Predictor Of Clinical Outcome Research Articles

Anatomic Reduction of Greater Tuberosity Fragment for Shoulder Hemiarthroplasty: a Predictor of Good Clinical Outcome.

Proximal humerus fractures account for four-five % of all fractures. Shoulder hemiarthroplasty is indicated for complex fractures with high complication rates when treated with ORIF. This study aims to evaluate the correlation between the proper intraoperative tuberosity reduction, and the mid-to-long-term clinical outcome in a series of patients treated with hemiarthroplasty after proximal humerus fracture. Forty-one patients with proximal humerus fractures who underwent hemiarthroplasty surgery between July 2009 and December 2019 were retrospectively reviewed. Quantitative analysis of the reduction of the tuberosities was performed on postoperative X-rays focusing on the distance between reconstructed greater tuberosity and the apex of the head of the prosthesis, (head-tuberosity distance), and contact between tuberosity and humerus diaphysis. The University of California Los Angeles Score (UCLA) was calculated for each patient. The mean time to surgery was 6.29 ± 2.8 days (range 2-18 days). Nine patients out of 41 (22%) had non anatomic tuberosity, and 32 (78%) were anatomic reduced. The UCLA score at the final follow-up was good and excellent (≥27) in 27 patients (66%), and poor (<27) in 14 (34%). A significant correlation was observed between proper tuberosity reduction and good/excellent UCLA scores (P<0.001). Hemiarthroplasty is a valid and reliable technique for the treatment of proximal humerus fracture not eligible for internal fixation, with high risk of failure. The proper tuberosity reconstruction, paying special attention to the HTD and the contact between the cortical of the humeral diaphysis and the reconstructed tuberosity, is essential to reach a good clinical outcome.

Analyzing the impact of heavy metal exposure on osteoarthritis and rheumatoid arthritis: an approach based on interpretable machine learning.

This investigation leverages advanced machine learning (ML) techniques to dissect the complex relationship between heavy metal exposure and its impacts on osteoarthritis (OA) and rheumatoid arthritis (RA). Utilizing a comprehensive dataset from the National Health and Nutrition Examination Survey (NHANES) spanning from 2003 to 2020, this study aims to elucidate the roles specific heavy metals play in the incidence and differentiation of OA and RA. Employing a phased ML strategy that encompasses a range of methodologies, including LASSO regression and SHapley Additive exPlanations (SHAP), our analytical framework integrates demographic, laboratory, and questionnaire data. Thirteen distinct ML models were applied across seven methodologies to enhance the predictability and interpretability of clinical outcomes. Each phase of model development was meticulously designed to progressively refine the algorithm's performance. The results reveal significant associations between certain heavy metals and an increased risk of arthritis. The phased ML approach enabled the precise identification of key predictors and their contributions to disease outcomes. These findings offer new insights into potential pathways for early detection, prevention, and management strategies for arthritis associated with environmental exposures. By improving the interpretability of ML models, this research provides a potent tool for clinicians and researchers, facilitating a deeper understanding of the environmental determinants of arthritis.

Hematological Parameters and Comorbidities in COVID-19: Insights into Clinical Profiles and Outcome Predictors.

The global pandemic, known as the coronavirus disease 2019 (COVID-19) and caused by the severe acute respiratory syndrome, coronavirus 2 (SARS-CoV-2), poses a significant threat, particularly to individuals with comorbidities such as hypertension, chronic obstructive pulmonary disease (COPD), diabetes, HIV, cardiovascular disease (CVD), and cancer. This descriptive retrospective study investigates the impact of comorbidities on COVID-19-positive patients. The study includes individuals that were tested positive for SARS-CoV-2 via polymerase chain reaction at the Security Forces Hospital, Makkah, KSA, between February, 2022, and June, 2022. A total of 208 patients (107 males, 101 females) were examined, and the laboratory results revealed normal parameters. An analysis indicates that 86.5% of the patients were discharged, 2.9% remained hospitalized, and 10.6% succumbed to the disease, indicating a 10.6% mortality rate among comorbid COVID-19-positive patients. Notably, the study identifies specific comorbidities (chronic kidney disease, diabetes mellitus, hypertension) and changes in laboratory parameters (red blood cells, hemoglobin, C-reactive protein, white blood cells, ferritin, D-dimer, ALT, troponin, LDH, neutrophils) associated with ICU admission during hospitalization. This study underscores the critical impact of comorbidities, such as chronic kidney disease, diabetes, and hypertension, on the clinical outcomes of COVID-19-positive patients. The identification of specific laboratory parameters linked with ICU admission provides valuable insights for risk stratification and tailored management strategies.

