False Negative Values Research Articles

Machine Learning-Based Profit Modeling for Credit Card Underwriting: Implications for Credit Risk

Accurate profit modeling is crucial for effective credit risk management in credit card underwriting. This study explores how machine learning methods can improve profit models in credit card underwriting, using data from a major Chinese bank as a case study. We employed three primary machine learning algorithms—Random Forest, Gradient Boosting Trees, and Neural Networks—to analyze a credit card customer dataset comprising 500,000 customers and 8 million transaction records. Model performance was evaluated using 10-fold cross-validation. The results show that the Gradient Boosting Trees model outperformed the others across all evaluation metrics. Specifically, the Gradient Boosting Trees model achieved an accuracy of 89.2%, a recall of 85.3%, an F1 score of 87.1%, and an AUC of 0.927, significantly surpassing the other models. Furthermore, the confusion matrix results indicated that the Gradient Boosting Trees model had the highest true positive and true negative values, and the lowest false positive and false negative values, further validating its superior classification performance. In summary, the Gradient Boosting Trees model demonstrated higher accuracy and stability in predicting profit in credit card underwriting, providing a robust basis for financial institutions to select appropriate machine learning models for credit risk management.

Timing of breast biopsy and axillary ultrasound does not affect the false positive rate of the axillary ultrasound

BackgroundThe determination of axillary lymph node metastases is an important component of breast cancer treatment planning. Lymph node biopsies can be performed simultaneously with breast biopsy or at a later time. However, a post-breast biopsy ultrasound of the axilla may appear abnormal due to reactivity in the axillary lymph nodes. This study examined the timing of the axillary ultrasound (AUS) in relation to a breast biopsy to determine if it would affect patient management. MethodsAll newly diagnosed breast cancers from 2016 to 2017 were analyzed. We analyzed the timing of breast abnormality diagnosis, breast ultrasound, breast biopsy, AUS, and the AUS biopsy (AUSBx). An interval AUS was considered one that was not performed on the same day as a breast biopsy. True positive (TP), false positive (FP), true negative (TN), and false negative (FN) values were calculated. Chi-square analysis and Fisher exact test were performed on categorical data, and a student’s t-test was performed for continuous variables. Significance was determined to be p < 0.05. ResultsSame-day TP and FP AUS rates were 66.5 % and 33.5 %, respectively, and interval TP and FP AUS rates were 60.1 % and 39.9 %, respectively (p = 0.4708). The same-day TN and FN AUS rates were 90.6 % and 9.4 %, respectively, and interval TN and FN rates were 82.4 % and 17.6 %, respectively (p = 0.3917). ConclusionOverall TP, FP, TN, and FN rates did not differ between patients who received same-day or interval AUS studies.

Comparison of diagnostic accuracy of rapid antigen tests for COVID-19 compared to the viral genetic test in adults: a systematic review and meta-analysis.

