Bootstrap Validation Research Articles

Construction of the machine learning-based live birth prediction models for the first in vitro fertilization pregnant women

BackgroundThis study was to conduct prediction models based on parameters before and after the first cycle, respectively, to predict live births in women who received fresh or frozen in vitro fertilization (IVF) or intracytoplasmic sperm injection (ICSI) for the first time.MethodsThis retrospective cohort study population consisted of 1,857 women undergoing the IVF cycle from 2019 to 2021 at Huizhou Municipal Central Hospital. The data between 2019 and 2020 were completely randomly divided into a training set and a validation set (8:2). The data from 2021 was used as the testing set, and the bootstrap validation was carried out by extracting 30% of the data for 200 times on the total data set. In the training set, variables are divided into those before the first cycle and after the first cycle. Then, predictive factors before the first cycle and after the first cycle were screened. Based on the predictive factors, four supervised machine learning algorithms were respectively considered to build the predictive models: logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM). The performances of the prediction models were evaluated by the area under the receiver operator characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy.ResultsTotally, 851 women (45.83%) had a live birth. The LGBM model showed a robust performance in predicting live birth before the first cycle, with AUC being 0.678 [95% confidence interval (CI): 0.651 to 0.706] in the training set, 0.612 (95% CI: 0.553 to 0.670) in the validation set, 0.634 (95% CI: 0.511 to 0.758) in the testing set, and 0.670 (95% CI: 0.626 to 0.715) in the bootstrap validation. The AUC value in the training set, validation set, testing set, and bootstrap of LGBM to predict live birth after the first cycle was 0.841 (95% CI: 0.821 to 0.861), 0.816 (95% CI: 0.773 to 0.859), 0.835 (95% CI: 0.743 to 0.926), and 0.839 (95% CI: 0.806 to 0.871), respectively.ConclusionThe LGBM model based on the predictive factors before and after the first cycle for live birth in women showed a good predictive performance. Therefore, it may assist fertility specialists and patients to adjust the appropriate treatment strategy.

Visual Dysfunction is a Risk Factor of Postoperation Delirium in Parkinson Disease

To investigate the incidence of and factors influencing postoperative delirium (POD) in Parkinson's disease after deep brain stimulation (DBS) surgery. A total of 272 patients with Parkinson's disease who underwent DBS completed the Visual Impairment in Parkinson's Disease Questionnaire (VIPD-Q) and underwent neuro-ophthalmologic examinations including optical coherence tomography and fundus vessel analysis. We retrospect the prevalence of POD in groups with different VIPD-Q scores, retinal nerve fiber layer (RNFL) thicknesses, and vessel percentage areas (VPA). A predictive model based on the VIPD-Q was constructed using multivariate logistic regression and verified using bootstrap validation. POD was experienced by 65 (23.9 %) of 272 patients. Patients with PD who had visual impairment (VIPD-Q > 6) had a higher incidence of POD (chi-square, p <0.001). The thickness of the retinal nerve fiber layer and vessel percentage area were also correlated with POD risk. Differences in implantation locations (subthalamic nucleus or pars interna of globus pallidus), operation times, and general anesthesia times did not affect the prevalence of DBS-related POD. A nomogram was constructed based on ophthalmic events to predict the risk of POD. The study findings provide convincing evidence of the relationship between visual dysfunction and the risk of POD. In view of the higher risk of POD, visually impaired patients with PD should undergo closer monitoring after DBS surgery.

A validated prognostic nomogram for patients with H3 K27M-mutant diffuse midline glioma

H3 K27M-mutant diffuse midline glioma (H3 K27M-mt DMG) is a rare, highly invasive tumor with a poor prognosis. The prognostic factors of H3 K27M-mt DMG have not been fully identified, and there is no clinical prediction model for it. This study aimed to develop and validate a prognostic model for predicting the probability of survival in patients with H3 K27M-mt DMG. Patients diagnosed with H3 K27M-mt DMG in the West China Hospital from January 2016 to August 2021 were included. Cox proportional hazard regression was used for survival assessment, with adjustment for known prognostic factors. The final model was established using the patient data of our center as the training cohort and data from other centers for external independent verification. One hundred and five patients were ultimately included in the training cohort, and 43 cases from another institution were used as the validation cohort. The factors influencing survival probability in the prediction model included age, preoperative KPS score, radiotherapy and Ki-67 expression level. The adjusted consistency indices of the Cox regression model in internal bootstrap validation at 6, 12, and 18 months were 0.776, 0.766, and 0.764, respectively. The calibration chart showed high consistency between the predicted and observed results. The discrimination in external verification was 0.785, and the calibration curve showed good calibration ability. We identified the risk factors that affect the prognosis of H3 K27M-mt DMG patients and then established and validated a diagnostic model for predicting the survival probability of these patients.