The predictive role of N-terminal pro-B-type natriuretic peptide in assessing outcomes for atrial fibrillation patients, with or without heart failure: a comprehensive systematic review and meta-analysis

Background and purpose: Brain natriuretic peptide (BNP) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) are commonly used to predict clinical outcomes in patients with heart failure (HF). The prognostic role of BNP/NT-proBNP in patients with atrial fibrillation (AF) and comorbid HF is controversial. The current study aimed to understand the clinical importance of BNP/NT-proBNP measurement in predicting the outcomes of AF patients regardless of HF status. Methods: This is a systematic review and meta-analysis. A comprehensive literature search was conducted using PubMed, EBSCOHost, Cochrane, ScienceDirect, and ClinicalKey. Studies that reported all-cause mortality, stroke/systemic embolic events (SEE)/thromboembolic events (TE), major adverse cardiovascular events (MACE), and major bleeding were included in this study. All-cause mortality was the primary outcome. Studies that reported BNP data but not NT-proBNP were also included. BNP/NT-proBNP is categorized as high and low level based on the highest and lowest groups compared in the included studies. Results: Sixteen studies (n = 45,400) were included in data synthesis: six were post hoc analysis of randomized controlled trials and the remaining were prospective cohort studies. The included studies were published between 2011 and 2022. The follow-up duration ranged from 1.0 to 5.2 years. High level of BNP/NT-proBNP was associated with a significantly increased risk of all-cause mortality (pooled hazard ratio [HR]: 2.26, 95% confidence interval [95% CI]: 1.98–2.56), stroke/SEE/TE (pooled HR: 2.45, 95% CI: 2.07–2.90), and MACE (pooled HR: 2.38, 95% CI: 1.90–2.99) in patients with AF; the pooled HR of major bleeding was 1.17 (95% CI: 1.01–1.36). Sensitivity analysis in patients with AF and HF produced similar results. Conclusions: BNP and NT-proBNP are strong predictors of clinical outcomes in patients with AF regardless of HF.

Compromised dynamic cerebral autoregulation is a hemodynamic marker for predicting poor prognosis even with good recanalization after endovascular thrombectomy.

In patients undergoing endovascular thrombectomy (EVT) with acute ischemic stroke (AIS), dynamic cerebral autoregulation (dCA) may minimize neurological injury from blood pressure fluctuations. This study set out to investigate the function of dCA in predicting clinical outcomes following EVT. 43 AIS of the middle cerebral or internal carotid artery patients underwent with EVT, and 43 healthy individuals (controls) were enrolled in this case control research. The dCA was evaluated using transcranial Doppler 12 h and five days after EVT. The transfer function analysis was used to derive the dCA parameters, such as phase, gain, and coherence. The modified Rankin scale (mRS) at 3 months after EVT was used to assess the clinical outcomes. Thefavorable outcome group was defined with mRS ≤2 and the unfavorable outcome group was defined with mRS score of 3-6. Logistic regression analysis was performed to determine the risk factors of clinical outcomes. A significant impairment in dCA was observed on the ipsilateral side after EVT, particularly in patients with unfavorable outcomes. After 5 days, the ipsilateral phase was associated with poor functional outcomes (adjusted odds ratio [OR] = 0.911, 95% confidence interval [CI]: 0.854-0.972; P = 0.005) and the area under the curve (AUC) (AUC, 0.878, [95% CI: 0.756-1.000] P < 0.001) (optimal cutoff, 35.0°). Phase change was an independent predictor of clinical outcomes from 12 h to 5 days after EVT (adjusted OR = 1.061, 95% CI: 1.016-1.109, P = 0.008). dCA is impaired in patients with AIS after EVT. Change in dCA could be an independent factor related to the clinical outcomes.

A Novel Feature Engineering Method Based on Latent Representation Learning for Radiomics: Application in NSCLC Subtype Classification.

