Prediction Score Research Articles

Advances in artificial intelligence for predicting complication risks post-laparoscopic radical gastrectomy for gastric cancer: A significant leap forward

In a recent paper, Hong et al developed an artificial intelligence (AI)-driven predictive scoring system for potential complications following laparoscopic radical gastrectomy for gastric cancer patients. They demonstrated that integrating AI with random forest models significantly improved the preoperative prediction and patient outcome management accuracy. By incorporating data from multiple centers, their model ensures standardization, reliability, and broad applicability, distinguishing it from the prior models. The present study highlights AI's potential in clinical decision support, aiding in the preoperative and postoperative management of gastric cancer patients. Our findings may pave the way for future prospective studies to further enhance AI-supported diagnoses in clinical practice.

Analyzing prognosis and comparing predictive scoring systems for mortality of COVID-19 patients with liver cirrhosis: a multicenter retrospective study

Analyzing prognosis and comparing predictive scoring systems for mortality of COVID-19 patients with liver cirrhosis: a multicenter retrospective study

Predictive Value of Neutrophil Extracellular Traps in Neoadjuvant Chemotherapy for Muscle-Invasive Bladder Cancer.

Cisplatin-based chemotherapy is the recommended therapy for muscle-invasive bladder cancer (MIBC). However, the efficacy of MIBC for chemotherapy is only about 40%. Therefore, predictors of therapy response are urgently needed. Neutrophils form neutrophil extracellular traps (NETs), a network structure, and growing evidence indicated that it could be a prognostic and predictive marker in cancer. In MIBC, the predictive role of NETs in chemotherapy resistance is unclear. We used the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression analyses to develop a NETs-associated signature score (NETs-score) for therapeutic response prediction in the discovery cohort (GSE169455). Then the NETs score-based risk stratification was verified in two validation cohorts (Taber et al.'s cohort, our institutional cohort). In the training cohort, high NETs-score was associated with poor chemotherapy response (AUC = 0.781) and reduced recurrence-free survival (RFS) (hazard ratio [HR] = 2.07, 95% confidence interval [CI]: [1.26-3.40], p = 0.003) in MIBC patients. The NETs-score was also demonstrated to be a predictive factor for the efficacy of neoadjuvant chemotherapy in the validation cohort (AUC = 0.731). The accuracy of the NETs-score was superior to other chemotherapy response predictors such as Ba/Sq expression subtype (AUC = 0.711), BRCA2 mutation (AUC = 0.692) and ERCC2 mutation (AUC = 0.548). Furthermore, in our center cohort, the expression level of H3Cit showed a significant difference between the response and no-response group (p = 0.01). Through immunohistochemical validation, NETs was an independent predictor of MIBC neoadjuvant chemotherapy efficacy as determined by the multivariate logistic regression analysis (OR = 5.94, 95% CI: 1.20-45.50, p = 0.045). Patients with high levels of NETs predicted poor response to neoadjuvant chemotherapy. This study was the first to reveal the correlation between the level of NETs in MIBC and the efficacy of chemotherapy, which may provide a theoretical basis regarding NETs inhibitors.

A Predictive Score for Bullying-Related Burnout in Healthcare Professionals: Implications for Organizational Interventions in Indonesia

Introduction: Workplace bullying is a pervasive issue with detrimental effects on the mental health and well-being of healthcare professionals. This study aimed to develop and validate a predictive score for bullying-related burnout among healthcare professionals in Indonesia and explore its implications for organizational interventions. Methods: A cross-sectional study was conducted involving 785 healthcare professionals from various hospitals in Indonesia. Data were collected using self-reported questionnaires, including the Indonesian versions of the Negative Acts Questionnaire-Revised (NAQ-R), the Copenhagen Burnout Inventory (CBI), and the Workplace Bullying Scale (WBS). Sociodemographic and work-related factors were also assessed. Multiple linear regression analysis was used to develop the predictive score, and its performance was evaluated using receiver operating characteristic (ROC) curve analysis. Results: The prevalence of workplace bullying was 32.1%, with verbal bullying being the most common type. Burnout was significantly associated with bullying experiences (p<0.001). The final predictive score included age, gender, profession, years of experience, work hours per week, perceived social support, and exposure to different types of bullying. The score demonstrated good predictive accuracy (AUC=0.88, 95% CI: 0.84-0.90) for identifying individuals at high risk of burnout. Conclusion: This study provides a validated predictive score for bullying-related burnout in Indonesian healthcare professionals. The score can be used to identify high-risk individuals and guide targeted organizational interventions to prevent and mitigate the negative consequences of workplace bullying.

