the remaining one-third formed the validation cohort (n = 239). Multivariable logistic regression was performed to identify factors associated with MCI-to-AD progression within 4 years. A prediction score was developed based on the regression coefficients derived from the logistic model and tested in the validation cohort. Results: A lipidomics-signature was obtained that showed a significant association with disease progression. The MCI conversion scoring system (ranged from 0 to 14 points), consisting of the lipidomics-signature and five other significant variables (Apolipoprotein ɛ4, Rey Auditory Verbal Learning Test immediate and delayed recall, Alzheimer’s Disease Assessment Scale delayed recall test, Functional Activities Questionnaire, and cortical thickness of the AD signature), was constructed. Higher conversion scores were associated with a higher proportion of patients converting to AD. The scoring system demonstrated good discrimination and calibration in both the training cohort (AUC = 0.879, p of Hosmer-Lemeshow test = 0.597) and the validation cohort (AUC = 0.915, p of Hosmer-Lemeshow test = 0.991). The risk classification achieved excellent sensitivity (0.84) and specificity (0.75). Conclusions: The MCI-to-AD conversion score is a reliable tool for predicting the risk of disease progression in individuals with MCI.

MSCT enterography score for prediction of disease severity in patients with active ulcerative colitis

BackgroundUlcerative colitis (UC) is a chronic non-specific inflammatory bowel disease (IBD). It is characterized by diffuse inflammatory process of the bowel mucosa with a relapsing course. The precise evaluation of UC severity is pivotal in the therapeutic decision-making. Modified Mayo score is consistently used for the evaluation of the disease activity which depends on the patient’s symptoms as well as the colonoscopic findings. The aim of this study is to assess the role of the CT enterography (CTE) scoring system in the evaluation of the disease severity in ulcerative colitis. From October 2022 to July 2023, 66 patients with known ulcerative colitis patients at time of disease activity were referred from the inflammatory bowel disease unit for radiological assessment by CTE. CT images were analyzed to determine the anatomical location of the affected bowel segments, mucosal thickening and hyperenhancement as well as the extra-enteric involvement. Correlation with the modified Mayo score was established.ResultsOur results showed a statistical significant correlation between modified Mayo score and CTE with a P value of 0.000. The correlation coefficient is r = 0.964. The cut-off value of the optimal CTE score to predict mild and moderate UC was 7.5 with 0.996 area under the ROC curve, 92%sensitivity and 100% specificity. The cut-off value of the optimal CTE score to predict moderate and severe UC was 10.5 with 0.983 area under the ROC curve, 90.6% sensitivity and 100% specificity.ConclusionsCTE is a reliable diagnostic method in the systematic assessment of the disease severity of active ulcerative colitis. CTE score shows a strong proportionate correlation with modified Mayo score. The aggravation of the course of the disease increased the CTE score. CTE scoring system can help plan the therapeutic strategy and predict prognosis.

Integrated clinical risk prediction of type 2 diabetes with a multifactorial polygenic risk score.

Combining information from multiple GWASs for a disease and its risk factors has proven a powerful approach for development of polygenic risk scores (PRSs). This may be particularly useful for type 2 diabetes (T2D), a highly polygenic and heterogeneous disease where the additional predictive value of a PRS is unclear. Here, we use a meta-scoring approach to develop a metaPRS for T2D that incorporated genome-wide associations from both European and non-European genetic ancestries and T2D risk factors. We evaluated the performance of this metaPRS and benchmarked it against existing genome-wide PRS in 620,059 participants and 50,572 T2D cases amongst six diverse genetic ancestries from UK Biobank, INTERVAL, the All of Us Research Program, and the Singapore Multi-Ethnic Cohort. We show that our metaPRS was the most powerful PRS for predicting T2D in European population-based cohorts and had comparable performance to the top ancestry-specific PRS, highlighting its transferability. In UK Biobank, we show the metaPRS had stronger predictive power for 10-year risk than all individual risk factors apart from BMI and biomarkers of dysglycemia. The metaPRS modestly improved T2D risk stratification of QDiabetes risk scores for 10-year risk prediction, particularly when prioritising individuals for blood tests of dysglycemia. Overall, we present a highly predictive and transferrable PRS for T2D and demonstrate that the potential for PRS to incrementally improve T2D risk prediction when incorporated into UK guideline-recommended screening and risk prediction with a clinical risk score.

