predictive values
Recently Published Documents





2022 ◽  
Vol 61 ◽  
pp. 101025
Hsin-Te Chang ◽  
Ming-Jang Chiu ◽  
Ta-Fu Chen ◽  
Meng-Ying Liu ◽  
Wan-Chun Fan ◽  

2022 ◽  
Vol 11 ◽  
Lingge Yang ◽  
Yuan Wu ◽  
Huan Xu ◽  
Jingnan Zhang ◽  
Xinjie Zheng ◽  

ObjectiveThis study was conducted in order to establish a long non-coding RNA (lncRNA)-based model for predicting overall survival (OS) in patients with lung adenocarcinoma (LUAD).MethodsOriginal RNA-seq data of LUAD samples were extracted from The Cancer Genome Atlas (TCGA) database. Univariate Cox survival analysis was performed to select lncRNAs associated with OS. The least absolute shrinkage and selection operator (LASSO) regression analysis and multivariate Cox analysis were performed for building an OS-associated lncRNA prognostic model. Moreover, receiver operating characteristic (ROC) curves were generated to assess predictive values of the hub lncRNAs. Consequently, qRT-PCR was conducted to validate its prognostic value. The potential roles of these lncRNAs in immunotherapy and anti-angiogenic therapy were also investigated.ResultsThe lncRNA-associated risk score of OS (LARSO) was established based on the LASSO coefficient of six individual lncRNAs, including CTD-2124B20.2, CTD-2168K21.1, DEPDC1-AS1, RP1-290I10.3, RP11-454K7.3, and RP11-95M5.1. Kaplan–Meier analysis revealed that LUAD patients with higher LARSO values had a shorter OS. Furthermore, a new risk score (NRS), including LARSO, stage, and N stage, could better predict the prognosis of LUAD patients compared with LARSO alone. Evaluation of the prognostic model in our cohort demonstrated that patients with higher scores had a worse prognosis. In addition, correlation analysis between these six lncRNAs and immune checkpoints or anti-angiogenic targets suggested that LUAD patients with high LARSO might not be sensitive to immunotherapy or anti-angiogenic therapy.ConclusionsThis robust six-lncRNA prognostic signature may be used as a novel and powerful prognostic biomarker for lung adenocarcinoma.

Pier Paolo Mattogno ◽  
Valerio M. Caccavella ◽  
Martina Giordano ◽  
Quintino G. D'Alessandris ◽  
Sabrina Chiloiro ◽  

Abstract Purpose Transsphenoidal surgery (TSS) for pituitary adenomas can be complicated by the occurrence of intraoperative cerebrospinal fluid (CSF) leakage (IOL). IOL significantly affects the course of surgery predisposing to the development of postoperative CSF leakage, a major source of morbidity and mortality in the postoperative period. The authors trained and internally validated the Random Forest (RF) prediction model to preoperatively identify patients at high risk for IOL. A locally interpretable model-agnostic explanations (LIME) algorithm is employed to elucidate the main drivers behind each machine learning (ML) model prediction. Methods The data of 210 patients who underwent TSS were collected; first, risk factors for IOL were identified via conventional statistical methods (multivariable logistic regression). Then, the authors trained, optimized, and audited a RF prediction model. Results IOL reported in 45 patients (21.5%). The recursive feature selection algorithm identified the following variables as the most significant determinants of IOL: Knosp's grade, sellar Hardy's grade, suprasellar Hardy's grade, tumor diameter (on X, Y, and Z axes), intercarotid distance, and secreting status (nonfunctioning and growth hormone [GH] secreting). Leveraging the predictive values of these variables, the RF prediction model achieved an area under the curve (AUC) of 0.83 (95% confidence interval [CI]: 0.78; 0.86), significantly outperforming the multivariable logistic regression model (AUC = 0.63). Conclusion A RF model that reliably identifies patients at risk for IOL was successfully trained and internally validated. ML-based prediction models can predict events that were previously judged nearly unpredictable; their deployment in clinical practice may result in improved patient care and reduced postoperative morbidity and healthcare costs.

2022 ◽  
Vol 8 (1) ◽  
pp. 287-295
Manjunath G N

Background: PIH is associated with increased vascular resistance and decreased utero -placental perfusion resulting in an increased incidence of foetal hypoxia and impaired foetalgrowth.The objective of this study was to assess the diagnostic performance of S/D ratio, resistance index(RI), pulsatility index (PI) and cerebro-placental ratio (CPR) in the prediction of adverse perinatal outcome in PIH and IUGR. Objective: is to determine S/D ratio, RI, PI, CPR and asses their diagnostic values in the prediction of adverse perinatal outcome.Material& Methods:50 pregnant patients with PIH and IUGR, beyond 28 weeks of gestation, were prospectively studied at P k das institute of medical college,vaniyamkulamand subjected for Doppler study of the umbilical artery and foetal middle cerebral artery. The abnormality of above parameters was correlated with the major adverse perinatal outcome.Results:Patients with abnormal Doppler parameters had a poor perinatal outcome, compared to those who had normal Doppler study. The cerebro-placental ratios(CPR) had the sensitivity and specificity, positive and negative predictive values of 95%,76%,73%,95% respectively with Kappa value of o .68(good agreement) and p value of .000 which was statistically significant, for the prediction of major adverse perinatal outcome.Conclusions:This study shows that Doppler study of umbilical and foetal middle cerebral artery can reliably predict the neonatal morbidity and helpful in determining the optimal time of delivery in complicated pregnancies. The CPR is more accurate than the independent evaluation of S/D, RI, PI, in identifying foetus with adverse perinatal outcome.