Routine 4D Cardiac Computed Tomography to Identify Concomitant Transthyretin Amyloid Cardiomyopathy in TAVI candidates with Severe Aortic Stenosis

Abstract Funding Acknowledgements Type of funding sources: Other. Main funding source(s): Bangerter-Rhyner Foundation, Pfizer, GAMBIT foundation. Background Transthyretin amyloid cardiomyopathy (ATTR-CM) may coexist in patients with severe aortic stenosis (AS) considered for transcatheter aortic valve implantation (TAVI). The diagnosis of ATTR-CM by 99mTechnetium-3,3-diphosphono-1,2-propanodicarboxylic-acid (DPD)-scintigraphy is costly, whereas endomyocardial biopsy is associated with relevant procedural risks and sampling error. Objectives To evaluate whether ATTR-CM may be diagnosed by routine 4D cardiac computed tomography (4DCCT). Methods In a prospective screening study for ATTR-CM, the diagnostic performance of 4DCCT-based left- (LV), right ventricular (RV) and left atrial (LA) dimensions, ejection fraction (EF) and myocardial strain was evaluated against DPD-scintigraphy to identify ATTR-CM. Diagnostic predictors and a newly developed 4DCCT-score were validated by internal bootstrapping. Results Among 263 patients considered for TAVI (57% males,age 83±4.6 years) undergoing 4DCCT, DPD-scintigraphy (Perugini grade 2–3) confirmed co-existing ATTR-CM in 27 (10.3%) patients. Patients with ATTR-CM had impaired 4DCCT-based LVEF, LV global longitudinal strain (GLS), and LA-GLS. LV mass index, LV-GLS, LA-GLS and relative apical longitudinal strain (ratio of apical to basal/midventricular strain), each predicted the presence of ATTR-CM with an area under the curve (AUC) of &amp;gt;0.7. Implementing these parameters with cutoff-values of ≥81g/m2, ≥-14.9%, &amp;lt;11.5% and ≥1.7 in an unweighted score yielded high prognostic accuracy (AUC=0.89; 95%CI:0.81–0.94;p&amp;lt;0.001), robust to internal bootstrapping validation (AUC=0.88;95%CI:0.82–0.94). If two criteria were fulfilled, sensitivity and specificity to detect ATTR-CM were 96.3 and 58.9%, respectively. Conclusions Clinically indicated, routine 4DCCT in patients considered for TAVI provides high diagnostic yield to detect concomitant ATTR-CM, by assessing LV- and LA-GLS, LV relative apical longitudinal strain and LV mass index.

Predicting AKI in patients with AMI: Development and assessment of a new predictive nomogram.

Acute kidney injury (AKI) is a common complication of acute myocardial infarction (AMI) and is associated with both long- and short-term consequences. This study aimed to investigate relevant risk variables and create a nomogram that predicts the probability of AKI in patients with AMI, so that prophylaxis could be initiated as early as possible. Data were gathered from the medical information mart for the intensive care IV database. We included 1520 patients with AMI who were admitted to the coronary care unit or the cardiac vascular intensive care unit. The primary outcome was AKI during hospitalization. Independent risk factors for AKI were identified by applying least absolute shrinkage and selection operator regression models and multivariate logistic regression analyses. A multivariate logistic regression analysis was used to build a predictive model. The discrimination, calibration, and clinical usefulness of the prediction model were assessed using C-index, calibration plot, and decision curve analysis. Internal validation was assessed using bootstrapping validation. Of 1520 patients, 731 (48.09%) developed AKI during hospitalization. Hemoglobin, estimated glomerular filtration rate, sodium, bicarbonate, total bilirubin, age, heart failure, and diabetes were identified as predictive factors for the nomogram construction (P < .01). The model displayed good discrimination, with a C-index of 0.857 (95% CI:0.807-0.907), and good calibration. A high C-index value of 0.847 could still be reached during interval validation. Decision curve analysis showed that the AKI nomogram was clinically useful when the intervention was determined at an AKI possibility threshold of 10%. The nomogram constructed herein can successfully predict the risk of AKI in patients with AMI early and provide critical information that can facilitate prompt and efficient interventions.

Prediction of Late Hospital Arrival in Patients with Mild and Rapidly Improving Acute Ischemic Stroke in a Rural Area of China.