Application of machine learning algorithms in predicting carotid artery plaques using routine health assessments.

Cardiovascular diseases (CVD) constitute a grave global health challenge, engendering significant socio-economic repercussions. Carotid artery plaques (CAP) are critical determinants of CVD risk, and proactive screening can substantially mitigate the frequency of cardiovascular incidents. However, the unequal distribution of medical resources precludes many patients from accessing carotid ultrasound diagnostics. Machine learning (ML) offers an effective screening alternative, delivering accurate predictions without the need for advanced diagnostic equipment. This study aimed to construct ML models that utilize routine health assessments and blood biomarkers to forecast the onset of CAP. In this study, seven ML models, including LightGBM, LR, multi-layer perceptron (MLP), NBM, RF, SVM, and XGBoost, were used to construct the prediction model, and their performance in predicting the risk of CAP was compared. Data on health checkups and biochemical indicators were collected from 19,751 participants at the Beijing MJ Health Screening Center for model training and validation. Of these, 6,381 were diagnosed with CAP using carotid ultrasonography. In this study, 21 indicators were selected. The performance of the models was evaluated using the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and area under the curve (AUC) value. Among the seven ML models, the light gradient boosting machine (LightGBM) had the highest AUC value (85.4%). Moreover, age, systolic blood pressure (SBP), gender, low-density lipoprotein cholesterol (LDL-C), and total cholesterol (CHOL) were the top five predictors of carotid plaque formation. This study demonstrated the feasibility of predicting carotid plaque risk using ML algorithms. ML offers effective tools for improving public health monitoring and risk assessment, with the potential to improve primary care and community health by identifying high-risk individuals and enabling proactive healthcare measures and resource optimization.

Comparison of five scores to predict mortality in malignant pleural effusion.

Malignant pleural effusion (MPE) is a complication of malignancy. Treatment of MPE is based on predicted outcome. The aim of this study was to compare the performance characteristics of LENT, PROMISE, RECLS, AL and pNLR scores for prediction of mortality in lung cancer patients who have MPE. Patients who were diagnosed with MPE that was associated with underlying lung cancer between January 2010 and December 2019 were included and analyzed retrospectively in a single center. Outcomes considered were 30-day, 6 months, and 1-year mortality. A total of 180 patients were examined. For 30-day mortality, the areas under the ROC curves (AUC) (95% CI) were: LENT 0.83 (0.76-0.87), RECLS 0.71 (0.63-0.77), and PROMISE 0.70 (0.17-0.38). For 6-month and 1-year mortality the order of these AUCs was similar. Cox regression showed that none of the scores were significantly associated with 30-day mortality, but LENT and RECLS were significantly associated with 6-month and 1-year mortality. Comparison of - 2log likelihood ratios showed that LENT score was more, strongly associated with 6-month mortality than PROMISE (p = 0.001) or RECLS (p = 0.02). LENT score was also more strongly associated with 1-year mortality than PROMISE (p = 0.001) but there was no difference between LENT and RECLS score (p = 0.64). We observed that the LENT score was more predictive than the other scores in mortality in patients who have lung cancer and MPE. The LENT and RECLS scores have similar performance characteristics for prediction of 1-year mortality in these patients.

Diagnosis of ophthalmologic diseases in canines based on images using neural networks for image segmentation

The primary challenge in diagnosing ocular diseases in canines based on images lies in developing an accurate and reliable machine learning method capable of effectively segmenting and diagnosing these conditions through image analysis. Addressing this challenge, the study focuses on developing and rigorously evaluating a machine learning model for diagnosing ocular diseases in canines, employing the U-Net neural network architecture as a foundational element of this investigation.Through this extensive evaluation, the authors identified a model that exhibited good reliability, achieving prediction scores with an Intersection over Union (IoU) exceeding 80 %, as measured by the Jaccard index. The research methodology encompassed a systematic exploration of various neural network backbones (VGG, ResNet, Inception, EfficientNet) and the U-Net model, combined with an extensive model selection process and an in-depth analysis of a custom training dataset consisting of historical images of different medical symptoms and diseases in dog eyes.The results indicate a fairly high degree of accuracy in the segmentation and diagnosis of ocular diseases in canines, demonstrating the model's effectiveness in real-world applications. In conclusion, this potentially makes a significant contribution to the field by utilizing advanced machine-learning techniques to develop image-based diagnostic routines in veterinary ophthalmology. This model's successful development and validation offer a promising new tool for veterinarians and pet owners, enhancing early disease detection and improving health outcomes for canine patients.

