Validation Group Research Articles

Development and validation of a nomogram for predicting early neurological deterioration in patients with moderate traumatic brain injury: a retrospective analysis

ObjectiveEarly neurological deterioration (END) greatly affects prognosis of moderate traumatic brain injury (TBI). This study aimed to develop and validate a nomogram to predict the occurrence of END in patients with moderate TBI.MethodsA total of 371 patients with moderate TBI were enrolled and divided into the training (n = 260) and validation (n = 111) groups at a ratio of 7:3. Univariate and multivariate logistic regression analyses were used to identify the significant factors for END, which were used to develop a nomogram. The discrimination of the nomogram was evaluated using area under the receiver operating characteristic curves (AUC), the calibration was evaluated using calibration curves and Hosmer-Lemeshow tests. Decision curve analysis (DCA) was used to evaluate the net benefit of the model for patients.ResultsIn the training group, multivariate logistic regression demonstrated that GCS score, epidural hematoma, intracerebral hemorrhage, fibrinogen, and D-dimer were independent risk factors for END in patients with moderate TBI. A nomogram was constructed using the logistic regression prediction model. The AUCs of the nomogram in the training and validation groups were 0.901 and 0.927, respectively. The calibration curves showed that the predicted probability was consistent with the actual situation in both the training and validation sets. DCA curves demonstrated significantly better net benefit with the model. Then a web-based calculator was generated to facilitate clinical application.ConclusionThe present study developed and validated a model to predict END in patients with moderate TBI. The nomogram that had good discrimination, calibration, and clinical utility can provide clinicians with an effective and accurate tool for evaluating the occurrence of END after moderate TBI.

Clinicopathologic predictors of renal response and survival in newly diagnosed multiple myeloma with renal injury: a retrospective study.

Renal impairment (RI) is a common complication of multiple myeloma (MM), which is associated with poor prognosis. Here, we revealed the association between regular examination data and RIincidence, RI response and survival in newly diagnosed multiple myeloma (NDMM) patients. A retrospective analysis was conducted on the initial clinical data of 647 NDMM patients, comprising 193 patients (29.83%, 193/647) with RI and 454 (70.17%, 454/647) without RI at diagnosis. Logistic regression analyses, both univariate and multivariate, were performed to identify the independent influencing factors of RI with bootstrap techniques and resampling. The model used to predict the RI response was established using the support vector machine-recursive feature elimination (SVM-RFE) machine learning algorithms. Six variables identified by multi-factorial logistic regression analysis were independently associated with the incidence of RI, including the secreted monoclonal immunoglobulin of IgG type (33.16% vs. 52.64%), deregulated serum free κ/λ light chain (58.12% vs. 33.93%), elevated serum calcium (> 2.65 mmol/L, 31.61% vs. 11.01%), elevated urea (≥ 8.3 mmol/L, 92.23% vs. 20.26%), elevated uric acid (≥ 340 μmol/L, 74.61% vs. 35.46%), and ISS (International Staging System) stage of III (90.16% vs. 31.50%). The lactate dehydrogenase (≥ 250 U/L; HR = 1.786, P = 0.005) and CKD (chronic kidney disease) stage (G4-G5; HR = 5.830, P = 0.016) were the independent adverse factors of the overall survival of NDMM patients with RI. In addition, this study provided a model to predict the response of RI using 5 clinical features, including calcium, Durie-Salmon (DS) stage, creatinine level before treatment, age and gender. The sensitivity, specificity, area under the curve (AUC) and accuracy were 86.75%, 51.15%, 78.30% and 72.99% in the training group, while 79.31%, 52.94%, 72.40% and 69.57% in the validation group. In conclusion, this study clarified the relationship between clinicopathologic characteristics and the incidence of renal injury, response and survival of NDMM patients, supporting clinical decision-making, and offering significant clinical application value.

Development and validation of a nomogram to predict recurrence in epithelial ovarian cancer using complete blood count and lipid profiles

ObjectiveOvarian cancer is one of the most lethal gynecological malignancies. This study aimed to evaluate the prognostic significance of complete blood count (CBC) and lipid profile in patients with optimally debulked epithelial ovarian cancer (EOC) and develop a nomogram model to predict recurrence-free survival (RFS).MethodsThis retrospective study analyzed patients diagnosed with EOC between January 2018 and June 2022.ResultsA total of 307 patients were randomly divided into training and validation sets in a ratio of 7:3. Grade, International Federation of Gynecology and Obstetrics (FIGO) stage, platelet-to-lymphocyte ratio, red blood cell distribution width-coefficient of variation, triglycerides, and human epididymal protein 4 were identified as independent prognostic factors. The novel nomogram displayed a good predictive performance, with a concordance index (C-index) of 0.787 in the training group and 0.807 in the validation group. The areas under the curve for 1-, 3-, and 5-year RFS were 0.770, 0.881, and 0.904, respectively, in the training group, and 0.667, 0.906, and 0.886, respectively, in the validation group. The calibration curves exhibited good concordance between the predicted survival probabilities and actual observations. Time-dependent C-index curves, integrated discrimination improvement, net reclassification index, and decision curve analysis showed that the nomogram outperformed FIGO staging.ConclusionThis study established and validated a nomogram combining CBC and lipid profiles to predict RFS in patients with optimally debulked EOC, which is expected to aid gynecologists in individualized prognosis assessment and clinical management.