Early Diagnostic Prediction of Infective Endocarditis: Development and Validation of EndoPredict-Dx

Background: Infective endocarditis is a life-threatening disease with diverse clinical presentations, making diagnosis challenging and requiring a range of complementary tests. The level of suspicion, based on clinical judgment, guides decisions regarding the initiation of empirical treatment and the selection of appropriate diagnostic tools. This study aimed to develop and validate the EndoPredict-Dx score for early prediction of infective endocarditis diagnosis. Methods: Patients admitted to a specialized cardiovascular hospital emergency department with suspected infective endocarditis between January 2011 and January 2020 were included. The primary outcome was left-sided infective endocarditis according to the Duke criteria. Logistic regression was used to derive the scoring system, with internal validation performed through bootstrapping. Candidate variables were obtained from the admission medical history, physical examination, and laboratory parameters. Results: Of the 805 individuals with suspected infective endocarditis (median age 56 years (40–73); 58.6% men), 530 confirmed the diagnosis based on the Duke criteria. The EndoPredict-Dx assigned points for male sex, previous endocarditis, petechiae, heart murmur, suspected embolism, symptoms lasting 14 or more days at the time of admission, hemoglobin level ≤ 12 g/dL, leukocyte level ≥ 10 × 109/L, C-reactive protein level ≥ 20 mg/L, and urine red blood cells ≥ 20,000 cells/mL. Patients were divided into three risk groups. The AUROC was 0.78 (95% CI 0.75–0.81) for the derivation cohort and 0.77 for the internal validation. Conclusions: The EndoPredict-Dx score accurately predicted the likelihood of infective endocarditis using clinical and laboratory data collected at admission.

A contemporary simple risk score for prediction of severe acute kidney injury after heart transplantation.

The aim of this study was to develop a simple risk score to estimate severe acute kidney injury (AKI) risk based on a large contemporary heart transplantation (HT) cohort. From 1 January 2015 to 31 December 2021, all consecutive HT recipients in our institute were included and analysed for the occurrence of AKI within the first seven postoperative days. Patients transplanted between 2015 and 2019 comprised the derivation cohort, and those transplanted between 2020 and 2021 formed the validation cohort. The primary endpoint was severe AKI (AKI stages 2-3). The impact of severe AKI on 90day mortality was also evaluated. Overall, 430 HT patients were included in the derivation cohort, and 108 were included in the validation cohort. Postoperative AKI occurred in 388 (72%) patients, including 162 (30%) severe AKI. The risk of 90day mortality significantly increased in patients with severe-AKI. Seven independent predictors of severe AKI were found in the derivation cohort, including recipients' body mass index, history of diabetes, anaemia, preoperative inotropes, estimated glomerular filtration rate, cardiopulmonary bypass duration and intraoperative red blood cell transfusion. The occurrence of severe AKI increased gradually from the lowest to the highest of the four risk score groups in the derivation and validation cohort. The scoring prediction model showed a highly acceptable discriminating power for severe-AKI [C statistic: 0.76, 95% confidence interval (CI): 0.71-0.80 for derivation cohort; C statistic: 0.79, 95% CI: 0.71-0.89 for validation cohort]. A contemporary simple risk score based on available variables from patients undergoing HT can accurately discriminate the risk of severe AKI.

Developing a peripheral blood RNA-seq based NETseq ensemble classifier: A potential novel tool for non-invasive detection and treatment response assessment in neuroendocrine tumor patients receiving 177Lu-DOTATATE PRRT.