Radiomics refers to the high-throughput extraction of quantitative features from medical images, and is widely used to construct machine learning models for the prediction of clinical outcomes, while feature engineering is the most important work in radiomics. However, current feature engineering methods fail to fully and effectively utilize the heterogeneity of features when dealing with different kinds of radiomics features. In this work, latent representation learning is first presented as a novel feature engineering approach to reconstruct a set of latent space features from original shape, intensity and texture features. This proposed method projects features into a subspace called latent space, in which the latent space features are obtained by minimizing a unique hybrid loss function including a clustering-like loss and a reconstruction loss. The former one ensures the separability among each class while the latter one narrows the gap between the original features and latent space features. Experiments were performed on a multi-center non-small cell lung cancer (NSCLC) subtype classification dataset from 8 international open databases. Results showed that compared with four traditional feature engineering methods (baseline, PCA, Lasso and L2,1-norm minimization), latent representation learning could significantly improve the classification performance of various machine learning classifiers on the independent test set (all p<0.001). Further on two additional test sets, latent representation learning also showed a significant improvement in generalization performance. Our research shows that latent representation learning is a more effective feature engineering method, which has the potential to be used as a general technology in a wide range of radiomics researches.

Development of a Novel Comprehensive Hepatocellular Carcinoma Outcome Prognostic Scoring System With Integration of Imaging Features.

Accurate prognostic stratification of hepatocellular carcinoma (HCC) is vital for clinical trial enrollment and treatment allocation. Multiple scoring systems have been created to predict patient survival, but no standardized scoring systems account for radiologic tumor features. We sought to create a generalizable scoring system for HCC which incorporates standardized radiologic tumor features and more accurately predicts overall survival (OS) than established systems. Clinicopathologic parameters were collected from a prospectively collected cohort of patients with HCC treated at a single institution. Imaging studies were evaluated for tumor characteristics. Patients were randomly divided into a training set for identification of covariates that impacted OS and a validation set. Cox models were used to determine the association of various factors with OS and a scoring system was created. We identified 383 patients with HCC with imaging and survival outcomes, n = 255 in the training set and 128 in the validation cohort. Factors associated with OS on multivariate analysis included: tumor margin appearance on CT or MRI (hazard ratio [HR] 1.37, 95% CI, 1.01-1.88) with infiltrative margins portending worse outcomes than encapsulated margins, massive tumor morphology (HR 1.64, 95% CI, 1.06-2.54); >2 lesions (HR 2.06, 95% CI, 1.46-2.88), Child-Turcotte-Pugh class C (HR 3.7, 95% CI, 2.23-6.16), and portal vein thrombus (HR 2.41, 95% CI, 1.71-3.39). A new scoring system was developed and more predictive of OS than other well-established systems. Incorporation of standardized imaging characteristics to established clinical and lab predictors of outcome resulted in an improved predictive scoring system for patients with HCC.

Recurrence risk stratification of hepatocellular carcinomas based on immune gene expression and features extracted from pathological images.

Immune-based therapy is a promising type of treatment for hepatocellular carcinoma (HCC) but has only been partially successful due to the high heterogeneity in HCC tumor. The differences in the degree of tumor cell progression and in the activity of tumor immune microenvironment could lead to varied clinical outcome. Accurate subgrouping for recurrence risk is an approach to address the issue of such heterogeneity. It remains under investigation as whether integrating quantitative whole slide image (WSI) features with the expression profile of immune marker genes can improve the risk stratification, and whether clinical outcome prediction can assist in understanding molecular biology that drives the outcome. We included a total of 231 patients from the Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) project. For each patient, we extracted 18 statistical metrics corresponding to a global region of interest and 135 features regarding nucleus shape from WSI. A risk score was developed using these image features with high-dimensional survival modeling. We also introduced into the model the expression profile of 66 representative marker genes relevant to currently available immunotherapies. We stratified all patients into higher and lower-risk subgroup based on the final risk score selected from multiple models generated, and further investigated underlying molecular mechanisms associated with the risk stratification. One WSI feature and three immune marker genes were selected into the final recurrence-free survival (RFS) prediction model following the best integrated modeling framework. The resultant score showed a significantly improved prediction performance on the test dataset (mean time-dependent AUCs = 0.707) as compared to those of other types (e.g: mean time-dependent AUCs of AJCC tumor stage = 0.525) of input data integration. To assess that the risk score could provide a higher-resolution risk stratification, a lower-risk subgroup (or a higher-risk subgroup) was arbitrarily assigned according to score falling below (or above) the median score. The lower risk subgroup had significantly longer median RFS time than that of the higher-risk patients (median RFS = 903 vs. 265 days, log-rank test p-value< 0.0001). Additionally, the higher-risk subgroup, in contrast to the lower-risk patients were characterized with a significant downregulation of immune checkpoint genes, suppressive signal in tumor immune response pathways, and depletion of CD8 T cells. These observations for the higher-risk subgroup suggest that new targets for adoptive or checkpoint-based combined systemic therapies may be useful. We developed a novel prognostic model to predict RFS for HCC patients, using one feature that can be automatically extracted from routine histopathological images, as well as the expression profiles of three immune marker genes. The methodology used in this paper demonstrates the feasibility of developing prognostic models that provide both useful risk stratification along with valuable biological insights into the underlying characteristics of the subgroups identified.