BJGP Open ◽  
2022 ◽  
pp. BJGPO.2021.0141
Anna Ruiz-Comellas ◽  
Pere Roura Poch ◽  
Glòria Sauch Valmaña ◽  
Víctor Guadalupe-Fernández ◽  
Jacobo Mendioroz Peña ◽  

Backgroundamong the manifestations of COVID-19 are Taste and Smell Disorders (TSDs).AimThe aim of the study is to evaluate the sensitivity and specificity of TSDs and other associated symptoms to estimate predictive values for determining SARS-CoV-2 infection.Design and settingRetrospective observational study.Methodsa study of the sensitivity and specificity of TSDs has been carried out using the Polymerase Chain Reaction (PCR) test for the diagnosis of SARS-CoV-2 as the Gold Standard value. Logistic regressions adjusted for age and sex were performed to identify additional symptoms that might be associated with COVID-19.Resultsthe results are based on 226 healthcare workers with clinical symptoms suggestive of COVID-19, 116 with positive PCR and 111 with negative PCR. TSDs had an OR of 12.43 (CI 0.95 6.33–26.19), sensitivity 60.34% and specificity 89.09%. In the logistic regression model, the association of TSD, fever or low-grade fever, shivering, dyspnoea, arthralgia and myalgia obtained an area under the curve of 85.7% (CI 0.95: 80.7 % - 90.7 %), sensitivity 82.8 %, specificity 80% and positive predictive values 81.4% and negative 81.5%.ConclusionsTSDs are a strong predictor of COVID-19. The association of TSD, fever, low-grade fever or shivering, dyspnoea, arthralgia and myalgia correctly predicts 85.7% of the results of the COVID-19 test.

Yingchun Liu ◽  
Lin Chen ◽  
Jia Zhan ◽  
Xuehong Diao ◽  
Yun Pang ◽  

Objective: To explore inter-observer agreement on the evaluation of automated breast volume scanner (ABVS) for breast masses. Methods: A total of 846 breast masses in 630 patients underwent ABVS examinations. The imaging data were independently interpreted by senior and junior radiologists regarding the mass size ([Formula: see text][Formula: see text]cm, [Formula: see text][Formula: see text]cm and total). We assessed inter-observer agreement of BI-RADS lexicons, unique descriptors of ABVS coronal planes. Using BI-RADS 3 or 4a as a cutoff value, the diagnostic performances for 331 masses with pathological results in 253 patients were assessed. Results: The overall agreements were substantial for BI-RADS lexicons ([Formula: see text]–0.779) and the characteristics on the coronal plane of ABVS ([Formula: see text]), except for associated features ([Formula: see text]). However, the overall agreement was moderate for orientation ([Formula: see text]) for the masses [Formula: see text][Formula: see text]cm. The agreements were substantial to be perfect for categories 2, 3, 4, 5 and overall ([Formula: see text]–0.918). However, the agreements were moderate to substantial for categories 4a ([Formula: see text]), 4b ([Formula: see text]), and 4c ([Formula: see text]), except for category 4b of the masses [Formula: see text][Formula: see text]cm ([Formula: see text]). Moreover, for radiologists 1 and 2, there were no significant differences in sensitivity, specificity, accuracy, positive and negative predictive values with BI-RADS 3 or 4a as a cutoff value ([Formula: see text] for all). Conclusion: ABVS is a reliable imaging modality for the assessment of breast masses with good inter-observer agreement.

2022 ◽  
Vol 3 ◽  
Elham Jamshidi ◽  
Amirhossein Asgary ◽  
Nader Tavakoli ◽  
Alireza Zali ◽  
Soroush Setareh ◽  

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission.Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP).Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset.Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

2022 ◽  
pp. emermed-2021-211823
Keita Shibahashi ◽  
Kazuhiro Sugiyama ◽  
Takuto Ishida ◽  
Yuichi Hamabe