Among all ischemic stroke patients, more than half are mild and rapidly improving acute ischemic stroke (MaRAIS) patients. However, many MaRAIS patients do not recognize the disease early on, and thus they delay access to the treatment that would be most effective if provided earlier. This is especially true in rural areas. The aim of this study was to develop and validate a late hospital arrival risk nomogram in a rural Chinese population of patients with MaRAIS. We developed a prediction model based on a training dataset of 173 MaRAIS patients collected from September 9, 2019 to May 13, 2020. Data analyzed included demographics and disease characteristics. A least absolute shrinkage and selection operator (LASSO) regression model was used to optimize feature selection for the late hospital arrival risk model. Multivariable logistic regression analysis was applied to build a prediction model incorporating the features selected in the LASSO regression models. The discrimination, calibration, and clinical usefulness of the prediction model were assessed using the C-index, calibration plot, and decision curve analysis, respectively. Internal validation was then assessed using bootstrapping validation. Variables contained in the prediction nomogram included transportation mode, history of diabetes, knowledge of stroke symptoms, and thrombolytic therapy. The model had moderate predictive power with a C-index of 0.709 (95% confidence interval: 0.636-0.783) and good calibration. In the internal validation, the C-index reached 0.692. The risk threshold was 30-97% according to the analysis of the decision curve, and the nomogram could be applied in clinical practice. This novel nomogram, which incorporates transportation mode, history of diabetes, knowledge of stroke symptoms, and thrombolytic therapy, was conveniently applied to facilitate individual late hospital arrival risk prediction among MaRAIS patients in a rural area of Shanghai, China.

Prognostic Models for Global Functional Outcome and Post-Concussion Symptoms Following Mild Traumatic Brain Injury: A Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) Study.

After mild traumatic brain injury (mTBI), a substantial proportion of individuals do not fully recover on the Glasgow Outcome Scale Extended (GOSE) or experience persistent post-concussion symptoms (PPCS). We aimed to develop prognostic models for the GOSE and PPCS at 6 months after mTBI and to assess the prognostic value of different categories of predictors (clinical variables; questionnaires; computed tomography [CT]; blood biomarkers). From the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study, we included participants aged 16 or older with Glasgow Coma Score (GCS) 13-15. We used ordinal logistic regression to model the relationship between predictors and the GOSE, and linear regression to model the relationship between predictors and the Rivermead Post-concussion Symptoms Questionnaire (RPQ) total score. First, we studied a pre-specified Core model. Next, we extended the Core model with other clinical and sociodemographic variables available at presentation (Clinical model). The Clinical model was then extended with variables assessed before discharge from hospital: early post-concussion symptoms, CT variables, biomarkers, or all three categories (extended models). In a subset of patients mostly discharged home from the emergency department, the Clinical model was extended with 2-3-week post-concussion and mental health symptoms. Predictors were selected based on Akaike's Information Criterion. Performance of ordinal models was expressed as a concordance index (C) and performance of linear models as proportion of variance explained (R2). Bootstrap validation was used to correct for optimism. We included 2376 mTBI patients with 6-month GOSE and 1605 patients with 6-month RPQ. The Core and Clinical models for GOSE showed moderate discrimination (C = 0.68 95% confidence interval 0.68 to 0.70 and C = 0.70[0.69 to 0.71], respectively) and injury severity was the strongest predictor. The extended models had better discriminative ability (C = 0.71[0.69 to 0.72] with early symptoms; 0.71[0.70 to 0.72] with CT variables or with blood biomarkers; 0.72[0.71 to 0.73] with all three categories). The performance of models for RPQ was modest (R2 = 4% Core; R2 = 9% Clinical), and extensions with early symptoms increased the R2 to 12%. The 2-3-week models had better performance for both outcomes in the subset of participants with these symptoms measured (C = 0.74 [0.71 to 0.78] vs. C = 0.63[0.61 to 0.67] for GOSE; R2 = 37% vs. 6% for RPQ). In conclusion, the models based on variables available before discharge have moderate performance for the prediction of GOSE and poor performance for the prediction of PPCS. Symptoms assessed at 2-3 weeks are required for better predictive ability of both outcomes. The performance of the proposed models should be examined in independent cohorts.

Analysis of prognostic factors and establishment of prognostic model for primary mediastinal germ cell tumors: a case controlled study.