Initial Diuretic Efficiency as Predictor of Diuretic Resistance and Clinical Outcome in Acute Decompensated Heart Failure

Initial Diuretic Efficiency as Predictor of Diuretic Resistance and Clinical Outcome in Acute Decompensated Heart Failure

Prevalence and Prognostic Value of Non-Alcoholic Fatty Liver Disease in Patients Hospitalized With Decompensated Chronic Heart Failure.

Aim To study the incidence and effect of non-alcoholic fatty liver disease (NAFLD) on clinical outcomes in patients with decompensated chronic heart failure (DCHF).Material and methods The study included 338 patients with NYHA functional class III-IV DCHF (51.2% men, mean age 72.8±11.7 years), arterial hypertension (AH) in 90%, myocardial infarction in 37%, atrial fibrillation in 64%, chronic kidney disease (CKD) in 42%, type 2 diabetes mellitus (T2DM) in 35%, left ventricular ejection fraction (LVEF) &lt;40% in 27%. NAFLD was diagnosed based on the 2021 Clinical Guidelines of the Russian Scientific Medical Society of Therapists and the Scientific Society of Gastroenterologists of Russia. The stage of liver steatosis was determined using transient elastometry with assessment of the controlled attenuation parameter (CAP) of ultrasound (S, dB/m) using a FibroScan device. Threshold CAP values &lt;294 dB/m corresponded to the degree of steatosis: S0; S1, 295-309 dB/m; S2, 310-330 dB/m; S3, ≥331 dB/m.Results NAFLD was diagnosed in 28.9% of patients. The patients were divided into two groups: group 1 included patients with CHF and NAFLD (n=98 (28.9%), 50.0% men) and group 2 included patients with CHF without NAFLD (n=240 (71.0 %), 51.6% men). A multivariate regression analysis showed that independent predictors of NAFLD were systolic blood pressure ≥130 mm Hg (odds ratio (OR), 3.700; p &lt;0.001), history of T2DM (OR, 2.807; p &lt;0.005), and waist circumference &gt;111 cm (OR, 2.530; p &lt;0.012). Patients with CAP ≥331 dB/m (S3) had a worse prognosis during the 2-year follow-up for the composite adverse outcome (all-cause mortality + readmission) (Kaplan-Meier curves - Log-Rank p=0.035).Conclusions NAFLD was detected in almost one-third of patients hospitalized for DCHF. AH, T2DM, and abdominal obesity were associated with a high risk of NAFLD. However, only severe steatosis (S3) was an independent predictor of adverse clinical outcomes during a 2-year period after adjustment for known risk factors.

The use of prognostic scales to assess the effectiveness of the use of anti-cytokine drugs in patients with moderate and severe course of a new coronavirus infection