Neuroendocrine tumors (NETs) are presented with metastases due to delayed diagnosis. We aimed to identify NET-related biomarkers from peripheral blood. The development and validation of a multi-gene NETseq ensemble classifier using peripheral blood RNA-Seq is reported. RNA-Seq was performed on peripheral blood samples from 178 NET patients and 73 healthy donors. Distinguishing gene features were identified from a learning cohort (59 PRRT-naïve GEP-NET patients and 38 healthy donors). Ensemble classifier combining the output of five machine learning algorithms viz. Random Forest (RF), Extreme Gradient Boosting (XGBOOST), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and Logistic Regression (LR) were trained and independently validated in the evaluation cohort (n = 106). The response to PRRT was evaluated in the PRRT cohort (n = 46) and the PRRT response monitoring cohort (n = 16). The response to 177Lu-DOTATATE PRRT was assessed using RECIST 1.1 criteria. The Ensemble classifier trained on 61 gene features, distinguished NET from healthy samples with 100% accuracy in the learning cohort. In an evaluation cohort, the classifier achieved 93% sensitivity (95% CI: 87.8%-98.03%) and 91.4% specificity (95% CI: 82.1%-100%) for PRRT-naïve GEP-NETs (AUROC = 95.4%). The classifier returned >87.5% sensitivity across different tumor characteristics and outperformed serum Chromogranin A sensitivity (χ2 = 21.89, p = 4.161e-6). In the PRRT cohort, RECIST 1.1 responders showed significantly lower NETseq prediction scores after 177Lu-DOTATATE PRRT, in comparison to the non-responders. In an independent response monitoring cohort, paired samples (before PRRT and after 2nd or 3rd cycle of PRRT) were analyzed. The NETseq prediction score significantly decreased in partial responders (p = .002) and marginally reduced in stable disease (p = .068). The NETseq ensemble classifier identified PRRT-naïve GEP-NETs with high accuracy (≥92%) and demonstrated a potential role in early treatment response monitoring in the PRRT setting. This blood-based, non-invasive, multi-analyte molecular method could be developed as a valuable adjunct to conventional methods in the detection and treatment response assessment in NET patients.

Abstract 4140117: A novel risk score predicts the prevalence of left atrial low-voltage areas and rhythm outcome in patients undergoing long-standing persistent atrial fibrillation ablation

Background: Catheter ablation is a most common treatment for atrial fibrillation (AF), but rhythm outcome after AF ablation in long-standing persistent atrial fibrillation (LS-PerAF) is still poor. Left atrial low-voltage areas (LVAs) is associated with poor rhythm outcome after catheter ablation. However, the predictors of LVAs presence have not been fully elucidated in patients with LS-PerAF. Purpose: The purpose of this study was to establish a novel predictive score for the prevalence of LVAs in patients with LS-PerAF ablation. Methods: In total, 109 consecutive patients who underwent initial ablation for LS-PerAF were included. LS-PerAF was defined as AF whose duration was more than 1 year. LVA was defined as areas with bipolar peak-to-peak voltage of < 0.50mV. A clinical risk score was obtained as the total number of independent predictors analyzed by multivariate logistic regression analysis. AF recurrence after the catheter ablation was followed for 24 months. Results: Of 109 patients with LS-PerAF, LVAs existed in 26 (24%) patients. A novel predictive score, named DESK score, consisted of diabetes mellitus (odds ratio [OR] 3.7, [95% confidence interval {CI} 2.2–11], p = 0.02), age ≥ 70 years (OR 3.8, [95% CI 1.4-10], p = 0.007), female sex (3.0 [95% CI 1.04-8.4], p = 0.04), AF duration ≥ 3.7 years (44 months) (OR 3.7, [95% CI 1.3-11], p =0.02). LVAs were more frequently found in patients with a higher DESK score (OR, 3.5 [95% CI, 1.9–6.5], p < 0.001) (Figure 1A). On receiver operating characteristic curve analysis, DESK score was a moderate predictor of LVAs presence (area under the curve, 0.750; Figure 1B). The optimal cut-off of DESK score was 3 points, corresponding to a 38.5% sensitivity, 97.6% specificity, and 83.5% predictive accuracy. Freedom from AF recurrence was significantly lower in patients with DESK score ≥ 3 than in those with DESK score < 3 (10.4% vs. 43.5%, p = 0.008). Conclusions: In patients who underwent LS-PerAF ablation, the DESK score correlated with the prevalence of LVAs, and associated with poor rhythm outcome.