The objective of this review was to determine the diagnostic accuracy of the currently available and upcoming point-of-care rapid antigen tests (RATs) used in primary care settings relative to the viral genetic real-time reverse transcriptase polymerase chain reaction (RT-PCR) test as a reference for diagnosing COVID-19/SARS-CoV-2 in adults. Accurate COVID-19 point-of-care diagnostic tests are required for real-time identification of SARS-CoV-2 infection in individuals. Real-time RT-PCR is the accepted gold standard for diagnostic testing, requiring technical expertise and expensive equipment that are unavailable in most primary care locations. RATs are immunoassays that detect the presence of a specific viral protein, which implies a current infection with SARS-CoV-2. RATs are qualitative or semi-quantitative diagnostics that lack thresholds that provide a result within a short time frame, typically within the hour following sample collection. In this systematic review, we synthesized the current evidence regarding the accuracy of RATs for detecting SARS-CoV-2 compared with RT-PCR. Studies that included nonpregnant adults (18 years or older) with suspected SARS-CoV-2 infection, regardless of symptomology or disease severity, were included. The index test was any available SARS-CoV-2 point-of-care RAT. The reference test was any commercially distributed RT-PCR-based test that detects the RNA genome of SARS-CoV-2 and has been validated by an independent third party. Custom or in-house RT-PCR tests were also considered, with appropriate validation documentation. The diagnosis of interest was COVID-19 disease and SARS-CoV-2 infection. This review considered cross-sectional and cohort studies that examined the diagnostic accuracy of COVID-19/SARS-CoV-2 infection where the participants had both index and reference tests performed. The keywords and index terms contained in relevant articles were used to develop a full search strategy for PubMed and adapted for Embase, Scopus, Qinsight, and the WHO COVID-19 databases. Studies published from November 2019 to July 12, 2022, were included, as SARS-CoV-2 emerged in late 2019 and is the cause of a continuing pandemic. Studies that met the inclusion criteria were critically appraised using QUADAS-2. Using a customized tool, data were extracted from included studies and were verified prior to analysis. The pooled sensitivity, specificity, positive predictive, and negative predictive values were calculated and presented with 95% CIs. When heterogeneity was observed, outlier analysis was conducted, and the results were generated by removing outliers. Meta-analysis was performed on 91 studies of 581 full-text articles retrieved that provided true-positive, true-negative, false-positive, and false-negative values. RATs can identify individuals who have COVID-19 with high reliability (positive predictive value 97.7%; negative predictive value 95.2%) when considering overall performance. However, the lower level of sensitivity (67.1%) suggests that negative test results likely need to be retested through an additional method. Most reported RAT brands had only a few studies comparing their performance with RT-PCR. Overall, a positive RAT result is an excellent predictor of a positive diagnosis of COVID-19. We recommend that Roche's SARS-CoV-2 Rapid Antigen Test and Abbott's BinaxNOW tests be used in primary care settings, with the understanding that negative results need to be confirmed through RT-PCR. We recommend adherence to the STARD guidelines when reporting on diagnostic data. PROSPERO CRD42020224250.

Is there added value of the hepatobiliary phase of MRI with hepatobiliary contrast agents for hepatocellular carcinoma diagnosis? A meta-analysis.

So far, there have been published several meta-analyses which focused on hepatocellular carcinoma (HCC) detection with hepatobiliary phase (HBP) contrast agents. However, only a few of them aimed at establishing whether there is any added value of the HBP itself for HCC diagnosis. To answer the question, we performed a systematic literature search with the time limit going back to 2010. True positive, false positive, false negative, and true negative values with and without the HBP were extracted from the included studies. Pooled sensitivities and specificities with and without the HBP were calculated and summary receiver operating characteristics curves were drawn to assess the diagnostic performance of the studies with and without the HBP. A total of 13 studies were included involving 1184 HCC lesions. In 13 studies without the HBP, the pooled sensitivity, specificity, and area under the curve (AUC) were 0.83, 0.89 and 0.94 respectively. In 13 studies with the HBP, the pooled sensitivity, specificity and AUC were 0.91, 0.85 and 0.98 respectively. We found no statistically significant differences in sensitivities between studies with and without the HBP (p = 0.1651).

Targeted nanopore sequencing using clinical specimens for the rapid diagnosis of extrapulmonary tuberculosis

BackgroundThe clinical presentation of extrapulmonary tuberculosis (EPTB) is atypical and it is easily confused with other diseases such as common infections, making prompt diagnosis a great challenge. This study aimed to evaluate the accuracy of targeted nanopore sequencing (TNS) in the diagnosis of EPTB. The diagnostic accuracy of TNS using different types of extrapulmonary specimens was also evaluated.MethodsWe reviewed the clinical data of patients with suspected EPTB for whom TNS was conducted and who were hospitalized at our center. The true positive, false positive, false negative, and true negative values were determined. Indices of diagnostic accuracy were computed, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC) for TNS and acid-fast bacilli (AFB) culture, and compared with those from clinical diagnosis.Results149 patients were included in the analysis. The overall sensitivity, specificity, PPV, NPV, and AUC of TNS for the diagnosis of EPTB were 86.4%, 87.5%, 97.3%, 55.3%, and 0.87, respectively. For diagnosis by AFB culture, these values were 25.6%, 100.0%, 100.0%, 20.5%, and 0.63, respectively. The most common specimens used were lymph node tissue, cerebrospinal fluid, pleural effusion, and pleural tissue. The diagnostic accuracy of TNS using all types of extrapulmonary specimens was good.ConclusionsTNS demonstrates good diagnostic accuracy in the rapid diagnosis of EPTB and this was true across different types of extrapulmonary specimens.