The Combined Prognostic Value of 18F-FDG PET/CT Metabolic Parameters of Immune Organs and Hematological Immune-Related Markers in Patients With Locally Advanced Cervical Cancer.

This study aimed to explore the prognostic value of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) metabolic parameters of immune organs and hematological immune-related markers for patients with locally advanced cervical cancer (LACC) undergoing concurrent chemoradiotherapy (CCRT), and to establish prognostic nomograms based on these potential biomarkers. A total of 180 patients with LACC undergoing CCRT were retrospectively reviewed and randomly divided into training and validation groups at a 7:3 ratio. Cox regression analysis was performed to identify independent prognostic factors for progression-free survival (PFS) and overall survival (OS) from hematological immune-related markers and 18F-FDG PET/CT metabolic parameters of the primary tumor, spleen, and bone marrow (BM). Nomograms were developed and evaluated using receiver operating characteristic curves, concordance index (C-index), calibration curves, and decision curve analysis (DCA). Spearman correlation analysis was used to assess the relationships among metabolic parameters. Multivariable analysis identified International Federation of Gynecology and Obstetrics (FIGO) stage, neutrophil-to-lymphocyte ratio (NLR), and spleen maximum standardized uptake value (SUVspleen) as independent prognostic factors for PFS. For OS, the independent prognostic factors were FIGO stage, NLR, metabolic tumor volume, and SUVspleen. The nomograms demonstrated better prognostic performance for PFS (area under curve [AUC]: 0.875 and 0.862; C-index: 0.809 and 0.775) and OS (AUC: 0.858 and 0.814; C-index: 0.828 and 0.792) in the training and validation groups. Calibration curves and DCA indicated that the nomograms have good predictive accuracy and clinical utility. Spearman correlation analysis revealed significant positive correlations among total lesion glycolysis, SUVspleen, SUVBM, and platelet-to-lymphocyte ratio. The nomograms based on metabolic parameters of immune organs and hematological immune-related markers demonstrated high predictive value for patients with LACC undergoing CCRT. The observed correlations between the metabolic parameters of the primary tumor and immune organs suggest a widespread disturbance of systemic immunity caused by the tumor.

A novel 2-2 5-5 model for stratifying liver metastasis burden in patients with pancreatic cancer.

711 Background: In metastatic pancreatic cancer (MPC), hepatic metastasis is uniformly counted as just ‘one organ metastasis’ regardless of its metastatic tumor burden. This study aims to develop a novel stratification system for liver metastasis based on tumor burden, and to evaluate its prognostic significance in MPC patients. Methods: Patients with MPC treated at Seoul National University Bundang Hospital from 2011 to 2021 were included as the training cohort. Patients with liver-only metastasis were selected for analysis. Liver metastasis burden was categorized by the number and maximum diameter of metastases as measured from diagnostic CT images. Optimal cutoffs for metastasis number and size were determined using Cox proportional hazards regression, adjusted for chemotherapy regimen. An independent cohort from Seoul St. Mary’s Hospital and Hallym University Sacred Heart Hospital served as the validation group. The ‘H category classification’ suggested by the Japanese Society for Cancer of the Colon and Rectum (JSCCR) was also referenced. Results: A total of 1,257 patients were included, with 1,084 in the training cohort and 173 in the validation cohort. In the training cohort, data from 311 patients with liver-only metastasis were analyzed to derive the Two-two five-five (‘2-2 5-5’) criteria, classifying metastasis into Oligo-metastasis (≤2 metastases and ≤2 cm), Meso-metastasis (non-oligo and non-mega), and Mega-metastasis (≥5 metastases or ≥5 cm). Median overall survival (OS) significantly differed between the groups: Oligo (11.4 months), Meso (9.2 months, HR 1.66, 95% CI 1.14–2.43), Mega (5.6 months, HR 2.63, 95% CI 1.94–3.58) in the training cohort; Oligo (5.8 months) vs Mega (1.81 months, HR 1.94, 95% CI 1.16–3.22) in the validation cohort. Conclusions: This 2-2 5-5 model effectively stratifies MPC patients with hepatic metastasis into three prognostic groups, demonstrating significant survival differences in both training and validation cohorts. This could rationalize the independent therapeutic strategies by extent of hepatic metastasis. Demographic characteristics of patients classified according to “two-two five-five” criteria. Oligo-metastasis(n = 88) Meso-metastasis(n = 59) Mega-metastasis(n = 164) Total(n = 311) P-value* Age, median (range) 66.0 (33.2-91.0) 67.1(37.2-86.9) 68.7 (40.1-94.6) 67.9 (33.2-94.6) 0.587 Male, n (%) 43 (48) 36 (61) 91 (55) 170 (54) 0.330 Tumor location(Head), n(%) 47 (53) 27 (45) 60 (36) 134 (43) <0.05 Number of liver metastasis, median (range) 1 (1-2) 3 (1-4) 12 (2-14) 5 (1-14) <0.05 Maximal size of liver metastasis, cm (IQR)Average size of liver metastasis, cm (IQR) 10.6 (8.1-13.1)10.3 (8.0-12.1) 15.9 (10.1-24.2)13.5 (7.8-19.1) 21.6 (16.8-33.7)13.2 (10.5-19.2) 17.2 (10.9-25.2)11.9 (9.2-17.1) <0.05<0.05 CA19-9 (U/mL) 462 (103-1,334) 560 (89-1,480) 1,170 (100-9,500) 745 (100-3,700) <0.05