Abstract 4124931: Usefulness of the AHEAD Score for Prediction of All-cause Death in Patients With Acute and Chronic Coronary Syndromes

Background: The AHEAD (A: atrial fibrillation; H: hemoglobin; E: elderly; A: abnormal renal parameters; D: diabetes mellitus) score has been introduced to predict all-cause death (ACD) in patients with heart failure. There is no information available on the utility of this score for the prediction of ACD in patients with coronary artery disease (CAD). Hypothesis: The AHEAD score may provide superior predictive value for ACD compared to the CHADS 2 score, which has been reported to be useful for predicting poor clinical outcomes in patients with acute (ACS) and chronic coronary syndromes (CCS). Methods: This retrospective multicenter cohort study analyzed data of the patients who underwent percutaneous coronary intervention for ACS or CCS between April 2013 and March 2019 using the Clinical Deep Data Accumulation System (CLIDAS) database. The AHEAD score was calculated by assigning 1 point each for atrial fibrillation, hemoglobin <13 mg/dL for men and <12 mg/dL for women, age >70 years, elevated creatinine levels (>130 μmol/L), and diabetes mellitus. The CHADS 2 score was calculated as previously reported. The study endpoint was ACD. Results: In total, 9,033 patients were enrolled (median age, 72 years; 77% male; 3,920 with ACS and 5,113 with CCS). Higher AHEAD or CHADS 2 scores were significantly associated with a higher rate of left main disease or three-vessel disease in both patients with ACS and CCS. In addition, after accounting for multiple variables using Cox multivariate analysis, both the AHEAD (hazard ratio [HR], 1.83 [95% confidence interval, 1.63–2.06] for ACS and 1.66 [1.49–1.85] for CCS) and CHADS 2 scores (HR 1.27 [1.15–1.40] for ACS and 1.23 [1.12–1.35] for CCS) remained significantly associated with ACD. However, receiver operating characteristic curve analysis for predicting ACD revealed that the predictive value of the AHEAD score was significantly higher than that of the CHADS 2 score in both ACS and CCS (Figure). A significant difference was found in the rate of ACD among patients stratified by the AHEAD score in both groups (both P <0.001). Conclusions: The AHEAD score had superior predictive value for ACD compared to the CHADS 2 score in patients with CAD, irrespective of ACS or CCS.

Abstract 4138733: Predictive Value of Serum Vasoactive Intestinal Peptide for Low-Voltage Areas in Atrial Fibrillation

Introduction: Identifying low-voltage areas (LVAs) within left atrium (LA) is crucial for predicting atrial fibrillation (AF) recurrence after pulmonary vein isolation (PVI). Animal studies have shown that the parasympathetic neurotransmitter vasoactive intestinal peptide (VIP) affects atrial electrophysiological remodeling. Hypothesis: Thus, we hypothesized that elevated serum VIP levels might contribute to the development of LVAs and that serum VIP concentrations could serve as a biomarker for LVA presence in AF patients. Aims: The aim of this study is to investigate the relationship between the blood levels of VIP and the presence of LVAs in AF patients with electroanatomical mapping (EAM). Methods: We conducted an observational, prospective cross-sectional study on AF patients undergoing PVI between 2021 and 2023. Blood samples for VIP were collected before atrial septal puncture, and EAM was performed using CARTO 3® before PVI. VIP concentrations were measured using an enzyme-linked immunosorbent assay kit. Patients were divided into two groups based on LVA presence (≥5% or <5%) as determined by EAM. Results: Among the 108 patients, 51 (47%) had LVA. VIP levels were significantly higher in patients with LVA compared to those without (median [interquartile range]: 335.1 [274.1-456.5] pg/mL vs. 247.7 [196.1-294.0] pg/mL, p<0.001). No difference was observed in VIP levels by LVA sites. Multivariate logistic regression identified VIP and sex as independent predictors of LVA (per 50 pg/mL, odds ratio [OR]: 1.44, 95% confidence interval [CI]: 1.13-1.83, p<0.001, OR: 4.67, 95% CI: 1.69-12.89, p=0.002, respectively). Females with high VIP had lower conduction velocity compared to other groups. (low VIP male: 0.9 [0.6-1.0] m/s, high VIP male: 0.9 [0.7-1.1] m/s, low VIP female: 0.8 [0.7-1.0] m/s, high VIP female: 0.7 [0.3-0.8] m/s, p=0.013). Incorporating VIP levels (≥288 pg/mL) into an existing predictive score (age ≥65 years, female, and LA volume index ≥57 mL/m 2 ) significantly improved LVA detection (area under the curve: 0.784 vs. 0.707, p<0.001). Conclusions: Serum VIP levels are higher in patients with LVAs, and VIP is a reliable predictor of LVA presence. Incorporating VIP levels into existing predictive models enhances the power for identifying LVAs in AF patients. Serum VIP measurement could be valuable for detecting LVAs, improving risk stratification, and tailoring strategies in AF management.