The overall prognosis of primary mediastinal germ cell tumors (PMGCTs) is poor and the associated prognostic factors are not fully understood. Our goal was to investigate the prognostic factors of PMGCTs and to develop a validated prognostic prediction model. A total of 114 PMGCTs with specific pathological types were included in this study. Clinicopathological characteristics of nonseminomatous PMGCTs and mediastinal seminomas were compared using the χ2 or Fisher's exact test. Independent prognostic factors of nonseminomatous PMGCTs screened using the univariate and multivariate Cox regression analysis were then used to generate a nomogram. The predictive performance of the nomogram was evaluated using the concordance index, decision curve, and the area under the receiver operating characteristic curve (AUC) and validated by bootstrap resampling. The Kaplan-Meier curves of independent prognostic factors were analyzed. This study included 71 cases of nonseminomatous PMGCTs and 43 cases of mediastinal seminomas. The 3-year overall survival rates for nonseminomatous PMGCTs and mediastinal seminomas patients were 54.5 and 97.4%, respectively. The overall survival prognostic nomogram for nonseminomatous PMGCTs was established by integrating independent prognostic factors, including the Moran-Suster stage, white blood cell, hemoglobin, and platelet-lymphocyte ratio. The nomogram demonstrated good performance with a concordance index of 0.760 and the 1-year and 3-year AUC values of 0.821 and 0.833, respectively. These values were better than those of the Moran-Suster stage system. The bootstrap validation had an AUC of 0.820 (0.724-0.915) and showed a well-fitting calibration curve. Besides, patients with mediastinal seminomas showed favorable clinical outcomes and all the nine patients received neoadjuvant therapy and postoperative surgery achieved pathological complete response. A nomogram based on staging and blood routine examination results was established to accurately and consistently predict the prognosis of patients with nonseminomatous PMGCTs.

Development, validation and outcomes associated with a risk prediction algorithm for incident atrial fibrillation: retrospective national cohort study of 2 081 139 individuals

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): British Heart Foundation Background An algorithm that identifies individuals with a digital electronic health record (EHR) signature homologous to patients with atrial fibrillation (AF) could delineate a subpopulation that may benefit from early interventions to reduce future adverse events. Purpose We aimed to train and test a scalable algorithm to identify individuals at higher risk of incident AF in the short-term, and quantify associations with AF and a range of other conditions. Methods We used UK primary care EHR data from individuals aged ≥30 years without known AF in the CPRD-GOLD dataset (Jan 2, 1998, Nov 30, 2018), randomly divided into training (80%) and testing (20%) datasets. We trained a random forest classifier using age, sex, ethnicity and comorbidities (FIND-AF). Performance was evaluated in the testing dataset with internal bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc and C2HEST scores. We calculated the cumulative incidence rate for AF, heart failure, valvular heart disease (and specifically aortic stenosis), MI, stroke or TIA, peripheral vascular disease, CKD, diabetes and COPD. Incident diagnoses were the first record of that condition in primary or secondary care records from any diagnostic position. We excluded individuals for the analysis of each condition who had a preceding diagnosis of that condition. Fine and Gray’s models with competing risk of death were fit for each condition between higher and lower predicted AF risk. Results FIND-AF could be applied to 100% of records for 2 081 139 individuals in the cohort. In the testing dataset (n = 416 228), individuals at higher predicted AF risk had similar baseline characteristics to individuals who developed incident AF (Table 1). Prediction performance for AF was strongest for FIND-AF (AUROC 0·824, 95% CI 0·813-0·829; Brier score 0.069) compared with CHA2DS2-VASc (0·784, 0·773-0·794; 0.093) and C2HEST (0·757, 0·744-0·770; 0.102). FIND-AF demonstrated favourable reclassification and superior net benefit on decision curve analysis, with robust performance in both sexes and across ethnic groups. The higher predicted risk cohort, compared to lower predicted risk, had a 20-fold higher 6-month incidence rate for AF and higher long-term risk of AF (HR 8·75, 95% CI 8·44-9·06), but also incident heart failure (HR 12.54, 95% CI 12.08-13.01) aortic stenosis (9.98, 9.16-10.87), stroke/TIA (8.07, 7.80-8.34), CKD (6.85, 6.70-7.00), peripheral vascular disease (6.62, 6.28-6.98), valvular heart disease (6.49, 6.14-6.85), MI (5.02, 4.82-5.22), diabetes (2.05, 2.00-2.10) and COPD (2.02, 2.00-2.05) (Figure 1). This cohort were also at higher risk of death (10.45, 10.23-10.68), accounting for 71% of cardiovascular deaths. Conclusions FIND-AF is applicable to national electronic health records data, identifies people at higher risk of incident AF within the next 6 months with good performance, and predicts risk of a range of other conditions and death.