A Systematic Review &amp; Meta-Analysis on Criteria for Transcranial Motor Evoked Potential for Intraoperative Neuromonitoring during Spine Surgeries

Abstract Background Spine Surgery is the definitive treatment and indication for many traumatic spine illnesses, as well as several pathologies and deformities. Surgery in such a vital organ, formed in its core of the neural pathway that controls the whole of the human body, must be as safe, and least risky as possible, so as to prevent injuries to the neural pathway, or the surrounding vessels, or vital organs. Such great importance of the spine and the spinal cord, has urged surgeons and researchers to create techniques through which spine surgeries are well monitored, and the efficacy and normal physiology is well assessed intraoperatively. Objective to conduct a systematic review and meta-analysis of what has been published of the studies using transcranial motor evoked potential for intraoperative neuromonitoring during spine surgeries. This is for acquiring the best criteria for transcranial motor evoked potential (TcMEP) utilization for intraoperative neuromonitoring, as well as identifying the most accurate alarm point for TcMEP during intraoperative neuromonitoring. Patients and Methods a comprehensive and detailed search of literature was conducted through the Pubmed, Google Scholar, and Research Gate databases including articles related to intraoperative neuromonitoring modalities and transcranial motor evoked potential alarm points and criteria. Searches were performed with a combination of MeSH (medical subject headings). Only Studies published in the English Language with no lower date limit were included. The following search string was used in all databases; (“Intraoperative Neuromonitoring” or “Transcranial Motor Evoked Potential”). Results In a prospective study conducted in 2018, performed on 2867 patients, using a 70 % decrease in amplitude of the TcMEP curve as an alarm point during high-risk spinal surgeries, the number of true positive to false positive cases was found to be 126/234, while the number of true negative cases to false negative cases was found to be 2362/9 cases in total. The study demonstrates the necessity of intraoperative neuromonitoring for high-risk spinal surgery. 136 cases in this study were identified as rescue cases, as intraoperative TcMEP alert occurred and intraoperative maneuverings were done to overcome those alerts, hence hindering occurrence of postoperative neural deficit. Conclusion As regards different TcMEP alarm point values, it has been concluded that an alarm point of 50-60% decrease in amplitude of TcMEP is a more sensitive alarm point, than a higher value alarm point of the same modality. An alarm point of &amp;gt; 70% decrease in amplitude has a much less sensitivity value than lower alarm points, which in turn will result in a lot of missed adverse events, and a higher percentage of false negative values.

Circulating IgG Fragments for Gastric Cancer and Esophageal Cancer.

Blood serum of patients with gastric (n = 68) and esophageal (n = 43) cancer was assessed for proteolytic fragments of IgG. Serum samples of 20 healthy donors were used as a control. We analyzed indicators of hemostasis (prothrombin time, fibrinogen, plasminogen activity, a2-antiplasmin activity, protein C activity) in blood plasma and the level of total IgG in the blood serum. The median IgG-LysK of healthy donors was lower than in esophageal cancer and in patients with gastric cancer. ROC-analysis showed high sensitivity (91%) and specificity (85%) in the group with esophageal cancer but 68% and 85%, respectively, in patients with gastric cancer. Analysis of false negatives IgG-LysK in cancer patients showed that most patients had an advanced stage of cancer accompanied by metastases. Total IgG in the plasma of patients with false-negative IgG-LysK values was 30% lower than in samples with positive values, while the level of a2-antiplasmin was increased and the prothrombin time was shorter. These changes in blood homeostasis may be the reason for an increase in the proportion of false-negative values of the IgG-LysK coefficient. Circulatory IgG-LysK levels increase in the early stages of such cancers as gastric and esophageal cancers. Thus, when used in a panel with other more specific markers for these pathologies, this indicator can significantly increase the early detection of cancer.