Risk prediction score for high spinal block in patients undergoing cesarean delivery: a retrospective cohort study.

High spinal block is a serious complication of spinal anesthesia. However, findings regarding its associated risk factors are inconsistent, and no studies have reported a relevant risk prediction score. We aimed to determine the risk prediction score for high spinal block in patients who were induced spinal anesthesia for cesarean delivery. This retrospective cohort study was conducted at a hospital in Southern Thailand between 2019 and 2020. We recorded demographic characteristics, gestational age (GA), hyperbaric bupivacaine dose, sensory block level, pre- and post-procedure blood pressure, and birth weight. High spinal block was defined as a decrease in pinprick sensation > T4. Risk scores, adjusted odds ratios (OR), and 95% confidence intervals (CI) were determined. Risk scores were derived from the coefficients of the final multivariate logistic regression model. The incidence of high spinal block was 22.4% among the 1003 parturients. Our risk prediction tool for high spinal block had a sensitivity and specificity of 76% and 49%, respectively, and was classified into high (> 21), intermediate (15-21), and low (≤ 14) risk groups. The patient-related predictors were a GA < 35weeks (OR [95% CI]: 2.31 [1.13, 4.71], score of 8), height < 150cm (2.21 [1.11, 4.38], score of 8), and post-pregnancy body mass index > 27.5kg/m2 (2.68 [1.33, 5.41], score of 10). The anesthesia-related predictors were a hyperbaric bupivacaine dose > 11mg (2.56 [1.34, 4.87], score of 9) and induction by a first-year resident (1.48 [1.05, 2.09], score of 4). The surgery-related predictors were previous cesarean delivery in labor (1.83 [1.2, 2.78], score of 6) and elective cesarean delivery (2.53 [1.57, 4.07], score of 9) compared to indication by cephalopelvic disproportion. The incidence of intraoperative hypotension was significantly higher in the high-block group than in the control group (46% vs. 25%, p < 0.001). The combination of patient- and anesthesia-related predictors played an important role in the intermediate- and high-risk groups for high sensory spinal block. Addressing the modifiable risk factors-a GA < 35weeks, an optimal dose of bupivacaine, and the experience level of the spinal block performer-could minimize the risk of high spinal block during cesarean delivery.

Predictive score for diagnosing acute colonic diverticulitis in the emergency department: a retrospective study