Revised algorithmic approach to differentiate between non-specific and specific etiologies of chronic terminal Ileitis.

/Aims-Chronic isolated terminal ileitis(TI) may be seen in Crohn's disease(CD) and Intestinal tuberculosis(ITB) in addition to other etiologies that may be managed symptomatically. We developed a revised algorithm to distinguish patients with a specific etiology from a non specific etiology. Patients with chronic isolated TI following-up from 2007 to 2022 were retrospectively reviewed. A specific(ITB or CD) diagnosis was made based on standardized criteria and other relevant data was collected. Using this cohort, validation of a previously suggested algorithm was conducted. Further, based on the results of a univariate analysis, a multivariate analysis with bootstrap validation was used to develop a revised algorithm. We included 153 patients(mean age-36.9+14.6 years, males-70%, median duration-1.5 years, range:0-56 years) with chronic isolated TI of whom 109(71.2%) received a specific diagnosis(CD-69, ITB-40). On multivariate regression and validation statistics with a combination of clinical, laboratory, radiological and colonoscopic findings, an optimism corrected c-statistic of 0.975 and 0.958 was obtained with and without histopathological findings respectively. Revised algorithm, based on these, showed a sensitivity, specificity, positive and negative predictive value, and overall accuracy of 98.2%(95%CI:93.5 - 99.8), 75.0%(95%CI:59.7 - 86.8), 90.7%(95%CI:85.4 - 94.2), 94.3%(95%CI:80.5 - 98.5) and 91.5%(95%CI:85.9 - 95.4), respectively. This was more sensitive and specific than the previous algorithm(accuracy 83.9%, sensitivity 95.5%, and specificity 54.6%). We developed a revised algorithm and a multi-modality approach to stratify patients with chronic isolated TI into specific and non-specific etiologies with an excellent diagnostic accuracy which could potentially avoid missed diagnosis and unnecessary side effects of treatment.

CT morphological features for predicting the risk of lymph node metastasis in T1 colorectal cancer.

The aim of this study is to evaluate the feasibility of clinicopathological characteristics and computed tomography (CT) morphological features in predicting lymph node metastasis (LNM) for patients with T1 colorectal cancer (CRC). A total of 144 patients with T1 CRC who underwent CT scans and surgical resection were retrospectively included in our study. The clinicopathological characteristics and CT morphological features were assessed by two observers. Univariate and multiple logistic regression analyses were used to identify significant LNM predictive variables. Then a model was developed using the independent predictive factors. The predictive model was subjected to bootstrapping validation (1000 bootstrap resamples) to calculate the calibration curve and relative C-index. LNM were found in 30/144 patients (20.83%). Four independent risk factors were determined in the multiple logistic regression analysis, including presence of necrosis (adjusted odds ratio [OR] = 10.32, 95% confidence interval [CI] 1.96-54.3, p = 0.004), irregular outer border (adjusted OR = 5.94, 95% CI 1.39-25.45, p = 0.035), and heterogeneity enhancement (adjusted OR = 7.35, 95% CI 3.11-17.38, p = 0.007), as well as tumor location (adjusted ORright-sided colon = 0.05 [0.01-0.60], p = 0.018; adjusted ORrectum = 0.22 [0.06-0.83], p = 0.026). In the internal validation cohort, the model showed good calibration and good discrimination with a C-index of 0.89. There are significant associations between lymphatic metastasis status and tumor location as well as CT morphologic features in T1 CRC, which could help the doctor make decisions for additional surgery after endoscopic resection. • LNM more frequently occurs in left-sided T1 colon cancer than in right-sided T1 colon and rectal cancer. • CT morphologic features are risk factors for LNM of T1 CRC, which may be related to fundamental biological behaviors. • The combination of tumor location and CT morphologic features can more effectively assist in predicting LNM in patients with T1 CRC, and decrease the rate of unnecessary extra surgeries after endoscopic resection.

A pharmacokinetic analysis of amisulpride in adult Chinese patients with schizophrenia: Impact of creatinine clearance.