BODYFAT: a new calculator to determine the risk of being overweight validated in Spanish children between 11 and 17 years of age

The assessment of body fat of children in primary care requires consideration of the dynamic changes in height, weight, lean mass, and fat mass during childhood growth. To achieve this, we aim to develop a predictive equation based on anthropometric values, with optimal diagnostic utility. This is a cross-sectional observational study, involving schoolgoers aged 11–17 years in the Vigo metropolitan area. Out of 10,747 individuals, 577 were randomly recruited. Variables: age, sex, ethnicity/country of origin, weight, height, 8 skinfolds, 3 diameters, 7 perimeters, and 85% percentile of body fat mass as the gold standard. Generalized additive regression was selected by cross-validation and compared using receiver operating characteristic curves (ROC curves). Sensitivity, specificity, positive and negative predictive values, true positive and true negative values, false positive and false negative values, accuracy, and positive and negative likelihood ratios were calculated. Two models were identified. The optimal model includes sex, weight, height, leg perimeter, and arm perimeter, with sensitivity of 0.93 (0.83–1.00), specificity of 0.91 (0.83–0.96), accuracy of 0.91 (0.84–0.96), and area under the curve (AUC) of 0.957 (0.928–0.986). The second model includes sex, age, and body mass index, with sensitivity of 0.93 (0.81–1.00), specificity of 0.90 (0.80–0.97), accuracy of 0.90 (0.82–0.96), and an AUC of 0.944 (0.903–0.984).Conclusion: Two predictive models, with the 85th percentile of fat mass as the gold standard, built with basic anthropometric measures, show very high diagnostic utility parameters. Their calculation is facilitated by a complementary online calculator.What is Known:• In routine clinical practice, mainly in primary care, BMI is used to determine overweight and obesity. This index has its weaknesses in the assessment of children.What is New:• We provide a calculator whose validated algorithm, through the determination of fat mass by impedanciometry, makes it possible to determine the risk of overweight and obesity in the community setting, through anthropometric measurements, providing a new practical, accessible and reliable model that improves the classification of overweight and obesity in children with respect to that obtained by determining BMI.

Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysis

ObjectiveWe aimed to determine if machine learning can predict acute brain injury and to identify modifiable risk factors for acute brain injury in patients receiving venoarterial extracorporeal membrane oxygenation. MethodsWe included adults (age ≥18 years) receiving venoarterial extracorporeal membrane oxygenation or extracorporeal cardiopulmonary resuscitation in the Extracorporeal Life Support Organization Registry (2009-2021). Our primary outcome was acute brain injury: central nervous system ischemia, intracranial hemorrhage, brain death, and seizures. We used Random Forest, CatBoost, LightGBM, and XGBoost machine learning algorithms (10-fold leave-1-out cross-validation) to predict and identify features most important for acute brain injury. We extracted 65 total features: demographics, pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation laboratory values, and pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation settings. ResultsOf 35,855 patients receiving venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation) (median age of 57.8 years, 66% were male), 7.7% (n = 2769) experienced acute brain injury. In venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation), the area under the receiver operator characteristic curves to predict acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.67, 0.67, and 0.62, respectively. The true-positive, true-negative, false-positive, false-negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively, for acute brain injury. Longer extracorporeal membrane oxygenation duration, higher 24-hour extracorporeal membrane oxygenation pump flow, and higher on-extracorporeal membrane oxygenation partial pressure of oxygen were associated with acute brain injury. Of 10,775 patients receiving extracorporeal cardiopulmonary resuscitation (median age of 57.1 years, 68% were male), 16.5% (n = 1787) experienced acute brain injury. The area under the receiver operator characteristic curves for acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.72, 0.73, and 0.69, respectively. Longer extracorporeal membrane oxygenation duration, older age, and higher 24-hour extracorporeal membrane oxygenation pump flow were associated with acute brain injury. ConclusionsIn the largest study predicting neurological complications with machine learning in extracorporeal membrane oxygenation, longer extracorporeal membrane oxygenation duration and higher 24-hour pump flow were associated with acute brain injury in nonextracorporeal cardiopulmonary resuscitation and extracorporeal cardiopulmonary resuscitation venoarterial extracorporeal membrane oxygenation.