BackgroundAcute diverticulitis is commonly misdiagnosed among patients with acute abdominal pain in the emergency department (ED). There are predictive scores that assist in the diagnosis of acute left-sided diverticulitis, but no scoring system is available for diagnosing acute diverticulitis without regard to the affected side. Therefore, developing a predictive score for diagnosing acute diverticulitis that is not limited to the left side will guide physicians in making a diagnosis and increase the appropriateness of computed tomography. This study aimed to establish a predictive score for diagnosing acute diverticulitis.MethodThis single-centre retrospective study included adult patients (≥ 18 years) who presented to the ED with acute abdominal pain. Multivariate logistic regression analysis was used to identify essential factors for diagnosing acute diverticulitis, and the Akaike information criterion was calculated to identify significant predictive factors for diagnosing acute diverticulitis using a clinical scoring system.ResultsOf 424 patients who fulfilled the inclusion criteria, 72 (17%) were diagnosed with acute diverticulitis. The significant factors associated with acute diverticulitis were age ≥ 60 years (adjusted odds ratio (adj.OR) 2.23, 95% confidence interval (CI): 1.20 − 4.14, p = 0.01), duration of abdominal pain ≥ 48 h (adj.OR 2.64, 95% CI: 1.28 − 5.45, p = 0.017), history of a diverticulum (adj.OR 7.77, 95% CI: 3.27 − 18.45, p < 0.001), absence of nausea and vomiting (adj.OR 3.42, 95% CI: 1.65 − 7.10, p < 0.001), absence of anorexia (adj.OR 3.33, 95% CI: 1.34 − 8.33, p = 0.026), absence of tachycardia (adj.OR 3.51, 95% CI: 1.39 − 8.87, p = 0.003), and abdominal guarding (adj.OR 2.99, 95% CI: 1.52 − 5.91, p = 0.002). These predictive factors were converted into predictive scores for diagnosing acute diverticulitis. For the score of ≥ 4, the sensitivity and specificity were 73.24% (95% CI: 0.61–0.83) and 80.40% (95% CI: 0.76–0.84), respectively, and the negative predictive value was 93.71% (95% CI: 0.90–0.96). No significant signs, symptoms, or laboratory findings were associated with complicated diverticulitis.ConclusionPredictive factors for diagnosing acute diverticulitis included age ≥ 60 years, duration of abdominal pain ≥ 48 h, history of a diverticulum, abdominal guarding, and absence of nausea and vomiting, anorexia, and tachycardia. A predictive score ≥ 4 suggested the presence of acute diverticulitis.

Predictors and Predictive Score of In-Hospital Mortality in Diabetic Ketoacidosis: A Retrospective Cohort Study

Background and Objectives: Diabetic ketoacidosis (DKA) is a critical complication of diabetes mellitus (DM). The primary objective of this study was to identify relevant clinical and biochemical predictors and create a predictive score for in-hospital DKA mortality. Materials and Methods: A 6-year retrospective cohort study of adult patients diagnosed with DKA and admitted to Chiang Mai University Hospital, a tertiary care center in Chiang Mai, Thailand, from 1 January 2015 to 31 December 2021, was conducted. Baseline clinical data and laboratory investigations were collected. The primary outcome was in-hospital mortality. Multivariable logistic regression analysis, clustered by type of diabetes, was performed to identify significant predictors. A predictive risk score was created using significant predictive factors identified by multivariable analysis. The results were presented as odds ratios (ORs) and 95% confidence intervals (CIs), with a significant p-value set at &lt;0.05. Results: Ninety-three patients diagnosed with DKA were included in the study. Ten patients died during admission. Significant predictors for in-hospital mortality of DKA included age &gt; 55 years (OR 7.8, p = 0.007), female gender (OR 3.5, p &lt; 0.001), anion gap &gt; 30 mEq/L (OR 2.6, p = 0.003), hemoglobin levels &lt; 10 g/dL (OR 16.9, p &lt; 0.001), and the presence of cardiovascular disease (OR 1.3, p = 0.046). The predictive risk score ranged from 1 to 14 for low risk, and 14.5–23.5 for high risk of in-hospital mortality. The predictive performance of the scoring system was 0.82 based on the area under the curve, with a sensitivity of 73.8% and specificity of 96.4%. Conclusions: Multiple clinical and biochemical factors, along with a predictive risk score, could assist in predicting in-hospital mortality of DKA and serve as a guide for physicians to identify patients at high risk. Nevertheless, as the predictive score was internally validated with data from a single institution, external validation in diverse healthcare settings with larger datasets or prospective cohorts is crucial to confirm the model’s generalizability and predictive accuracy.

Early Viral Dynamics Predict HIV Post-Treatment Control After Analytic Treatment Interruption.

A key research priority for developing an HIV cure strategy is to define the viral dynamics and biomarkers associated with sustained post-treatment control. The ability to predict the likelihood of sustained post-treatment control or non-control could minimize the time off antiretroviral therapy (ART) for those destined to not control and anticipate longer periods off ART for those destined to control. Mathematical modeling and machine learning were used to characterize virologic predictors of long-term virologic control using viral kinetics data from several studies in which participants interrupted ART. Predictors of post-ART outcomes were characterized using data accumulated from the time of treatment interruption, replicating real-time data collection in a clinical study, and classifying outcomes as either post-treatment control (plasma viremia ≤400 copies/mL at 2 of 3 time points for ≥24 weeks) or non-control. Potential predictors of virologic control were the time to rebound, the rate of initial rebound, and the peak plasma viremia. We found that people destined to be non-controllers could be identified within 3 weeks of rebound (prediction scores: accuracy, 80%; sensitivity, 82%; specificity, 71%). Given the widespread use of analytic treatment interruption in cure-related trials, these predictors may be useful to increase the safety of analytic treatment interruption through the early identification of people who are unlikely to become post-treatment controllers.