To develop a stable population pharmacokinetic (PPK) model of amisulpride and to investigate the effects of covariates on the pharmacokinetic parameters in adult Chinese patients with schizophrenia. This retrospective study was carried out using 168 serum samples from 88 patients collected during routine clinical monitoring. Covariates recorded included demographic parameters (gender, age, weight), clinical parameters (serum creatinine, creatinine clearance), and intake of co-medications. The amisulpride PPK model was established using a nonlinear mixed effects modeling (NONMEM) approach. Goodness-of-fit (GOF) plots, bootstrap validation (1,000 runs), and normalized prediction distribution error (NPDE) were used in the evaluation of the final model. A one-compartment model with first-order absorption and elimination was developed. The population estimates for apparent clearance (CL/F) and apparent volume of distribution (V/F) were 32.6 L/h and 391 L, respectively. Estimated creatinine clearance (eCLcr) was a significant covariate for CL/F. The established model was: CL/F = 32.6 × (eCLcr/114.3)0.485 (L/h). The stability of the model was confirmed using GOF plots, bootstrap, and NPDE. Creatinine clearance is a major covariate which is positively correlated with CL/F. Therefore, additional dose adjustments of amisulpride may be required on the basis of eCLcr. An ethnic difference may exist in the pharmacokinetics of amisulpride, but further research is needed in order to confirm this possibility. The PPK model of amisulpride for adult Chinese schizophrenic patients established here using NONMEM, is potentially an important tool for individualizing drug dosage and therapeutic drug monitoring.

Development and validation of a prediction nomogram for non-suicidal self-injury in female patients with mood disorder.

Non-suicidal self-injury (NSSI) is a highly prevalent behavioral problem among people with mental disorders that can result in numerous adverse outcomes. The present study aimed to systematically analyze the risk factors associated with NSSI to investigate a predictive model for female patients with mood disorders. A cross-sectional survey among 396 female patients was analyzed. All participants met the mood disorder diagnostic groups (F30-F39) based on the Diseases and Related Health Problems 10th Revision (ICD-10). The Chi-Squared Test, t-test, and the Wilcoxon Rank-Sum Test were used to assess the differences of demographic information and clinical characteristics between the two groups. Logistic LASSO Regression Analyses was then used to identify the risk factors of NSSI. A nomogram was further used to construct a prediction model. After LASSO regression selection, 6 variables remained significant predictors of NSSI. Psychotic symptom at first-episode (β = 0.59) and social dysfunction (β = 1.06) increased the risk of NSSI. Meanwhile, stable marital status (β = -0.48), later age of onset (β = -0.01), no depression at onset (β = -1.13), and timely hospitalizations (β = -0.10) can decrease the risk of NSSI. The C-index of the nomogram was 0.73 in the internal bootstrap validation sets, indicated that the nomogram had a good consistency. Our findings suggest that the demographic information and clinical characteristics of NSSI can be used in a nomogram to predict the risk of NSSI in Chinese female patients with mood disorders.

Development of a model by LASSO to predict hospital length of stay (LOS) in patients with the SARS-Cov-2 omicron variant

ABSTRACT The length of stay (LOS) in hospital varied considerably in different patients with COVID-19 caused by SARS-CoV-2 Omicron variant. The study aimed to explore the clinical characteristics of Omicron patients, identify prognostic factors, and develop a prognostic model to predict the LOS of Omicron patients. This was a single center retrospective study in a secondary medical institution in China. A total of 384 Omicron patients in China were enrolled. According to the analyzed data, we employed LASSO to select the primitive predictors. The predictive model was constructed by fitting a linear regression model using the predictors selected by LASSO. Bootstrap validation was used to test performance and eventually we obtained the actual model. Among these patients, 222 (57.8%) were female, the median age of patients was 18 years and 349 (90.9%) completed two doses of vaccination. Patients on admission diagnosed as mild were 363 (94.5%). Five variables were selected by LASSO and a linear model, and those with P < 0.05 were integrated into the analysis. It shows that if Omicron patients receive immunotherapy or heparin, the LOS increases by 36% or 16.1%. If Omicron patients developed rhinorrhea or occur familial cluster, the LOS increased by 10.4% or 12.3%, respectively. Moreover, if Omicron patients’ APTT increased by one unit, the LOS increased by 0.38%. Five variables were identified, including immunotherapy, heparin, familial cluster, rhinorrhea, and APTT. A simple model was developed and evaluated to predict the LOS of Omicron patients. The formula is as follows: Predictive LOS = exp(1*2.66263 + 0.30778*Immunotherapy + 0.1158*Familiar cluster + 0.1496*Heparin + 0.0989*Rhinorrhea + 0.0036*APTT).

A visualized MAC nomogram online predicts the risk of three-month mortality in Chinese elderly aneurysmal subarachnoid hemorrhage patients undergoing endovascular coiling.