A comparison of two user-friendly methods to identify and support correction of misspelled medications

ObjectiveTo identify and support correction of misspelled medication names recorded as free text, we compared the relative effectiveness of two user-friendly methods, used without reliance on clinical knowledge. MethodsLeveraging the SAS® COMPGED function, fuzzy string search programs examined 1.8 million medication records from 183,600 World Trade Center General Responder Cohort monitoring visits conducted in New York and New Jersey between 7/16/2002 and 3/31/2021, producing replicable generalized edit distance scores between the reported and correct spelling. Scores < 120 were selected as optimal and compared to Stedman’s 2020 Plus Medical/Pharmaceutical Spell Checker first suggested word, used as the comparative standard because it employs both spelling and phonetic similarities to suggest matching words. We coded each methods’ results as identifying or not identifying the medications within each visit. ResultsMost types of medications (94.4 % anxiety, 98.4 % asthma and 94.6 % ulcer/gastroesophageal reflux disease) were correctly spelled. Cross tabulations assessed the agreement (anxiety 99.9 %, asthma 99.6 % and 98.4 % ulcer/ gastroesophageal reflux disease), false positive (respectively 0.02 %, 0.03 % and 2.0 %) and false negative (respectively 1.9 %, 0.5 % and 1.0 %) values. Scores < 120 occasionally correctly identified medications missed by the spell checker. We observed no difference in medication misspellings across socio-economically and culturally diverse patient characteristics. ConclusionsBoth methods efficiently identified most misspelled medications, greatly minimizing the review and rectification needed. The fuzzy method is more universally applicable for condition-specific medications identification, but requires more programming skills. The spell checker is inexpensive, but benefits from modest programming skills and is only available in some languages.

18F-FDG PET/MR for diagnosis of primary central nervous system lymphoma: protocol for a systematic review and meta-analysis

BackgroundPrimary central nervous system lymphoma (PCNSL) is a rare form of extranodal non-Hodgkin’s lymphoma with poor prognosis. 18F-flourodeoxyglucose positron emission tomography (PET)/magnetic resonance (MR) combines the advantages of PET and...

Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study

BackgroundDeep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future.MethodsA total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 × 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined.ResultsAmong the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model’s performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425.ConclusionsThe model’s accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm.Clinical revelanceDeep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.

Diagnostic value of HPV E6/E7 mRNA in screening for cervical intraepithelial neoplasia grade 2 or worse: A systematic review and meta‑analysis.

Histology is considered the gold standard for diagnosing the pathological progress of cervical cancer development, while cervical intraepithelial neoplasia of grade 2 or worse (CIN2+) is the cutoff for intervention in clinical practice. The diagnostic value of human papillomavirus (HPV) E6/E7 mRNA in screening for CIN2+ has not been systematically summarized. A meta-analysis was conducted as part of the present study conducted to explore the diagnostic value of HPV E6/E7 mRNA in screening for CIN2+, aiming to provide a new marker for earlier clinical diagnosis of cervical cancer. The PubMed, Embase and Cochrane Library databases were searched from inception to May 2023. Studies reporting the true positive, false positive, true negative and false negative values in differentiating between CIN2+ and CIN2- were included, while duplicate publications, studies without full text, incomplete information or inability to conduct data extraction, animal experiments, reviews and systematic reviews were excluded. STATA software was used to analyze the data. A total of 2,224 patients were included of whom there were 1,274 patients with CIN2+ and 950 patients with CIN2-. The pooled sensitivity and specificity of the studies overall were 0.89 (95% CI, 0.84-0.92) and 0.59 (95% CI, 0.46-0.71), respectively; the positive likelihood ratio (LR) and the negative LR of the studies overall were 2.31 (95% CI, 1.61-3.32) and 0.21 (95% CI, 0.14-0.30), respectively. The pooled diagnostic odds ratio of the studies overall was 11.53 (95% CI, 6.85-19.36). Additionally, the area under the curve was 0.88. The analysis indicated that HPV E6/E7 mRNA has high diagnostic efficacy for CIN2+. HPV E6/E7 mRNA is highly sensitive in the diagnosis of CIN2+, which helps to reduce the rate of missed diagnoses. However, lower specificity may lead to a higher number of misdiagnoses in healthy patients.