The aim. To analyze the effectiveness of the use of anti-cytokine drugs (tocilizumab, olokizumab and sarilumab) in a single-center retrospective cohort study based on the prediction of clinical outcomes using prognostic scales, with a single administration in patients with moderate to severe course of a new coronavirus infection.Materials and methods. The retrospective cohort study included three groups of patients with single administration of tocilizumab (65 patients), olokizumab (56 patients) and sarilumab (26 patients). All patients were treated in a repurposed infectious diseases hospital for patients with COVID-19 on the basis of Аlexandro-Mariinskaya Regional Clinical Hospital in the period January- August 2021. Upon admission to the hospital and 2 days after administration of the drug, patients were predicted the severity of the course and outcome using prognostic scales: 4C Mortality Score, COVID-GRAM, SHOCS-COVID.Results. A comparative analysis of the effectiveness of the use of anti-cytokine drugs using the 4C Mortality Score scale revealed a further deterioration in the prognosis of clinical outcome in the groups receiving tocilizumab (p = 0,002) and sarilumab (p = 0,031). When using the COVID-GRAM predictive scale, further deterioration of the prognosis was also noted in the tocilizumab (p = 0,004) and olokizumab (p = 0,005) groups. The SHOCS-COVID scale showed a further deterioration in the prognosis in the tocilizumab group (p = 0,001).Conclusion. The use of drugs based on monoclonal antibodies against IL-6 and its receptors in patients with moderate to severe COVID-19 did not reveal significant positive dynamics in changing the prognosis of clinical outcome 2 days after administration of these drugs.

Predicting disease severity in multiple sclerosis using multimodal data and machine learning.

Multiple sclerosis patients would benefit from machine learning algorithms that integrates clinical, imaging and multimodal biomarkers to define the risk of disease activity. We have analysed a prospective multi-centric cohort of 322 MS patients and 98 healthy controls from four MS centres, collecting disability scales at baseline and 2years later. Imaging data included brain MRI and optical coherence tomography, and omics included genotyping, cytomics and phosphoproteomic data from peripheral blood mononuclear cells. Predictors of clinical outcomes were searched using Random Forest algorithms. Assessment of the algorithm performance was conducted in an independent prospective cohort of 271 MS patients from a single centre. We found algorithms for predicting confirmed disability accumulation for the different scales, no evidence of disease activity (NEDA), onset of immunotherapy and the escalation from low- to high-efficacy therapy with intermediate to high-accuracy. This accuracy was achieved for most of the predictors using clinical data alone or in combination with imaging data. Still, in some cases, the addition of omics data slightly increased algorithm performance. Accuracies were comparable in both cohorts. Combining clinical, imaging and omics data with machine learning helps identify MS patients at risk of disability worsening.

Predictors of parenchymal hematoma and clinical outcome after mechanical thrombectomy in patients with large ischemic core due to large vessel occlusion: a retrospective multicenter study.

The aim of our study was to find predictors of parenchymal hematoma (PH) and clinical outcome after mechanical thrombectomy (MT) in patients with large vessel occlusion (LVO) and baseline large infarct. The databases of 16 stroke centers were retrospectively screened for patients with anterior circulation LVO and baseline Alberta Stroke Program Early CT Score (ASPECTS) ≤5 that received MT. Procedural parameters, including the number of passes during first and second technique of MT, were recorded. Outcome measures were occurrence of PH type 2 and any type of PH after MT, and the 90-day modified Rankin Scale (mRS) score of 0-3 and 0-2. In total, 408 patients were available for analysis. A higher number of passes in the second technique was predictive of PH type 2 (odds ratio (OR) - 3.204, 95% confidence interval (CI) 1.140 to 9.005), whereas procedure conducted under general anesthesia was associated with lower risk (OR 0.127, 95% CI 0.002 to 0.808). The modified thrombolysis in cerebral infarction grade 2c-3 was associated with the mRS score 0-3 (OR 3.373, 95% CI 1.891 to 6.017), whereas occurrence of PH type 2 was predictive of unfavorable outcome (OR 0.221, 95% CI 0.063 to 0.773). Similar results were found for the mRS score 0-2 outcome measure. In patients with large ischemic core, a higher number of passes during MT and procedure not conducted under general anesthesia are associated with increased rate of PH type 2, that negatively impact the clinical outcome. Our data outline a delicate balance between the need of a complete recanalization and the risk of PH following MT.