Development and Validation of Parental Self-Efficacy Scale for Dietary Management of Children with Food Allergies.

It is necessary to evaluate the parental ability to achieve nutritional adequacy while avoiding allergens for children with food allergies (FA), yet this area is currently understudies. Our study aimed to develop and validate the Parental Self-Efficacy Scale for Dietary Management of Children with Food Allergies (PSED-FA). PSED-FA was developed through a literature review and semi-structured interviews refined by a panel of five allergists and five dietitians, and validated using responses from caregivers of children with FA. The construction of the tool involved exploratory factor analysis (EFA), confirmatory factor analysis for model fit, and evaluation of internal consistency using Cronbach's alpha. Convergent and divergent validity were assessed using the average variance extracted (AVE), maximum shared variance (MSV), and average shared variance (ASV). Participants included nine focus interview groups, with 114 individuals in the validation group. Egg whites (55.2%), tree nuts (35.2%), and peanuts (22.8%) were the most common allergens. The EFA identified three factors: preparing allergen-free meals, knowledge of nutrition management, and management of food restrictions. The goodness of fit of our model met all the criteria. The tool showed high internal consistency (overall Cronbach's alpha: 0.902) and met the criteria for both convergent (AVE >0.5) and divergent validity (AVE > MSV and ASV). This study validated a reliable and effective tool for assessing parental self-efficacy in managing the dietary needs of children with FA. This tool can aid health professionals in evaluating parental confidence and identifying areas for improving dietary management in children with FA.

Whole exome sequencing-based homologous recombination deficiency test for epithelial ovarian cancer.

The homologous recombination deficiency (HRD) test is an important tool for identifying patients with epithelial ovarian cancer (EOC) benefit from the treatment with poly(adenosine diphosphate-ribose) polymerase inhibitor (PARPi). Using whole exome sequencing (WES)-based platform can provide information of gene mutations and HRD score; however, the clinical value of WES-based HRD test was less validated in EOC. We enrolled 40 patients with EOC in the training cohort and 23 in the validation cohort. The WES-based HRD score was calculated using the scarHRD software. We first evaluated the concordance of the HRD status defined by the Myriad MyChoice CDx and then assessed the value of HRD on clinical prognosis in patients with EOC. The HRD score defined by the WES-based test was positively correlated with that of the Myriad MyChoice® CDx test (r = 0.82, p < 0.01) in the training cohort. In compared to HRD status of Myriad test, the sensitivity, specificity, positive predictive value, and negative predictive value of the WES-based HRD test were 93.5% (29/31), 77.8% (7/9), 93.5% (29/31), and 77.8% (7/9), respectively. Patients with positive HRD status defined by WES-based scarHRD test and Myriad MyChoice® CDx test were both highly associated with platinum sensitive response (both Fisher's exact test, p = 0.002) as well as the superior progression-free survival (both log-rank p = 0.002). The multi-variate Cox regression model incorporated with optimal debulking surgery showed that the recurrence risk was decreased in the patients with positive HRD status, either defined by Myriad MyChoice® CDx test (Hazard ratio (HR) 0.33, 95% confidence interval (CI) 0.14-0.79, p = 0.013) or WES-based test Myriad MyChoice® CDx test (HR 0.34, 95% CI 0.14-0.80, p = 0.014). Nine patients had mutations in the genes involved in HR DNA repair, and all of them were positive for HRD. In the validation group, 23 patients were defined as positive HRD by WES-based testing. Six positive HRD patients and 5 negative HRD patients received maintenance PARPi. The median responsive interval of PARPi was 17 months in positive HRD patients and 3 months in negative HRD patients. The WES-based test is a potential option for determining the HRD status in EOC patients, and desires for further validation in large-scale cohorts.

A risk prediction model for adult patients with difficult intravenous access.