Machine Learning of Laboratory Data in Predicting 30-Day Mortality for Adult Hemophagocytic Lymphohistiocytosis.

Hemophagocytic Lymphohistiocytosis (HLH) carries a high mortality rate. Current existing risk-evaluation methodologies fall short and improved predictive methods are needed. This study aimed to forecast 30-day mortality in adult HLH patients using 11 distinct machine learning (ML) algorithms. A retrospective analysis on 431 adult HLH patients from January 2015 to September 2021 was conducted. Feature selection was executed using the least absolute shrinkage and selection operator. We employed 11 ML algorithms to create prediction models. The area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, F1 score, calibration curve and decision curve analysis were used to evaluate these models. We assessed feature importance using the SHapley Additive exPlanation (SHAP) approach. Seven independent predictors emerged as the most valuable features. An AUC between 0.65 and 1.00 was noted among the eleven ML algorithms. The gradient boosting decision tree (GBDT) algorithms demonstrated the most optimal performance (1.00 in the training cohort and 0.80 in the validation cohort). By employing the SHAP method, we identified the variables that contributed to the model and their correlation with 30-day mortality. The AUC of the GBDT algorithms wasthe highest when using the top 4 (ferritin, UREA, age and thrombin time (TT)) features, reaching 0.99 in the training cohort and 0.83 in the validation cohort. Additionally, we developed a web-based calculator to estimate the risk of 30-day mortality. With GBDT algorithms applied to laboratory data, accurate prediction of 30-day mortality is achievable. Integrating these algorithms into clinical practice could potentially improve 30-day outcomes.

The Lyon Score: A Novel Reflux Scoring System Based on the Lyon Consensus 2.0 That Associates With Treatment Outcome From Antireflux Therapy.

We explored if a score derived from parameters from esophageal testing could increase confidence in diagnosing conclusive gastroesophageal reflux disease and in predicting outcome. A prediction score was developed using metrics based on Lyon Consensus 2.0 thresholds extracted from endoscopy and pH-impedance monitoring. The Lyon score was the sum of weighted scores derived from a logistic regression model. The outcome was response to antireflux therapy, defined as 50% reduction in global symptoms on validated questionnaires. An existing database of endoscopy-negative patients with typical reflux symptoms undergoing esophageal testing from 2 centers (Europe and the United States) constituted the developmental cohort, while 2 separate cohorts (Europe and Asia) served as validation cohorts. Receiver operating characteristics analysis determined performance of the Lyon score in predicting treatment response. In 281 developmental cohort patients (median age 53 years, 57.7% female), the Lyon score demonstrated an area under the curve (AUC) of 0.819 in predicting 50% symptom improvement ( P < 0.001) on receiver operating characteristics, with an optimal threshold of 6.25 (sensitivity 81.2%, specificity 73.4%). Of the individual components, only acid exposure time (AUC 0.799, P < 0.001), mean nocturnal baseline impedance (AUC 0.785, P < 0.001), and reflux episodes (AUC 0.764, P < 0.001) approached the Lyon score performance. The Lyon score segregated treatment response in both the European (AUC 0.908, P < 0.001) and Asian validation cohorts (AUC 0.637, P < 0.001) and outperformed the DeMeester score in sensitivity for predicting outcome in the developmental and Asian validation cohorts. The novel Lyon score segregates reflux phenotypes and identifies likelihood of symptom response from antireflux therapy.