Aneurysmal subarachnoid hemorrhage (aSAH) is an aggressive disease with higher mortality rate in the elderly population. Unfortunately, the previous models for predicting clinical prognosis are still not accurate enough. Therefore, we aimed to construct and validate a visualized nomogram model to predict online the 3-month mortality in elderly aSAH patients undergoing endovascular coiling. We conducted a retrospective analysis of 209 elderly aSAH patients at People's Hospital of Hunan Province, China. A nomogram was developed based on multivariate logistic regression and forward stepwise regression analysis, then validated using the bootstrap validation method (n = 1000). In addition, the performance of the nomogram was evaluated by various indicators to prove its clinical value. Morbid pupillary reflex, age, and using a breathing machine were independent predictors of 3-month mortality. The AUC of the nomogram was 0.901 (95% CI: 0.853-0.950), and the Hosmer-Lemeshow goodness-of-fit test showed good calibration of the nomogram (p = 0.4328). Besides, the bootstrap validation method internally validated the nomogram with an area under the curve of the receiver operator characteristic (AUROC) of 0.896 (95% CI: 0.846-0.945). Decision curve analysis (DCA) and clinical impact curve (CIC) indicated the nomogram's excellent clinical utility and applicability. An easily applied visualized nomogram model named MAC (morbid pupillary reflex-age-breathing machine) based on three accessible factors has been successfully developed. The MAC nomogram is an accurate and complementary tool to support individualized decision-making and emphasizes that patients with higher risk of mortality may require closer monitoring. Furthermore, a web-based online version of the risk calculator would greatly contribute to the spread of the model in this field.

Towards a predictive model for prevention of the risk of COVID-19 infection.

The scarcity of person-centered applications aimed at developing awareness on the risk posed by the COVID-19 pandemic, stimulates the exploration and creation of preventive tools that are accessible to the population. To develop a predictive model that allows evaluating the risk of mortality in the event of SARS-CoV-2 virus infection. Exploration of public data from 16,000 COVID-19-positive patients to generate an efficient discriminant model, evaluated with a score function and expressed by a self-rated preventive interest questionnaire. A useful linear function was obtained with a discriminant capacity of 0.845; internal validation with bootstrap and external validation, with 25 % of tested patients showing marginal differences. The predictive model with statistical support, based on 15 accessible questions, can become a structured prevention tool.

Development and Validation of a Nomogram to Predict the Risk of Lumbar Disk Reherniation within 2 Years After Percutaneous Endoscopic Lumbar Discectomy.

To develop and validate a nomogram for predicting recurrent lumbar disk herniation (LDH) within 2 years after percutaneous endoscopic lumbar discectomy. Information on patients' LDH was collected from 1 medical center between January 2015 and September 2020. The LASSO (least absolute shrinkage and selection operator) method was applied to select the most significant risk factors. A multivariate logistic regression analysis was used to develop a predictive model incorporating the possible factors selected by the LASSO regression model. The discriminant, corrected, and clinically useful prediction models were evaluated using consistency index (C-index), receiver operating characteristic curve, calibration curves, and decision curve analysis. Internal validation of clinical predictive power was also assessed by bootstrap validation. A total of 690 patients with LDH were included in this study. Sixty-three patients experienced recurrence within 2 years whereas 627 experienced no recurrence. The nomogram predictors included age, body mass index, Modic change, Pfirrmann grade, and sagittal range of motion. The model had good discrimination power, with a reliable C-index of 0.868 (95% confidence interval, 0.822-0.913) and interval validation confirmed a higher C-index value of 0.846. The area under the receiver operating characteristic curve was 0.868, indicating a good predictive value. The decision curve analysis indicated that it was clinically feasible to use the predictive recurrence nomogram model. We developed and validated a new accurate and effective nomogram for predicting recurrent LDH within 2 years after percutaneous endoscopic lumbar discectomy. Age, body mass index, Modic change, Pfirrmann grade, and sagittal range of motion were significant features for predicting rLDH.

A Nomogram for Predicting Delayed Viral Shedding in Non-Severe SARS-CoV-2 Omicron Infection.