The challenges posed by difficult intravenous access (DIVA) in clinical treatment are not only related to technical difficulties but also have the potential to affect the quality of patient care and overall experience. It is crucial to adopt effective strategies to address difficult intravenous access. Currently, the assessment of difficult veins largely relies on individual perception and experience, which introduces a significant degree of subjectivity. To develop and validate a risk prediction model for DIVA in adult patients, providing a tool for early identification and intervention. An observational study. Retrospective data collection was conducted on 1170 hospitalized patients who required the placement of a short peripheral venous catheter for treatment in a tertiary hospital from June 1, 2022, to September 30, 2022, as the training set. Logistic regression analysis was employed to identify factors influencing DIVA in adult patients and to construct a risk prediction model. Prospective data collection was conducted on 300 hospitalized patients from June 1, 2023, to June 30, 2023, for external validation. The discriminative ability, calibration, and clinical utility of the model were evaluated using the area under the receiver operating characteristic curve, calibration curve, and clinical decision curve, respectively. A TRIPOD checklist was used to guide the reporting of this study. The average age of patients in the training set was 58.60 ± 15.39 years. Among them, 626 were males (53.50%) and 544 were females (46.50%). The external validation group included a total of 300 patients with a mean age of 58.77 ± 15.26 years. There were 142 males (47.33%) and 158 females (52.67%). Advanced age, female sex, extreme weight (BMI <18.5 or >30), history of hemodialysis, axillary lymph node dissection for breast cancer, compromised skin integrity, history of DIVA, and target cannula size ⩽20G are independent predictive factors for DIVA in adult patients (all p < 0.05). The risk prediction model constructed based on these factors had an area under the ROC curve of 0.912 (95% CI 0.880-0.943) in the modeling group. The areas under the ROC curve in the internal and external validation groups were 0.887 (95% CI 0.855-0.924) and 0.870 (95% CI 0.799-0.942), respectively. Calibration curves showed good agreement between predicted and observed probabilities. Decision curve analysis demonstrated that intervening when the risk of venous puncture difficulty ranged from 3% to 91% yielded favorable clinical benefits for patients. Constructing a risk prediction model for DIVA in adult patients has significant predictive value. It assists medical staff in early intervention and management for high-risk patients, thereby achieving effective prediction, warning, and control.

P-2239. RNA Signatures for Diagnosing or Predicting Febrile Illness: A Descriptive Analysis

Abstract Background Fever is a common sign of illness; it may self-resolve or be present in serious illnesses requiring hospitalization. Investigating the cause of fever can be extremely resource intensive requiring multiple diagnostic tests and healthcare providers thereby delaying time to diagnosis. RNA molecules present in the blood can be easily detected and reflect a patient’s disease state, making them ideal biomarkers. Our objective was to identify RNA common to signatures that diagnose and predict the outcome of febrile illnesses. Our secondary objectives were to assess whether signatures are being validated and translated. Methods We conducted a scoping review of published research articles, including preprints, from EMBASE and Medline that measured blood RNA in patients with febrile illness. Here we are analyzing a articles that used array or RNA-seq to generate original signatures. Results We identified 248 original blood RNA signatures for the diagnosis or prognosis of febrile illness. 154 were diagnostic, 56 prognostic, 15 diagnostic/prognostic and 23 exploratory. The most common illnesses studied were sepsis (n=83), viral infections (n=74) and tuberculosis (n=38). From all sepsis signatures there were 214 unique RNA and 74 RNA present in multiple signatures. The most common RNA, C3AR1 (complement receptor) and MPO (myeloperoxidase), appeared in 5 signatures. For viral infections there were 54 signatures, and IFI27 (interferon) appeared in 8 signatures. For tuberculosis there were 26 signatures, and the most common RNA were BATF2 (transcription factor) and FCGR1B (Fc receptor) each appearing in 4 signatures. 158/248 signatures were validated. Clinical sensitivity and specificity in validation groups were 54-100% and 79-97%, respectively. 9/248 studies claimed that they had filed or were filing for a patent. Conclusion Blood RNA molecules can be used for the diagnosis and prognosis of febrile illnesses. Currently, &amp;lt; 65% of RNA signatures are validated and &amp;lt; 5% of signatures are commercialized. In conducting this analysis, we encountered a lack of standardization in methods reporting. Further work to improve transparency and encourage validation is needed so RNA signatures can be adapted into simple, molecular diagnostic tests and translated for patient use. Disclosures Shaun Morris, MD, MPH, DTM&amp;H, FRCPC, FAAP, GSK Canada: Advisor/Consultant|GSK Canada: Honoraria|Pfizer: Advisor/Consultant|Pfizer: Honoraria|Sanofi Canada: Advisor/Consultant|Sanofi Canada: Honoraria

Development and validation of a risk prediction model for early postoperative high intraocular pressure after implantation of posterior chamber intraocular lens