Comparison of Injury Severity Score, New Injury Severity Score, Revised Trauma Score, and Trauma and Injury Severity Score for Mortality Prediction in Trauma Patients in a Tertiary Care Center

Comparison of Injury Severity Score, New Injury Severity Score, Revised Trauma Score, and Trauma and Injury Severity Score for Mortality Prediction in Trauma Patients in a Tertiary Care Center

Prognostic Implications of Initial Radiological Findings of Pulmonary Fibrosis in Patients with Acute SARS-CoV-2 Infection: A Prospective Multicentric Study

Pulmonary fibrosis detected during the acute phase of SARS-CoV-2 infection may significantly influence patient prognosis. This study aimed to evaluate the prognostic value of initial high-resolution computed tomography (HRCT) findings of pulmonary fibrosis in hospitalized COVID-19 patients and to examine how these findings relate to disease severity and clinical outcomes, with a particular focus on the development and validation of predictive scoring systems. In this multicentric prospective cohort study from January 2023 to January 2024, 120 adult patients with confirmed SARS-CoV-2 infection requiring hospitalization were enrolled from two Romanian university hospitals. Patients were categorized based on the presence (n = 60) or absence (n = 60) of pulmonary fibrosis signs on admission HRCT scans, identified by reticular opacities, traction bronchiectasis, honeycombing, and architectural distortion. Biochemical analyses, severity scores (SOFA, APACHE II, NEWS 2), and novel compound scores combining clinical and radiological data were assessed. Patients with HRCT evidence of pulmonary fibrosis had significantly higher severity scores and worse clinical outcomes. The HRCT score alone was a strong predictor of severe COVID-19 (area under the ROC curve [AUC] = 0.885), with a best cutoff value of 9.72, yielding 85.7% sensitivity and 79.8% specificity. Compound Score 1, integrating SOFA, APACHE II, and HRCT scores, demonstrated excellent predictive performance with an AUC of 0.947, sensitivity of 92.5%, and specificity of 88.9%. Compound Score 2, combining systemic inflammation markers (SIRI, SII) and NEWS 2, also showed a strong predictive capability (AUC = 0.913), with 89.2% sensitivity and 85.7% specificity at the optimal cutoff. Regression analysis revealed that Compound Score 1 had the highest hazard ratio for severe COVID-19 outcomes (HR = 4.89; 95% CI: 3.40–7.05), indicating its superior prognostic value over individual markers and traditional severity scores. Initial HRCT findings of pulmonary fibrosis are significantly associated with increased disease severity in hospitalized COVID-19 patients. The HRCT score is a valuable prognostic tool, and, when combined with clinical severity scores into Compound Score 1, it enhances the prediction of severe COVID-19 outcomes with high sensitivity and specificity. These compound scores facilitate the early identification of high-risk patients, guiding clinical decision-making and optimizing patient management to improve outcomes.

Development and validation of a predictive scoring model for complications following endoscopic endonasal skull base surgery.