Development of Five-Tier Instruments to Identify Students' Misconceptions about Centripetal and Centrifugal Force

The purpose of the study was to determine the development process and the feasibility of a five-tier diagnostic test instrument to identify students' misconceptions about centripetal and centrifugal forces. This research is a type of Research and Development (R&amp;D) with the development model used, namely the 4D (Four-D) development model. This study uses the R&amp;D method because the results of this study are in the form of a diagnostic test instrument to identify misconceptions in the learning process, and to find out the main source of the causes of misconceptions. The results of the diagnostic test of students who have misconceptions about centripetal and centrifugal forces are 20.31%.The percentage of false positive is 9.62%, the false negative is 8.49 and the Lack of Knowledge is 16.97%. From the percentage results obtained that the false positive (FP) and false negative (FN) values ​​are valid because &lt;10%.The results of the validity test on the instrument are said to be valid because &gt;0.3 and the results of the reliability test are Cronbach's Alpha value obtained at 0.715 from 7 item questions. So this instrument can be said to be reliable because the Cronbach's Alpha value is classified as high based on the reliability criteria.

Comparison of National Factor-Based Models for Preeclampsia Screening.

This study aimed to compare the predictive values of the American College of Obstetricians and Gynecologists (ACOG), the National Institute for Health and Care Excellence (NICE), and the Society of Obstetricians and Gynecologists of Canada (SOGC) factor-based models for preeclampsia (PE) screening. We conducted a secondary analysis of maternal and birth data from 32 hospitals. For each delivery, we calculated the risk of PE according to the ACOG, the NICE, and the SOGC models. Our primary outcomes were PE and preterm PE (PE combined with preterm birth) using the ACOG criteria. We calculated the detection rate (DR or sensitivity), the false positive rate (FPR or 1 - specificity), the positive (PPV) and negative (NPV) predictive values of each model for PE and for preterm PE using receiver operator characteristic (ROC) curves. We used 130,939 deliveries including 4,635 (3.5%) cases of PE and 823 (0.6%) cases of preterm PE. The ACOG model had a DR of 43.6% for PE and 50.3% for preterm PE with FPR of 15.6%; the NICE model had a DR of 36.2% for PE and 41.3% for preterm PE with FPR of 12.8%; and the SOGC model had a DR of 49.1% for PE and 51.6% for preterm PE with FPR of 22.2%. The PPV for PE of the ACOG (9.3%) and NICE (9.4%) models were both superior than the SOGC model (7.6%; p < 0.001), with a similar trend for the PPV for preterm PE (1.9 vs. 1.9 vs. 1.4%, respectively; p < 0.01). The area under the ROC curves suggested that the ACOG model is superior to the NICE for the prediction of PE and preterm PE and superior to the SOGC models for the prediction of preterm PE (all with p < 0.001). The current ACOG factor-based model for the prediction of PE and preterm PE, without considering race, is superior to the NICE and SOGC models. · Clinical factor-based model can predict PE in approximately 44% of the cases for a 16% false positive.. · The ACOG model is superior to the NICE and SOGC models to predict PE.. · Clinical factor-based models are better to predict PE in parous than in nulliparous..