BackgroundThe duration from collapse to initiation of cardiopulmonary resuscitation (no-flow time) is one of the most important determinants of outcomes after out-of-hospital cardiac arrest (OHCA). Initial shockable cardiac rhythm (ventricular fibrillation or ventricular tachycardia) is reported to be a marker of short no-flow time; however, there is conflicting evidence regarding the impact of initial shockable cardiac rhythm on treatment decisions. We investigated the association between initial shockable cardiac rhythm and the no-flow time and evaluated whether initial shockable cardiac rhythm can be a marker of short no-flow time in patients with OHCA.MethodsPatients aged 18 years and older experiencing OHCA between 2010 and 2016 were selected from a nationwide population-based Japanese database. The association between the no-flow time duration and initial shockable cardiac rhythm was evaluated. Diagnostic accuracy was evaluated using the sensitivity, specificity and positive predictive value.ResultsA total of 177 634 patients were eligible for the analysis. The median age was 77 years (58.3%, men). Initial shockable cardiac rhythm was recorded in 11.8% of the patients. No-flow time duration was significantly associated with lower probability of initial shockable cardiac rhythm, with an adjusted OR of 0.97 (95% CI 0.96 to 0.97) per additional minute. The sensitivity, specificity and positive predictive value of initial shockable cardiac rhythm to identify a no-flow time of <5 min were 0.12 (95% CI 0.12 to 0.12), 0.88 (95% CI 0.88 to 0.89) and 0.35 (95% CI 0.34 to 0.35), respectively. The positive predictive values were 0.90, 0.95 and 0.99 with no-flow times of 15, 18 and 28 min, respectively.ConclusionsAlthough there was a significant association between initial shockable cardiac rhythm and no-flow time duration, initial shockable cardiac rhythm was not reliable when solely used as a surrogate of a short no-flow time duration after OHCA.

2022 ◽  
Vol 11 ◽  
Wojciech Blogowski ◽  
Katarzyna Dolegowska ◽  
Anna Deskur ◽  
Barbara Dolegowska ◽  
Teresa Starzynska

Eicosanoids are bioactive lipids derived from arachidonic acid, which have emerged as key regulators of a wide variety of pathophysiological processes in recent times and are implicated as mediators of gastrointestinal cancer. In this study, we investigated the systemic levels of lipoxygenase (LOX)-derived lipoxin A4 and B4, together with resolvin D1 and D2 in patients with pancreatic adenocarcinoma (n = 68), as well as in healthy individuals (n = 32). Systemic concentrations of the aforementioned immunoresolvents were measured using an enzyme-linked immunosorbent assay (ELISA). In this study, we observed that compared with concentrations in healthy individuals, the peripheral concentrations of the aforementioned eicosanoids were significantly elevated (2- to 10-fold) in patients with pancreatic cancer (in all cases p&lt;0.00001). No significant association was observed between eicosanoid levels and the TNM clinical staging. Furthermore, we observed no significant differences in concentrations of the analyzed bioactive lipids between patients diagnosed with early-stage (TNM stage I-II) and more advanced disease (TNM stage III-IV). Receiver operating characteristic (ROC) curve analysis of each aforementioned immunoresolvent showed area under the curve values ranging between 0.79 and 1.00. Sensitivity, specificity, as well as positive and negative predictive values of the eicosanoids involved in the detection/differentiation of pancreatic adenocarcinoma ranged between 56.8% and 100%. In summary, our research is the first study that provides clinical evidence to support a systemic imbalance in LOX-derived lipoxins and resolvins as the mechanism underlying the pathogenesis of pancreatic adenocarcinoma. This phenomenon occurs regardless of the clinical TNM stage of the disease. Furthermore, our study is the first to preliminarily highlight the role of peripheral levels of immunoresolvents, particularly resolvin D1, as potential novel biomarkers of pancreatic cancer in humans.

2022 ◽  
Dominik Lutter ◽  
Stephan Sachs ◽  
Marc Walter ◽  
Leigh Perreault ◽  
Darcy Kahn ◽  

Although insulin resistance often leads to Type 2 Diabetes Mellitus (T2D), its early stages remain often unrecognized thus reducing the probability of successful prevention and intervention. Moreover, treatment efficacy is affected by the genetics of the individual patient. To identify potential candidate genes for the prediction of diabetes risk and intervention response we linked genetic expression profiles of human skeletal muscle and intermuscular adipose tissue (IMAT) to fasting glucose (FG) and glucose infusion rate (GIR). We found that genes with a strong association to these measures clustered into three distinct expression patterns. Their predictive values for insulin resistance varied strongly between muscle and IMAT. Moreover, we discovered that individual genetic expression based classifications may differ from those classifications based predominantly on clinical parameters indicating a potential incomplete patient stratification. Out of the 15 top hit candidate genes, we identified ST3GAL2, AASS, ARF1 and the transcription factor SIN3A as novel candidates for a refined diabetes risk and intervention response prediction. Our results confirm that disease progression and a successful intervention depend on individual genetics. We anticipate that our findings may lead to a better understanding and prediction of the individual diabetes risk and may help to develop individualized intervention strategies.

Sign in / Sign up

Export Citation Format

Share Document