Objective: To develop and validate a predictive model for assessing the risk of early postoperative high intraocular pressure (HIOP) following posterior chamber intraocular lens implantation. Methods: The clinical data of patients who underwent posterior chamber intraocular lens implantation at the Second Affiliated Hospital of Zhejiang University School of Medicine between May 2023 and April 2024 were retrospectively reviewed. Patients were divided into a modeling group and a validation group with a 7∶3 ratio using computerized random allocation. The modeling group was further categorized into normal intraocular pressure and HIOP groups based on the occurrence of early postoperative HIOP. Multivariate logistic regression analysis was employed to establish a risk prediction model. Receiver operating characteristic (ROC) curve analysis was conducted using R software to assess the predictive ability and accuracy of the model, along with calibration and decision curve analysis (DCA) curve plotting. Results: A total of 239 patients (478 eyes) were enrolled. The modeling group consisted of 168 patients (82 males and 86 females) (336 eyes), with an average age of (25.5±5.1) years. The validation group consisted of 71 patients (36 males and 35 females) (142 eyes), with an average age of (24.7±5.7) years. The early postoperative HIOP incidence rate after posterior chamber intraocular lens implantation was 32.4% (109/336), while it was 26.8% (38/142) in the validation group. The multivariate logistic regression analysis indicated that preoperative refractive diopter (OR=0.873, 95%CI: 0.782-0.976, P=0.017), corneal endothelial cell count (OR=0.996, 95%CI: 0.995-0.997, P<0.001), corneal thickness (OR=1.015, 95%CI: 1.006-1.024, P=0.001), and preoperative intraocular pressure (OR=1.470, 95%CI: 1.283-1.686, P<0.001) were associated factors for early HIOP. The Hosmer-Lemeshow test showed that the χ2 value was 8.444 (P=0.391), and the area under the ROC curve (AUC) was 0.888 (95%CI: 0.852-0.925). The Youden index reached its maximum value of 0.646, with a sensitivity of 0.862 and specificity of 0.784. AUC of validation group was 0.921 (95%CI: 0.870-0.972), with a maximum Youden index of 0.765, sensitivity of 0.842 and specificity of 0.923. Conclusions: The risk prediction model constructed based on preoperative refractive diopter, corneal endothelial cell count, corneal thickness, and preoperative intraocular pressure demonstrates good predictive performance for early postoperative HIOP following posterior chamber intraocular lens implantation.

Machine Learning-Based Real-Time Survival Prediction for Gastric Neuroendocrine Carcinoma.

This study aimed to develop a dynamic survival prediction model utilizing conditional survival (CS) analysis and machine learning techniques for gastric neuroendocrine carcinomas (GNECs). Data from the Surveillance, Epidemiology, and End Results (SEER) database (2004-2015) were analyzed and split into training and validation groups (7:3 ratio). CS profiles for patients with GNEC were examined in the full cohort. We utilized random survival forests (RSFs) and least absolute shrinkage and selection operator (LASSO) regression, alongside stepwise Cox regression, for variable selection. A CS-based nomogram was developed on the basis of key prognostic factors, followed by risk stratification and model validation. We included 654 patients with GNEC in our study, with 457 assigned to the training set and 197 to the validation set. The CS analysis demonstrated that the probability of achieving 5-year CS improved from 48% immediately after diagnosis to 68%, 81%, 88%, and 94% after surviving an additional year (i.e., at 1, 2, 3, and 4 years, respectively). Through the use of RSFs and LASSO regression, combined with multivariable regression analysis, we identified the optimal combination of prognostic factors, which included age, tumor grade, tumor stage, surgery, and chemotherapy. Utilizing these prognostic indicators, we successfully developed a nomogram model that incorporated CS and effectively stratified these patients by risk. Subsequent performance analyses further validated the superior efficacy of the nomogram. Our study highlights the value of CS in GNEC prognosis. The nomogram offers dynamic, individualized survival predictions, supporting personalized treatment strategies.

Establishing of a risk prediction model for metabolic dysfunction-associated steatotic liver disease: a retrospective cohort study

ObjectivesOver 30% of people worldwide suffer from metabolic dysfunction-associated steatotic liver disease (MASLD), a significant global health issue. Identifying and preventing high-risk individuals for MASLD early is crucial. The purpose of our study is to investigate the factors related to the development of MASLD and develop a risk prediction model for its occurrence.MethodsThe study included 5107 subjects, divided into training and validation groups in a 7:3 ratio using a random number table method. Collinearity diagnosis and Cox regression were used to identify factors associated with MASLD incidence, and a risk prediction model was created. The model’s accuracy, reliability, and clinical applicability were assessed.ResultsOur study indicated that male, body mass index (BMI), low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), fasting plasma glucose (FPG), serum uric acid to creatinine ratio (SUA/Cr) and white blood cell (WBC) were associated with MASLD incidence. The elements were determined to be crucial for creating a risk prediction model. The model showed strong discriminative potential with a C-index of 0.783 and the time-dependent AUCs of 0.781, 0.789, 0.814 and 0.796 for 1–4 years in the training group, and a C-index of 0.788 and the time-dependent AUCs of 0.798, 0.782, 0.787 and 0.825 for 1–4 years in validation. Calibration curves confirmed the model’s accuracy, and decision curve analysis (DCA) validated its clinical utility.ConclusionsThe model may provide clinical physicians with a reliable method for identifying high-risk populations for MASLD and serve as a guide for developing prediction models for other diseases.

