scholarly journals Predicting Disease in Transition Dairy Cattle Based on Behaviors Measured Before Calving

Animals ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 928
Author(s):  
Mohammad W. Sahar ◽  
Annabelle Beaver ◽  
Marina A. G. von Keyserlingk ◽  
Daniel M. Weary
Keyword(s):  
Dairy Cattle ◽  
Sensitivity And Specificity ◽  
Roc Curve ◽  
Predictive Value ◽  
Predictive Ability ◽  
Training Dataset ◽  
Test Dataset ◽  
Increased Risk ◽  
High Prevalence ◽  
Random Method

Dairy cattle are particularly susceptible to metritis, hyperketonemia (HYK), and mastitis in the weeks after calving. These high-prevalence transition diseases adversely affect animal welfare, milk production, and profitability. Our aim was to use prepartum behavior to predict which cows have an increased risk of developing these conditions after calving. The behavior of 213 multiparous and 105 primiparous Holsteins was recorded for approximately three weeks before calving by an electronic feeding system. Cows were also monitored for signs of metritis, HYK, and mastitis in the weeks after calving. The data were split using a stratified random method: we used 70% of our data (hereafter referred to as the “training” dataset) to develop the model and the remaining 30% of data (i.e., the “test” dataset) to assess the model’s predictive ability. Separate models were developed for primiparous and multiparous animals. The area under the receiver operating characteristic (ROC) curve using the test dataset for multiparous cows was 0.83, sensitivity and specificity were 73% and 80%, positive predictive value (PPV) was 73%, and negative predictive value (NPV) was 80%. The area under the ROC curve using the test dataset for primiparous cows was 0.86, sensitivity and specificity were 71% and 84%, PPV was 77%, and NPV was 80%. We conclude that prepartum behavior can be used to predict cows at risk of metritis, HYK, and mastitis after calving.

scholarly journals Association between clinical risk scores and mortality in atrial fibrillation: Systematic review and network meta-regression of 669,000 patients

2018 ◽  
Vol 27 (6) ◽  
pp. 633-644 ◽  
Author(s):  
Marco Proietti ◽  
Alessio Farcomeni ◽  
Giulio Francesco Romiti ◽  
Arianna Di Rocco ◽  
Filippo Placentino ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Predictive Ability ◽  
Risk Scores ◽  
Clinical Risk ◽  
Increased Risk ◽  
High Negative Predictive Value ◽  
Meta Regression

Aims Many clinical scores for risk stratification in patients with atrial fibrillation have been proposed, and some have been useful in predicting all-cause mortality. We aim to analyse the relationship between clinical risk score and all-cause death occurrence in atrial fibrillation patients. Methods We performed a systematic search in PubMed and Scopus from inception to 22 July 2017. We considered the following scores: ATRIA-Stroke, ATRIA-Bleeding, CHADS2, CHA2DS2-VASc, HAS-BLED, HATCH and ORBIT. Papers reporting data about scores and all-cause death rates were considered. Results Fifty studies and 71 scores groups were included in the analysis, with 669,217 patients. Data on ATRIA-Bleeding, CHADS2, CHA2DS2-VASc and HAS-BLED were available. All the scores were significantly associated with an increased risk for all-cause death. All the scores showed modest predictive ability at five years (c-indexes (95% confidence interval) CHADS2: 0.64 (0.63–0.65), CHA2DS2-VASc: 0.62 (0.61–0.64), HAS-BLED: 0.62 (0.58–0.66)). Network meta-regression found no significant differences in predictive ability. CHA2DS2-VASc score had consistently high negative predictive value (≥94%) at one, three and five years of follow-up; conversely it showed the highest probability of being the best performing score (63% at one year, 60% at three years, 68% at five years). Conclusion In atrial fibrillation patients, contemporary clinical risk scores are associated with an increased risk of all-cause death. Use of these scores for death prediction in atrial fibrillation patients could be considered as part of holistic clinical assessment. The CHA2DS2-VASc score had consistently high negative predictive value during follow-up and the highest probability of being the best performing clinical score.

scholarly journals Can computed tomography-based radiomics potentially discriminate between anterior mediastinal cysts and type B1 and B2 thymomas?