The Omicron variant of SARS-CoV-2 has emerged as a significant global concern, characterized by its rapid transmission and resistance to existing treatments and vaccines. However, the specific hematological and biochemical factors that may impact the clearance of Omicron variant infection remain unclear. The present study aimed to identify easily accessible laboratory markers that are associated with prolonged virus shedding in non-severe patients with COVID-19 caused by the Omicron variant. A retrospective cohort study was conducted on 882 non-severe COVID-19 patients who were diagnosed with the Omicron variant in Shanghai between March and June 2022. The least absolute shrinkage and selection operator regression model was used for feature selection and dimensional reduction, and multivariate logistic regression analysis was performed to construct a nomogram for predicting the risk of prolonged SARS-CoV-2 RNA positivity lasting for more than 7 days. The receiver operating characteristic (ROC) curve and calibration curves were used to assess predictive discrimination and accuracy, with bootstrap validation. Patients were randomly divided into derivation (70%, n = 618) and validation (30%, n = 264) cohorts. Optimal independent markers for prolonged viral shedding time (VST) over 7 days were identified as Age, C-reactive protein (CRP), platelet count, leukocyte count, lymphocyte count, and eosinophil count. These factors were subsequently incorporated into the nomogram utilizing bootstrap validation. The area under the curve (AUC) in the derivation (0.761) and validation (0.756) cohorts indicated good discriminative ability. The calibration curve showed good agreement between the nomogram-predicted and actual patients with VST over 7 days. Our study confirmed six factors associated with delayed VST in non-severe SARS-CoV-2 Omicron infection and constructed a Nomogram which may assist non-severely affected patients to better estimate the appropriate length of self-isolation and optimize their self-management strategies.

Predicting the Efficacy of SBRT for Lung Cancer with 18F-FDG PET/CT Radiogenomics.

to develop a radiogenomic model on the basis of 18F-FDG PET/CT radiomics and clinical-parameter EGFR for predicting PFS stratification in lung-cancer patients after SBRT treatment. A total of 123 patients with lung cancer who had undergone 18F-FDG PET/CT examination before SBRT from September 2014 to December 2021 were retrospectively analyzed. All patients' PET/CT images were manually segmented, and the radiomic features were extracted. LASSO regression was used to select radiomic features. Logistic regression analysis was used to screen clinical features to establish the clinical EGFR model, and a radiogenomic model was constructed by combining radiomics and clinical EGFR. We used the receiver operating characteristic curve and calibration curve to assess the efficacy of the models. The decision curve and influence curve analysis were used to evaluate the clinical value of the models. The bootstrap method was used to validate the radiogenomic model, and the mean AUC was calculated to assess the model. A total of 2042 radiomics features were extracted. Five radiomic features were related to the PFS stratification of lung-cancer patients with SBRT. T-stage and overall stages (TNM) were independent factors for predicting PFS stratification. AUCs under the ROC curve of the radiomics, clinical EGFR, and radiogenomic models were 0.84, 0.67, and 0.86, respectively. The calibration curve shows that the predicted value of the radiogenomic model was in good agreement with the actual value. The decision and influence curve showed that the model had high clinical application values. After Bootstrap validation, the mean AUC of the radiogenomic model was 0.850(95%CI 0.849-0.851). The radiogenomic model based on 18F-FDG PET/CT radiomics and clinical EGFR has good application value in predicting the PFS stratification of lung-cancer patients after SBRT treatment.

CT-based radiomics nomogram may predict who can benefit from adaptive radiotherapy in patients with local advanced-NSCLC patients

BackgroundAlthough adaptive radiotherapy (ART) has many advantages, ART is not universal in the clinical appliance due to the consumption of a lot of labor, and economic burden. It is necessary to explore a CT stimulation-based radiomics model for screening who can get more benefits from ART in locally advanced non-small cell lung cancer (NSCLC) patients. Method183 cases of NSCLC patients receiving concurrent chemoradiotherapy with an adaptive approach were enrolled as a primary cohort, while 28 cases from another hospital served as an independent external validation cohort. Tumor regression assessment was conducted based on GTV reduction (Criteria A) or according to RECIST Version 1.1(Criteria B). The radiomics features were extracted by the “PyRadiomics” package and further screened by the LASSO method. Then, logistic regression was used to establish the model. Bootstrap and external validation were applied to verify the stability of the model. The receiver operating characteristic (ROC) curve was delineated to assess the predictive efficacy of the radiomics model. Dose-volume histograms were quantitatively compared between the initial and composite ART plans. Clinical endpoints included overall survival (OS) and progression-free survival (PFS). ResultThere were no significant differences in clinical features between tumor regression-resistant (RR) and tumor regression-sensitivity (RS) groups. The AUC values of the Criteria A model and Criteria B model were 0.767 and 0.771, respectively. Bootstrapping validation and external validation confirmed the stability of models. In all patients, there was a significant benefit of ART in the lung, heart, cord, and esophagus compared to non-ART, particularly in RS patients. Furthermore, PFS and OS from ART were significantly longer in RS as defined by Criterion B than in RR patients with the same ART application. ConclusionCT-based radiomics can screen out the patients who can gain more benefits from ART, which contribute to guiding and popularizing the application of ART strategy in the clinic within economic benefits and feasibility.