The endoscopic endonasal approach (EEA) has evolved into an established technique in skull base surgery. The authors previously examined 1002 EEA procedures and reported factors associated with postoperative complications. Here they report the development and validation of a scoring model based on risk factors to better predict complications following EEA. The authors developed an optimized EEA scoring model for predicting postoperative complications as evidenced by the area under the receiver operating characteristic (AUROC) curve using their previously published data in addition to data collected from the subsequent 292 EEA procedures from years 2010-2020. The model was built systematically by evaluating the contributions that different variables had on the overall predictive ability of the model. The aim was to design a model containing as few variables as possible for practicality and to facilitate calculation and use at the bedside. The Clavien-Dindo grading system was used to classify complications into grades I-V based on the level of intervention that was required to manage the complication, with grades III-V considered to be higher-grade (i.e., those requiring reoperation or ICU-level care or death). The authors identified 1294 EEA operations performed between July 2010 and July 2020 that met their inclusion criteria. Higher-grade complications were identified following 135 EEA operations. The variables that were ultimately included in the model were age, BMI, operative time, meningioma, chordoma, expanded intradural approach, and nasoseptal flap use. The final model yielded an acceptable AUROC curve of 0.72 and predicted a stepwise increase in the rate of higher-grade complications as the score increased. A score of 0-2 (low) on the grading system was associated with an average complication rate of 5.1%. A score of 3-5 (medium) was associated with an average complication rate of 12.6%. A score of 6 or above (high) was associated with an average complication rate of 26%. This EEA complications scoring model accurately categorizes patients into low-, medium-, and high-risk groups with readily obtained variables. A high score in this complications model does not suggest that a patient is ineligible for surgery, but rather highlights the importance of thorough case selection, operating with caution, and appropriate preoperative counseling.

Development and validation of the prediction score for augmented renal clearance in critically Ill Japanese adults.

Augmented renal clearance (ARC) decreases the therapeutic concentration of drugs excreted by the kidneys in critically ill patients. Several ARC prediction models have been developed and validated; however, their usefulness in Japan has not been comprehensively investigated. Thus, we developed a unique ARC prediction model for a Japanese mixed intensive care unit (ICU) population and compared it with existing models. This retrospective study enrolled a mixed ICU population in Japan from January 2019 and June 2022. The primary outcome was the development and validation of a model to predict ARC onset based on baseline information at ICU admission. Patients admitted until May 2021 were included in the training set, and external validation was performed on patients admitted thereafter. A multivariate logistic regression model was used to develop an integer-based predictive scoring system for ARC. The new model (the JPNARC score) was externally validated along with the ARC and Augmented Renal Clearance in Trauma Intensive Care (ARCTIC) scores. A total of 2,592 critically ill patients were enrolled initially, with 651 patients finally included after excluding 1,941 patients. The training and validation datasets comprised 456 and 195 patients, respectively. Multivariate analysis was performed to develop the JPNARC score, which incorporated age, sex, serum creatinine, and diagnosis upon ICU admission (trauma or central nervous system disease). The JPNARC score had a larger area under the receiver operating characteristic curve than the ARC and ARCTIC scores in the validation dataset (0.832, 0.633, and 0.740, respectively). An integer-based scoring system was developed to predict ARC onset in a critically ill Japanese population and showed high predictive performance. New models designed to predict the often-unrecognized ARC phenomenon may aid in the decision-making process for upward drug dosage modifications, especially in resource- and labor-limited settings.

Reply to "Development of risk scores for prognosis prediction among patients with early-stage hepatocellular carcinoma".

Reply to "Development of risk scores for prognosis prediction among patients with early-stage hepatocellular carcinoma".

Leveraging calcium score CT radiomics for heart failure risk prediction.

Studies have used extensive clinical information to predict time-to-heart failure (HF) in patients with and without diabetes mellitus (DM). We aimed to determine a screening method using only computed tomography calcium scoring (CTCS) to assess HF risk. We analyzed CTCS scans from 1,998 patients (336 with type 2 diabetes) from a no-charge coronary artery calcium score registry (CLARIFY Study, Clinicaltrials.gov NCT04075162). We used deep learning to segment epicardial adipose tissue (EAT) and engineered radiomic features of calcifications ("calcium-omics") and EAT ("fat-omics"). We developed models incorporating radiomics to predict risk of incident HF in patients with and without type 2 diabetes. At a median follow-up of 1.7 years, 5% had incident HF. In the overall cohort, fat-omics (C-index: 77.3) outperformed models using clinical factors, EAT volume, Agatston score, calcium-omics, and calcium-and-fat-omics to predict HF. For DM patients, the calcium-omics model (C-index: 81.8) outperformed other models. In conclusion, CTCS-based models combining calcium and fat-omics can predict incident HF, outperforming prediction scores based on clinical factors.Please check article title if captured correctly.YesPlease check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary.Yes.