Who Responds to an Adaptive Intervention for Adolescents With Anorexia Nervosa Being Treated With Family-Based Treatment? Outcomes From a Randomized Clinical Trial

Anorexia nervosa (AN) is a serious psychiatric disorder with high morbidity and mortality. The current evidence supports the use of family-based treatment (FBT), but recovery rates are only about 40%. Improving treatment outcomes among adolescents with AN will save lives, improve health, and prevent chronicity. This study examined the relative efficacy of adding intensive parental coaching (IPC) to standard FBT for patients who do not respond by weight gain of 2.4 kg by session 4, a clinical predictor of outcome at the end of treatment, to improve remission rates (>94% of expected mean body mass index). The study recruited 107 participants and their families from across the United States; 69 participants failed to respond early and were randomly assigned to continue with standard FBT or to receive 3 sessions of IPC. Participants were adolescents (ages 12-18) meeting DSM-5 criteria for AN; 6.5% were male, and 11% were Hispanic. Main outcomes were mean body mass index >94% expected for age, height, and sex. Secondary outcomes included change in eating-related cognitions. Adding IPC to early nonresponders did not improve outcomes except for participants whose parents demonstrated low parental self-efficacy at baseline (moderator). Early weight gain of 2.4 kg by session 4 was replicated as a predictor of end of treatment remission. Parental self-efficacy moderates IPC as an adaptive treatment for adolescents with AN. Baseline parental self-efficacy assessment can be used to identify families most likely to benefit from adding IPC to FBT. Future studies should consider earlier interventions to improve early response rates. Anorexia nervosa is a serious psychiatric disorder. While family-based treatment (FBT) has the largest evidence base for adolescents with anorexia, recovery rates are only about 40%. This study investigated the addition of 3 sessions of intensive parental coaching intervention (IPC) to FBT among youth with anorexia who did not gain adequate weight early in treatment, a predictor of recovery by the end of treatment. Youth with inadequate weight gain were randomized to either receive FBT with IPC or FBT as usual. Overall, adding IPC did not improve outcomes among youth with anorexia. However among those whose parents demonstrated low parental self-efficacy at baseline, youth who received FBT with IPC had higher remission rates than youth who received FBT alone. Intensive parental coaching shows promise for improving outcomes among youth with anorexia whose parents report low parental self-efficacy. Adaptive Treatment for Adolescent Anorexia Nervosa; https://clinicaltrials.gov/; NCT03097874.

Role of Intestinal Inflammation and Permeability in Patients with Acute Heart Failure.

Background and Objectives: Heart failure (HF) represents a major health burden. Although several treatment regimens are available, their effectiveness is often unsatisfactory. Growing evidence suggests a pivotal role of the gut in HF. Our study evaluated the prognostic role of intestinal inflammation and permeability in older patients with acute HF (AHF), and their correlation with the common parameters traditionally used in the diagnostic-therapeutic management of HF. Materials and Methods: In a single-center observational, prospective, longitudinal study, we enrolled 59 patients admitted to the Emergency Department (ED) and then hospitalized with a diagnosis of AHF, from April 2022 to April 2023. Serum routine laboratory parameters and transthoracic echocardiogram were assayed within the first 48 h of ED admission. Fecal calprotectin (FC) and both serum and fecal levels of zonulin were measured, respectively, as markers of intestinal inflammation and intestinal permeability. The combined clinical outcome included rehospitalizations for AHF and/or death within 90 days. Results: Patients with increased FC values (>50 µg/g) showed significantly worse clinical outcomes (p < 0.001) and higher median levels of NT-proBNP (p < 0.05). No significant correlation was found between the values of fecal and serum zonulin and the clinical outcome. Median values of TAPSE were lower in those patients with higher values of fecal calprotectin (p < 0.05). After multivariate analysis, NT-proBNP and FC values > 50 µg/g resulted as independent predictors of a worse clinical outcome. Conclusions: Our preliminary finding supports the hypothesis of a close relationship between the gut and heart, recognizing in a specific marker of intestinal inflammation such as FC, an independent predictive prognostic role in patients admitted for AHF. Further studies are needed to confirm these results, as well as investigate the reliability of new strategies targeted at modulation of the intestinal inflammatory response, and which are able to significantly impact the course of diseases, mainly in older and frail patients.

Predicting Postoperative Hospital Stays Using Nursing Narratives and the Reverse Time Attention (RETAIN) Model: Retrospective Cohort Study.