Clinical correlates of a high cardiorespiratory risk score for very low birth weight infants

Abstract Background A pulse oximetry warning system (POWS) to analyze heart rate and oxygen saturation data and predict risk of sepsis was developed for very low birth weight (VLBW) infants. Methods We determined the clinical correlates and positive predictive value (PPV) of a high POWS score in VLBW infants. In a two-NICU retrospective study, we identified times when POWS increased above 6 (POWS spike). We selected an equal number of control times, matched for gestational and chronologic age. We reviewed records for infection and non-infection events around POWS spikes and control times. We calculated the frequencies and PPV of a POWS spike for infection or another significant event. Results We reviewed 111 POWS spike times and 111 control times. Days near POWS spikes were more likely to have clinical events than control days (77% vs 50%). A POWS spike had 52% PPV for suspected or confirmed infection and 77% for any clinically significant event. Respiratory deterioration occurred near more POWS spike times than control times (34% vs 18%). Conclusions In a retrospective cohort, infection and respiratory deterioration were common clinical correlations of a POWS spike. POWS had a high PPV for significant clinical events with or without infection. Impact There are significant gaps in understanding the best approach to implementing continuous sepsis prediction models so that clinicians can best respond to early signals of deterioration. Infection and respiratory deterioration were common clinical events identified at the time of a high predictive model score. Understanding the clinical correlates of a high-risk early warning score will inform future implementation efforts.

Model-Based Prediction for Small Domains Using Covariates: A Comparison of Four Methods

Abstract We consider methods for model-based small area estimation when the number of areas with sampled data is a small fraction of the total areas for which estimates are required. Abundant auxiliary information is available from the survey for all the sampled areas. Further, through an external source, there is information for all areas. The goal is to use auxiliary variables to predict the outcome of interest for all areas. We compare areal-level random forests and LASSO approaches to a frequentist forward variable selection approach and a Bayesian shrinkage method using a horseshoe prior. Further, to measure the uncertainty of estimates obtained from random forests and the LASSO, we propose a modification of the split conformal procedure that relaxes the assumption of exchangeable data. We show that the proposed method yields intervals with the correct coverage rate and this is confirmed through a simulation study. This work is motivated by Ghanaian data available from the sixth Ghana Living Standards Survey (GLSS) and the 2010 Population and Housing Census, in the Greater Accra Metropolitan Area (GAMA) region, which comprises eight districts that are further divided into enumeration areas (EAs). We estimate the areal mean household log consumption using both datasets. The outcome variable is measured only in the GLSS for 3 percent of all the EAs (136 out of 5019) and 174 potential covariates are available in both datasets. In the application, among the four modeling methods considered, the Bayesian shrinkage performed the best in terms of bias, mean squared error (MSE), and prediction interval coverages and scores, as assessed through a cross-validation study. We find substantial between-area variation with the estimated log consumption showing a 1.3-fold variation across the GAMA region. The western areas are the poorest while the Accra Metropolitan Area district has the richest areas.

SIMAP500: A novel risk score to identify recipients at higher risk of hepatocellular carcinoma recurrence following liver transplantation.

Recurrence of hepatocellular carcinoma (HCC) following liver transplantation (LT) has a devastating influence on recipients' survival; however, the risk of recurrence is not routinely stratified. Risk stratification is vital with a long LT waiting time, as that could influence the recurrence despite strict listing criteria. This study aims to identify predictors of recurrence and develop a novel risk prediction score to forecast HCC recurrence following LT. A retrospective review of LT for HCC recipients at University Hospitals Birmingham between July 2011 and February 2020. Univariate and multivariate analyses were performed to identify recurrence predictors, based on which the novel SIMAP500 (satellite nodules, increase in size, microvascular invasion, AFP > 500, poor differentiation) risk score was proposed. 234 LTs for HCC were performed with a median follow-up of 5.3 years. Recurrence developed in 25 patients (10.7%). On univariate analyses, RETREAT score > 3, α-fetoprotein (AFP) at listing 100-500 and > 500, bridging, increased tumour size between imaging at the listing time and explant histology, increase in the size of viable tumour between listing and explant, presence of satellite nodules, micro- and macrovascular invasion on explant and poor differentiation of tumours were significantly associated with recurrence, based on which, the SIMAP500 risk score is proposed. The SIMAP500 demonstrated an excellent predictive ability (c-index = 0.803) and outperformed the RETREAT score (c-index = 0.73). SIMAP500 is indicative of the time to disease recurrence. SIMAP500 risk score identifies the LT recipients at risk of HCC recurrence. Risk stratification allows patient-centric post-transplant surveillance programs. Further validation of the score is recommended.