Development and validation of a prediction model of hospital mortality for patients with cardiac arrest survived 24 hours after cardiopulmonary resuscitation

ObjectiveResearch on predictive models for hospital mortality in patients who have survived 24 h following cardiopulmonary resuscitation (CPR) is limited. We aim to explore the factors associated with hospital mortality in these patients and develop a predictive model to aid clinical decision-making and enhance the survival rates of patients post-resuscitation.MethodsWe sourced the data from a retrospective study within the Dryad dataset, dividing patients who suffered cardiac arrest following CPR into a training set and a validation set at a 7:3 ratio. We identified variables linked to hospital mortality in the training set using Least Absolute Shrinkage and Selection Operator (LASSO) regression, as well as univariate and multivariate logistic analyses. Utilizing these variables, we developed a prognostic nomogram for predicting mortality post-CPR. Calibration curves, the area under receiver operating curves (ROC), decision curve analysis (DCA), and clinical impact curve were used to assess the discriminability, accuracy, and clinical utility of the nomogram.ResultsThe study population comprised 374 patients, with 262 allocated to the training group and 112 to the validation group. Of these, 213 patients were dead in the hospital. Multivariate logistic analysis revealed age (OR 1.05, 95% CI: 1.03–1.08), witnessed arrest (OR 0.28, 95% CI: 0.11–0.73), time to return of spontaneous circulation (ROSC) (OR 1.05, 95% CI: 1.02–1.08), non-shockable rhythm (OR 3.41, 95% CI: 1.61–7.18), alkaline phosphatase (OR 1.01, 95% CI: 1–1.01), and sequential organ failure assessment (SOFA) (OR 1.27, 95% CI: 1.15–1.4) were independent risk factors for hospital mortality for patients who survived 24 h after CPR. ROC of the nomogram showed the AUC in the training and validation group was 0.827 and 0.817, respectively. Calibration curves, DCA, and clinical impact curve demonstrated the nomogram with good accuracy and clinical utility.ConclusionOur prediction model had accurate predictive value for hospital mortality in patients who survived 24 h after CPR, which will be beneficial for assisting in identifying high-risk patients and intervention. Further confirmation of the model's accuracy required external validation data.

An MRI radiomics model for predicting a prostate-specific antigen response following abiraterone treatment in patients with metastatic castration-resistant prostate cancer

ObjectiveTo establish a combined radiomics-clinical model for the early prediction of a prostate-specific antigen(PSA) response in patients with metastatic castration-resistant prostate cancer(mCRPC) after treatment with abiraterone acetate(AA).MethodsThe data of a total of 60 mCRPC patients from two hospitals were retrospectively analyzed and randomized into a training group(n=48) or a validation group(n=12). By extracting features from biparametric MRI, including T2-weighted imaging(T2WI), diffusion-weighted imaging(DWI), and apparent diffusion coefficient(ADC) maps, radiomics features from the training dataset were selected using least absolute shrinkage and selection operator(LASSO) regression. Four predictive models were developed to assess the efficacy of abiraterone in treating patients with mCRPC. The primary outcome variable was the PSA response following AA treatment. The performance of each model was evaluated using the area under the receiver operating characteristic curve(AUC). Univariate and multivariate analyses were performed using Cox regression to identify significant predictors of the efficacy of abiraterone treatment in patients with mCRPC.ResultsThe integrated model was constructed from seven radiomics features extracted from the T2WI, DWI, and ADC sequence images of the training data. This model demonstrated the highest AUC in both the training and validation cohorts, with values of 0.889 (95% CI, 0.764-0.961) and 0.875 (95% CI, 0.564-0.991). The Rad-score served as an independent predictor of the response to abiraterone treatment in patients with mCRPC (HR: 2.21, 95% CI: 1.01-4.44).ConclusionThe biparametric MRI-based radiomics model has the potential to predict the PSA response in patients with mCRPC following abiraterone treatment.Clinical relevance statementThe MRI-based radiomics model could be used to noninvasively identify the AA response in mCRPC patients, which is helpful for early clinical decision-making.

Construction of a nomogram prediction model for early postoperative stoma complications of colorectal cancer.