Nursing narratives are an intriguing feature in the prediction of short-term clinical outcomes. However, it is unclear which nursing narratives significantly impact the prediction of postoperative length of stay (LOS) in deep learning models. Therefore, we applied the Reverse Time Attention (RETAIN) model to predict LOS, entering nursing narratives as the main input. A total of 354 patients who underwent ovarian cancer surgery at the Seoul National University Bundang Hospital from 2014 to 2020 were retrospectively enrolled. Nursing narratives collected within 3 postoperative days were used to predict prolonged LOS (≥10 days). The physician's assessment was conducted based on a retrospective review of the physician's note within the same period of the data model used. The model performed better than the physician's assessment (area under the receiver operating curve of 0.81 vs 0.58; P=.02). Nursing narratives entered on the first day were the most influential predictors in prolonged LOS. The likelihood of prolonged LOS increased if the physician had to check the patient often and if the patient received intravenous fluids or intravenous patient-controlled analgesia late. The use of the RETAIN model on nursing narratives predicted postoperative LOS effectively for patients who underwent ovarian cancer surgery. These findings suggest that accurate and interpretable deep learning information obtained shortly after surgery may accurately predict prolonged LOS.

Analysis of Extracranial Cerebrovascular Injuries: Clinical Predictors of Management and Outcomes

Optimal management of traumatic extracranial cerebrovascular injuries (ECVIs) remains undefined. We sought to evaluate the factors that influence management and neurologic outcomes (stroke and brain death) following traumatic ECVI. A retrospective review of a single level 1 trauma center's prospectively maintained data registry of patients older than 18years of age with a diagnosis of ECVI was performed from 2013 to 2019. Injuries limited to the external carotid artery were excluded. Patient demographics, type of injury, timing of presentation, Biffl Classification of Cerebrovascular Injury Grade, Injury Severity Score (ISS), and Abbreviated Injury Scale were documented. Ultimate treatments (medical management and procedural interventions) and brain-related outcomes (stroke and brain death) were recorded. ECVIs were identified in 96 patients. The primary mechanism of injury was blunt trauma (89.5% vs. 10.5%, blunt versus penetrating), with 70 cases (66%) of vertebral artery injury and 37 cases of carotid artery injury. Treatments included vascular intervention (6.5%) and medical management (93.5%). Overall outcomes included ipsilateral ischemic stroke (29%) and brain death (6.5%). In the carotid group, vascular intervention was associated with higher Biffl grades (mean Biffl 3.17 vs. 2.23; P=0.087) and decreased incidence of brain death (0% vs. 19%, P=0.006), with no difference seen in ISS scores. Brain death was associated with higher ISS scores (40.29 vs. 24.17, P=0.01), lower glascow coma score on arrival (3.57 vs. 10.63, P<0.001), and increased rates of ischemic stroke (71% vs. 30%, P=0.025). In the vertebral group, neither Biffl grade nor ISS were associated with treatment or outcomes. Regarding the timing of stroke in ECVI, there was no significant difference in the time from presentation to cerebral infarction between the carotid and vertebral artery groups (24.7hr vs. 21.20hr, P=0.739). After this window, 98% of the ECVI cases demonstrated no further aneurysmal degeneration or new neurological deficits beyond the early time period (mean follow-up 9.7months). Blunt cerebrovascular injuries should be viewed distinctly in the carotid and vertebral territories. In cases of injury to the carotid artery, Biffl grade and ISS score are associated with surgical intervention and neurologic events, respectively; vertebral artery injuries did not share this association. Neurologic deficits were detected in a similar time frame between the carotid artery and the vertebral artery injury groups and both groups had rare late neurologic events.

Prediction of adverse clinical outcomes in pregnant women with severe and extremely severe forms of coronavirus infection

The objective was to identify prognostic criteria for unfavorable outcome in pregnant women with severe and extremely severe forms of COVID-19 and to build a model for predicting clinical outcome.Materials and methods. The cohort single-center retrospective study was conducted, which included 83 patients who were treated in the intensive care unit (ICU) from January 1 to December 31, 2021. Of these, 13 patients had an unfavorable outcome – death, and 70 patients with a successful outcome – recovery. The differences in the main clinical and laboratory parameters of patients of both groups during hospitalization in the ICU and on the 3rd day of treatment (Δ – delta) were analyzed.Results. The Cox regression analysis identified laboratory parameters, the difference of which (Δ) on admission to the ICU and on the 3rd day of treatment is associated with the development of the unfavorable outcome (death). These indicators were used as variables in a linear regression equation. The equation for calculating the prognostic index met the criteria of a statistically significant model (sensitivity 84.6 %, specificity 85.7 %, area under the operating characteristic curve (AUROC – Area Under Receiver Operator Curve) – 0.959 (95 % confidence interval [95 % CI] 0.918 – 1.0).Conclusion. The calculation of the prognostic index can be an additional clinical tool that allows one to predict the development of an unfavorable outcome, concentrate the work of a multidisciplinary team, attract additional reserves of a medical institution and/or evacuate such patients to high-level hospitals.