Risk factors and the CCTA application in patients with vulnerable coronary plaque in type 2 diabetes: a retrospective study

BackgroundDiabetes is an independent risk factor for cardiovascular disease. The purpose of this study was to identify the risk factors for vulnerable coronary plaques (VCPs), which are associated with adverse cardiovascular events, and to determine the value of coronary CT angiography (CCTA) in patients with type 2 diabetes mellitus (T2DM) and VCPs.MethodsNinety-eight T2DM patients who underwent CCTA and intravascular ultrasound (IVUS) were retrospectively included and analyzed. The patients were grouped and analyzed according to the presence or absence of VCPs.ResultsAmong the patients with T2DM, time in range [TIR {the percentage of time blood glucose levels were in the target range}] (OR = 0.93, 95% CI = 0.89–0.96; P < 0.001) and the high-density lipoprotein-cholesterol (HDL-C) concentration (OR = 0.24, 95% CI = 0.09–0.63; P = 0.04) were correlated with a lower risk of VCP, but the triglycerides (TG) concentration was correlated with a higher risk of VCP (OR = 1.79, 95% CI = 1.01–3.18; P = 0.045). The area under the receiver operator characteristic curve (AUC) of TIR, and HDL-C and TG concentrations were 0.76, 0.73, and 0.65, respectively. The combined predicted AUC of TIR, and HDL-C and TG concentrations was 0.83 (P < 0.05). The CCTA sensitivity, specificity, false-negative, and false-positive values for the diagnosis of VCP were 95.74%, 94.12%, 4.26%, and 5.88%, respectively. The identification of VCP by CCTA was positively correlated with IVUS (intraclass correlation coefficient [ICC] = 0.90).ConclusionsThe TIR and HDL-C concentration are related with lower risk of VCP and the TG concentration was related with higher risk of VCP in patients with T2DM. In clinical practice, TIR, HDL-C and TG need special attention in patients with T2DM. The ability of CCTA to identify VCP is highly related to IVUS findings.

A new modified MR dual precision positioning of thin-slice oblique sagittal fat suppression proton density weighted imaging: its diagnostic accuracy in anterior cruciate ligament injury

To evaluate the diagnostic accuracy of a new modified MR dual precision positioning of thin-slice oblique sagittal fat suppression proton density-weighted imaging (DPP-TSO-Sag-FS-PDWI) sequence in detecting ACL injuries and its grades compared to standard sequences using arthroscopy as the standard reference. 42 patients enrolled in this retrospective study received the 1.5-T MRI with standard sequences and the new modified DPP-TSO-Sag-FS-PDWI sequence, and their arthroscopy results was recorded. The Mc Nemer-Bowker and weighted Kappa was performed to compare the consistency of MRI diagnosis with arthroscopic results. Finally, the diagnostic accuracy was calculated based on the true positive, true negative, false negative and false positive values. The diagnostic consistency of the DPP-TSO-Sag-FS-PDWI were higher than standard sequences for both reader 1 (K = 0.876 vs. 0.620) and reader 2 (K = 0.833 vs. 0.683) with good diagnostic repeatability (K = 0.794 vs. 0.598). Furthermore, the DPP-TSO-Sag-FS-PDWI can classify and diagnose three grades of ACL injury [the sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value were more than 84%], especially for grade II injury as the PPV was superior for reader 1 (92.3% vs. 53.9%) and reader 2 (84.6% vs. 69.2%). The new modified DPP-TSO-Sag-FS-PDWI sequence can display the ACL injury on one or continuous levels by maximizing the acquisition of complete ligament shape and true anatomical images, and excluding the influence of anatomical differences between individuals. It can improve the diagnostic accuracy with good repeatability and classify three grades of the ACL injury.

Determination of Sensitivity and Positive Predictive Value for Handheld Doppler in the Assessment of Thoracodorsal Artery Perforators and Literature Review