Postoperative enterostomy is increasing in patients with colorectal cancer, but there is a lack of a model that can predict the probability of early complications. To explore the factors influencing early postoperative stoma complications in colorectal cancer patients and to construct a nomogram prediction model for predicting the probability of these complications. A retrospective study of 462 patients who underwent postoperative ostomy for colorectal cancer in the Gastrointestinal Department of the Anhui Provincial Cancer Hospital. The patients' basic information, surgical details, pathological results, and preoperative inflammatory and nutritional indicators were reviewed. We used univariate and multivariate logistic regression to analyze the risk factors for early postoperative stoma complications in colorectal cancer patients and constructed a nomogram prediction model to predict the probability of these complications. Binary logistic regression analysis revealed that diabetes [odds ratio (OR) = 3.088, 95% confidence interval (CI): 1.419-6.719], preoperative radiotherapy and chemotherapy (OR = 6.822, 95%CI: 2.171-21.433), stoma type (OR = 2.118, 95%CI: 1.151-3.898), Nutritional risk screening 2002 score (OR = 2.034, 95%CI: 1.082-3.822) and prognostic nutritional index (OR = 0.486, 95%CI: 0.254-0.927) were risk factors for early stoma complications after colorectal cancer surgery (P < 0.05). On the basis of these results, a prediction model was constructed and the area under the receiver operating characteristic curve was 0.740 (95%CI: 0.669-0.811). After internal validation, the area under the receiver operating characteristic curve of the validation group was 0.725 (95%CI: 0.631-0.820). The calibration curves for the modeling group and validation group are displayed. The predicted results have a good degree of overlap with the actual results. A previous history of diabetes, preoperative radiotherapy and chemotherapy, stoma type, Nutritional risk screening 2002 score and prognostic nutritional index are risk factors for early stoma complications after colorectal cancer surgery. The nomogram prediction model constructed on the basis of the results of logistic regression analysis in this study can effectively predict the probability of early stomal complications after colorectal cancer surgery.

Predicting survival rates: the power of prognostic nomograms in distal cholangiocarcinoma

ObjectiveThe purpose of this research is to establish a prognostic nomogram for patients with distal cholangiocarcinoma (dCCA).MethodsWe obtained clinical data from 2401 patients diagnosed with distal cholangiocarcinoma (dCCA) between 2010 and 2020 from the Surveillance, Epidemiology, and End Results database. These patients were randomly assigned to either the training or validation group in a ratio of 6:4. 228 patients were enrolled from 9 hospitals in China as the external validation cohort. Univariate and multifactorial Cox regression analyses were conducted to ascertain prognostic factors and prognostic nomograms were developed utilizing LASSO logistic regression analysis. We used the calibration curve, and area under the curve to validate the nomograms. Decision curve analysis was used to evaluate the model and its clinical applicability.ResultsThe findings demonstrated that Grade, M stages, Surgery, and Chemotherapy emerged as autonomous prognostic factors for the survival of individuals with dCCA. The developed nomograms exhibited satisfactory accuracy in forecasting 1-year, 3-year, and 5-year survival probabilities. Furthermore, the calibration curves indicated a strong concordance between the anticipated and observed outcomes. The AUC of the nomogram for 1-year, 3-year, 5 year overall survival (OS) predication were 0.809 (95%CI 78.5-83.3), 0.79 (95%CI 75.8-82.2) and 0.761 ((95%CI 72.3-80.0) in the training cohort, 0.79 (95%CI 75.9-82.0), 0.73 (95%CI 68.5-77.5), and 0.732(95%CI 68.0-78.3) in internal test cohort, 0.862 (95%CI 81.7-90.7),0.83 (95%CI 76.4-89.6),and 0.819(95%CI 74.6-89.2) in external test cohort.ConclusionThe nomograms that have been suggested demonstrate strong predictive capability. These tools can assist medical professionals in assessing the prognosis of patients with dCCA and in devising more accurate treatment strategies for them.

Risk Prediction Model of Peristomal Skin Complications Among Patients with Colorectal Cancer and an Ostomy: A Cross-sectional Study in Shanghai, China.

To analyze the risk factors for peristomal skin complications (PSCs) in patients with colorectal cancer and an ostomy, construct a prediction model, and verify its effectiveness. In this cross-sectional study, researchers recruited 265 patients with an ostomy at the stoma clinic of a tertiary hospital, from May 2022 to August 2023. Patients were divided into two groups: complications group (n = 81) and no complications group (n = 184). Researchers constructed a logistic regression prediction model using univariate and multivariate analyses. From May 2023 to August 2023, a validation group of 135 patients with an ostomy was selected for external validation of the model. The incidence of PSCs was 30.57% in the modeling group and 30.37% in the validation group. The predictor variables were preoperative and postoperative health education, tumor therapy within 3 months, preoperative stoma positioning, stoma height, stoma type, and excrement state. The Hosmer-Lemeshow test yielded a P value of .513, the area under the ROC curve was 0.872, the Youden index was 0.561, and the sensitivity and specificity were 0.827 and 0.734. For external validation, the Hosmer-Lemeshow test yielded a P value of .835, the area under the ROC curve was 0.887, and the sensitivity and specificity were 0.905 and 0.720, respectively. The prediction model demonstrates good predictive efficacy and can serve as a reference for clinical caregivers in identifying patients at high risk of PSCs.