Acute COVID-19 severity markers predict post-COVID new-onset psychiatric disorders: A 2-year cohort study of 34,489 patients.

New-onset psychiatric disorders are frequent after COVID-19. We aim to determine whether acute COVID-19 severity markers can predict post-COVID new-onset psychiatric disorders. We conducted an electronic health records (EHR) cohort study of patients hospitalized for COVID-19 and without any known history of psychiatric disorders. Patients were included between January 2020 and September 2022 in one of the 36 university hospitals of the Assistance Publique - Hôpitaux de Paris. Acute COVID-19 clinical and biological severity markers were recorded during hospitalization for COVID-19. Psychiatric ICD-10 diagnoses were recorded up to 2 years and 9 months after hospitalization for COVID-19. Predictors of post-COVID new-onset psychiatric disorders were identified based on Cox regression models and sensitivity analyses. Predictive scores were built and tested in age- and sex-stratified populations. A total 34,489 patients hospitalized for COVID-19 were included; 3717 patients (10.8%) had at least one post-COVID new-onset psychiatric disorder. Hospital stay >7 days (HR = 1.72, 95%CI [1.59-1.86], p < 0.001), acute delirium (HR = 1.49, 95%CI [1.28-1.74], p < 0.001), elevated monocyte count (HR = 1.14, 95%CI [1.06-1.23], p < 0.001) and elevated plasma CRP (HR = 0.92, 95%CI [0.86-0.99], p = 0.04) independently predicted post-COVID new-onset psychiatric disorders. Sensitivity analyses confirmed hospital stay >7 days, acute delirium, and elevated monocyte count as predictors. Predictive scores based on these variables had good 12-month positive predictive values, up to 7.5 times more accurate than random in women < 65 years. In conclusion, hospital stay >7 days, acute delirium, and elevated monocyte count during acute COVID-19 predict post-COVID new-onset psychiatric disorders.

Waste management and water quality evaluation prediction in urban environments through advanced robust hybrid machine learning algorithms

Water quality management is a crucial aspect of environmental protection, requiring the monitoring and regulation of effluent discharges into surface water bodies. This research introduces a novel approach to predicting Water Quality Evaluation (WQE) through a unique hybrid model, ABC-DWKNN-ICA, which integrates the Distance-weighted K-Nearest Neighbors (DWKNN) algorithm with the Artificial Bee Colony (ABC), Firefly Algorithm (FA), Imperialist Competitive Algorithm (ICA), and Gravitational Search Algorithm (GSA). Utilizing a comprehensive dataset of 1106 data points from Telangana, India, spanning 2018–2020, the study examines a range of water quality parameters, including Ground Water Level (GWL), Potential of Hydrogen (PH), Electrical Conductivity (EC), and others. The ABC-DWKNN-ICA model demonstrates exceptional performance in terms of Recall, Precision, Accuracy, and F1 Score for WQE prediction, distinguishing itself with enhanced feature selection, improved classification accuracy, robustness to noise and outliers, reduced dimensionality, and scalability to large datasets. This hybrid model represents a significant advancement over existing approaches, including traditional Hybrid Machine Learning (HML) algorithms such as ABC-DWKNN, FA-DWKNN, ICA-DWKNN, and GSA-DWKNN. By focusing on the capabilities of ABC-DWKNN-ICA rather than comparing all HML algorithms, the research highlights its superior effectiveness in water quality prediction, with performance metrics of 0.83 for Recall, 0.86 for Precision, 0.91 for Accuracy, and 0.86 for F1 Score. This study thus fills a critical research gap by demonstrating the model's value in environmental data analysis and offering promising prospects for more effective management of water resources. Additionally, feature selection, dimensionality reduction, enhanced accuracy, noise handling, and imbalanced dataset management are key advantages of the proposed model.