Abstract Background: Hand-held Doppler (HHD) is still a very useful tool in the reconstructive surgeon’s armamentarium. One hundred percent specificity in detecting perforators can be achieved with HHD when a perforator compression test is applied. The study aimed to determine the sensitivity and positive predictive value (PPV) for HHD in the assessment of thoracodorsal artery perforators, by applying the perforator compression test, using the color Doppler ultrasound (CDU) as the standard. Materials and Methods: This was a cross-sectional study. The Plastic Surgeon assessed for perforators using HHD on both lateral thoracic areas for each patient, with a re-evaluation of the same locations by a Consultant Radiologist using the CDU. The data generated were analysed using the Statistical Package for the Social Sciences (SPSS) software version 20, and results were presented in charts and tables. The sensitivity and PPV for HHD were then calculated. Results: A total of 70 patients were included, 58 males (82.9%) and 12 females (17.1%). The age range was 18–65 years, with a mean of 31.77 years ± 11.72 years. Overall, 247 perforators were identified by HHD. The true positive, false-positive, and false-negative values for HHD were 127 (51.4%), 120 (48.6%), and 20 (8.1%), respectively. The sensitivity and PPV for the HHD were calculated as 86.3% and 51.4%, respectively. Conclusion: The sensitivity of HHD was high while the PPV was much lower compared to other studies. This implies that for patients with positive HHD signals, the probability of having perforators intraoperative is low.

PREDICT-GTN 2: Two-factor streamlined models match FIGO performance in gestational trophoblastic neoplasia

ObjectiveThe International Federation of Gynecology and Obstetrics (FIGO) scoring system uses the sum of eight risk-factors to predict single-agent chemotherapy resistance in Gestational Trophoblastic Neoplasia (GTN). To improve ease of use, this study aimed to generate: (i) streamlined models that match FIGO performance and; (ii) visual-decision aids (nomograms) for guiding management. MethodsUsing training (n = 4191) and validation datasets (n = 144) of GTN patients from two UK specialist centres, logistic regression analysis generated two-factor models for cross-validation and exploration. Performance was assessed using true and false positive rate, positive and negative predictive values, Bland-Altman calibration plots, receiver operating characteristic (ROC) curves, decision-curve analysis (DCA) and contingency tables. Nomograms were developed from estimated model parameters and performance cross-checked upon the training and validation dataset. ResultsThree streamlined, two-factor models were selected for analysis: (i) M1, pre-treatment hCG + history of failed chemotherapy; (ii) M2, pre-treatment hCG + site of metastases and; (iii) M3, pre-treatment hCG + number of metastases. Using both training and validation datasets, these models showed no evidence of significant discordance from FIGO (McNemar's test p > 0.78) or across a range of performance parameters. This behaviour was maintained when applying algorithms simulating the logic of the nomograms. ConclusionsOur streamlined models could be used to assess GTN patients and replace FIGO, statistically matching performance. Given the importance of imaging parameters in guiding treatment, M2 and M3 are favoured for ongoing validation. In resource-poor countries, where access to specialist centres is problematic, M1 could be pragmatically implemented. Further prospective validation on a larger cohort is recommended.

A HYBRID MODEL FOR THE CLASSIFICATION OF PHYSIOLOGICAL AND NEURAL SIGNAL USING CNN-LSTM TECHNIQUE

Physiological and neural signal classification has many important applications in healthcare, including medical diagnosis and monitoring. For example, electrocardiogram (ECG) classification can be used to detect arrhythmias and other cardiac abnormalities; while EEG classification can be used to diagnose neurological disorders such as epilepsy and sleep apnea. This paper presents an LSTM model for the decoding of physiological and neural signals. In this paper, an electroencephalography brain signal data which was gotten from Kaggle.com was used. The dataset was pre-processed so as to remove noise from the data. The pre-processed data was used in training the LSTM model. The LSTM model was trained on fourteen (14) steps. The result of the LSTM model showed an accuracy of 85% at the first step and a validation (testing) accuracy of 90%. For the fourteenth step, the model achieved an accuracy result of 98% for training and 94% for validation (testing). We also evaluated the performance of the model using a classification report and confusion matrix. The result of the classification report showed an accuracy of 95%, which is implication that the performance of the model on the test data is efficient. The confusion matrix was used to specify how well the proposed model classified the electroencephalography signal. The result of the confusion matrix showed that the model predicted the result correctly to be neutral 151 out of 153, positive to be 127 out of 142, and negative to be 128 out of 132. The result showed that the level of false positive and negative values is minimal (0.02% and 0.05%).