Clinical significance of serum lactate and lactate dehydrogenase levels for disease severity and clinical outcomes in patients with colorectal cancer admitted to the intensive care unit

ObjectiveSerum lactate (LA) and lactate dehydrogenase (LDH) levels have a major impact on the clinical treatment of malignant tumors and critically ill patients. Nevertheless, the assessment of disease severity in oncology patients admitted to the intensive care unit (ICU) remains incomplete when considering the serum LA and LDH levels. This study aimed to investigate the significance of serum LDH and LA levels in assessing disease severity and predicting clinical outcomes in patients with colorectal cancer (CRC) admitted to the ICU. MethodsThis retrospective study included patients with CRC who were admitted to the ICU between January 2017 and December 2022. The patients were divided into three groups based on the tumor treatment methods they had received within 3 months before ICU admission: post-chemotherapy group, post-surgery group, and palliative treatment group. The association between serum LA and LDH levels and disease severity and clinical outcomes was analyzed. ResultsOf 137 patients with CRC admitted to the ICU were finally studied. Patients in the post-chemotherapy group exhibited higher serum LA and LDH levels compared to those in the other two groups. Additionally, they had higher Acute Physiology and Chronic Health Evaluation (APACHE) II scores, longer ICU length of stay, and a higher 30-day mortality. We found a significant positive correlation between serum LA levels and APACHE II scores as well as ICU length of stay and 30-day mortality. In contrast, we only observed a significant positive correlation between serum LDH levels and disease severity in the post-chemotherapy group, whereas no significant correlation between LDH levels and 30-day mortality in any of the three groups. ConclusionOur study concludes that elevated serum LA levels, rather than LDH levels, are more effective in assessing disease severity and could be used as predictors for clinical outcomes in patients with CRC admitted to the ICU.

Incremental prognostic value of speckle tracking echocardiography and early follow-up echo assessment in predicting left ventricular recovery after reperfusion for ST-segment elevation myocardial infarction (STEMI).

Up to 50% of patients do not achieve significant left ventricular ejection fraction (LVEF) recovery after primary percutaneous intervention (PPCI) for STEMI. We aimed to identify the echocardiographic predictors for LVEF recovery and assess the value of early follow-up echocardiography (Echo) in risk assessment of post-myocardial infarction (MI) patients. One hundred one STEMI patients undergoing PPCI were enrolled provided EF below 50%. Baseline echocardiography assessed LVEF, volumes, wall motion score index (WMSI), global longitudinal strain (GLS), global circumferential strain (GCS), and E/e'. Follow-up echocardiography after 6weeks reassessed left ventricular volumes, LVEF and GLS.GCS was not assessed at follow up. Patients were classified into recovery and non-recovery groups. Predictors of LVEF recovery and major adverse cardiovascular events (MACE) at 6 months were analysed. The mean change of EF was 8.04±3.32% in group I versus -.39±5.09 % in group II (p<.001). Recovered patients had better baseline GLS, baseline GCS, E/e', and follow-up GLS. Multivariate regression analysis revealed E/e', GCS, and follow-up GLS after 6weeks to be strong independent predictors for LVEF recovery. Composite MACE was considerably higher in group II (32.7% vs. 4.1%, p<.001) mainly driven by higher heart failure hospitalisation Multivariate regression analysis revealed baseline GLS, E/e', and ejection fraction (EF) percentage recovery as strong independent predictors for MACE. Multiparametric echocardiographic approach incorporating LVEF, strain parameters, and diastolic function could allow early optimal risk stratification after STEMI treated with PPCI. Follow-up GLS and LVEF percentage change are the strongest predictors for early LV recovery and long term clinical outcome, respectively.