Incidence trends and prognostic factors in head and neck MALT lymphoma.

Primary head and neck mucosa-associated lymphoid tissue lymphoma (HN-MALT) is a rare lymphoma with unknown incidence and prognosis. We allocated HN-MALT data from the Self-Surveillance, Epidemiology, and End Results database (2000-2021) into training and validation cohorts at a 7:3 ratio. A joinpoint regression analysis was used to examine sex-specific and age-group morbidities, and independent prognostic factors were identified through multivariate Cox analysis to construct a nomogram prediction model and verify the accuracy of prediction. A total of 2,517 patients with HN-MALT were randomly divided into training (1,762) and validation (755) groups. The incidence of HN-MALT in men and women decreased from 2007 to 2021, with an annual percent change (APC) of -3.04% (95%: -4.4 - -1.6, P < 0.05), while in the ≥ 60 years old group, the incidence decreased significantly from 2016 to 2021, with an APC of -8.20 (95%: -13.9 - -2.1, P < 0.05). The multivariate Cox analysis revealed that male, ≥ 60 years old, white, and divorced/separated/widowed were independent risk factors of the overall survival and lymphoma-specific survival. A nomogram prediction model was constructed based on the Cox regression results for multiple factors, the areas under the curve, the calibration curve, and decision curve analysis results of which indicated that the nomogram prediction model performed very well. HN-MALT cells exhibit distinctive clinical and pathological characteristics. Furthermore, we developed a nomogram model for the prognostic assessment to offer valuable guidance for clinical decision-making.

Utilizing machine learning to predict hospital admissions for pediatric COVID-19 patients (PrepCOVID-Machine)

The COVID-19 pandemic has burdened healthcare systems globally. To curb high hospital admission rates, only patients with genuine medical needs are admitted. However, machine learning (ML) models to predict COVID-19 hospitalization in Asian children are lacking. This study aimed to develop and validate ML models to predict pediatric COVID-19 hospitalization. We collected secondary data with 2200 patients and 65 variables from Malaysian aged 0 to 12 with COVID-19 between 1st February 2020 and 31st March 2022. The sample was partitioned into training, internal, and external validation groups. Recursive Feature Elimination (RFE) was employed for feature selection, and we trained seven supervised classifiers. Grid Search was used to optimize the hyperparameters of each algorithm. The study analyzed 1988 children and 30 study variables after data were processed. The RFE algorithm selected 12 highly predicted variables for COVID-19 hospitalization, including age, male sex, fever, cough, rhinorrhea, shortness of breath, vomiting, diarrhea, seizures, body temperature, chest indrawing, and abnormal breath sounds. With external validation, Adaptive Boosting was the highest-performing classifier (AUROC = 0.95) to predict COVID-19 hospital admission in children. We validated AdaBoost as the best to predict COVID-19 hospitalization among children. This model may assist front-line clinicians in making medical disposition decisions.

Actors influencing cancer-related fatigue and the construction of a risk prediction model in lung cancer patients

PurposeThe paper aims to investigate the factors influencing cancer-related fatigue (CRF) in lung cancer patients and construct a CRF risk prediction model, providing effective intervention strategies for clinical medical staff.MethodsThis paper employs convenience sampling to select 400 lung cancer patients who visited a tertiary hospital in Dazhou, Sichuan Province, from January 2021 to January 2022. A questionnaire survey was conducted using the Revised Piper Fatigue Scale (PFS-R), Pittsburgh Sleep Quality Index (PSQI), and Hospital Anxiety and Depression Scale (HADS) to collect data on patient demographics and sociological characteristics, disease-related information, physiological indicators, sleep quality, mental health, and other relevant factors. To explore the factors influencing CRF in lung cancer patients, single-factor analysis and multiple logistic regression analysis were performed. A CRF risk prediction model was then established, with its predictive performance and calibration evaluated using ROC curves.FindingsThe results of multivariate logistic regression analysis showed that gender, age, education level, living status, daily exercise, clinical stage, course of disease, treatment mode, chronic disease, BMI, hemoglobin, serum albumin, blood glucose, potassium concentration, magnesium concentration, PSQI score and HAD score were the influencing factors of CRF in lung cancer patients (P&amp;lt;0.05). The AUC of the model construction group and the model validation group were 0.863 and 0.838, respectively, and the results of Hosmer-Lemeshow fit test showed that χ2 = 7.540, P=0.378&amp;gt;0.05 of the model construction group and χ2 = 8.120, P=0.320&amp;gt;0.05 of the model validation group indicated that the model had high prediction accuracy.Originality/valueThe risk prediction model for CRF holds significant clinical value. It can help medical staff to promptly identify high-risk patients, develop personalized intervention strategies, alleviate fatigue symptoms, and improve overall patient quality of life.