2020 ◽  
Vol 19 (1) ◽  
Author(s):  
Lulu Liu ◽  
Fangxiao Lu ◽  
Peipei Pang ◽  
Guoliang Shao
Keyword(s):  
Computed Tomography ◽  
Sensitivity And Specificity ◽  
Texture Features ◽  
Training Dataset ◽  
Features Selection ◽  
Clinical Factors ◽  
Combined Model ◽  
Test Dataset ◽  
Enhanced Ct ◽  
Mediastinal Cysts

Abstract Background Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resource waste. The purpose of this study is to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas. Methods A group of 188 patients with pathologically confirmed AMC (106 cases misdiagnosed as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the artificial intelligence kit (AK) software. A total of 180 tumour texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis, and LASSO were used to features selection and then the radiomics signature (radscore) was obtained. The combined model including radscore and independent clinical factors was developed. The model performances were evaluated on discrimination, calibration curve. Results Two radscore models were constructed from the unenhanced and enhanced phases based on the selected four and three features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3%, and 83.8% in the training dataset and 0.899, 84.6%, and 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model). Conclusions The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Malnutrition prevalence in a medical assessment and planning unit and its association with hospital readmission

2013 ◽  
Vol 37 (5) ◽  
pp. 636 ◽  
Author(s):  
Marte Ulltang ◽  
Angela P. Vivanti ◽  
Eryn Murray
Keyword(s):  
Sensitivity And Specificity ◽  
Predictive Value ◽  
Hospital Readmission ◽  
Nutritional Risk ◽  
Medical Assessment ◽  
Medical Unit ◽  
Planning Unit ◽  
Acute Medical Unit ◽  
Increased Risk ◽  
Prospective Longitudinal

Objective To investigate malnutrition prevalence on presentation to a Medical Assessment and Planning Unit (MAPU) in a setting designed to prevent hospital admission, the association of nutritional status with hospital readmission at 90 days, and agreement of nutritional risk between the Malnutrition Screening Tool (MST) and Subjective Global Assessment (SGA). Methods Prospective longitudinal cohort study of consecutive patients admitted to MAPU during the first 6 weeks of operation. The main outcome measures were prevalence of malnutrition and hospital readmission at 90 days. Sensitivity and specificity of the MST was assessed against the criterion standard of SGA. Results The mean participant age was 62 years (n = 153, s.d. 17.4 years) with 50% male (77/153, 95% CI 42–58%). According to the SGA, 17% (95% CI 8–26%) were assessed as malnourished on admission. The MST identified that 18% (95% CI 12–24%) were at nutritional risk, and participants screening positive for nutritional risk had significantly increased odds of hospital readmission at 90 days (OR 3.4, 95% CI, 1.3–9.1, P < 0.029). The MST was practical and successfully identified patients assessed as malnourished within the MAPU setting (sensitivity 73%, specificity 76%, negative predictive value 93%, positive predictive value 38%). Conclusions Malnutrition is a significant problem in a MAPU setting, and patients screened at nutritional risk are at significantly higher risk of hospital readmission within 90 days. What is known about the topic? The prevalence of malnutrition in Australian hospitals is estimated to be between 30 and 53%. It is important to identify malnutrition, given that the consequences contribute to increased morbidity, mortality, length of hospital stay, readmission and healthcare costs. Malnutrition screening is strongly advocated as the first step to routinely identify nutritional problems early in acute care settings. To date only one Australian study has documented the prevalence of malnutrition in an acute medical unit setting, estimating it to be 53%. What does this paper add? The acute medical unit in the previous study operates under a different model of care acute assessment unit, in which patients are triaged to the wards, and no known study to date has investigated the prevalence of malnutrition in a MAPU setting aiming to avoid hospital admissions. Furthermore, no other studies have explored malnutrition and its association with risk of hospital readmission in these settings. Our study reveals that malnutrition is a problem in MAPU settings, demonstrating the important role malnutrition screening plays in identifying malnutrition risk in a MAPU setting due to the increased risk of readmission at 90 days evident in this group. What are the implications for practitioners? The study identified that malnutrition risk significantly increased the odds of hospital readmission at 90 days. The MST was confirmed as a practical tool for use in the MAPU setting, showing acceptable sensitivity and specificity. Incorporation of malnutrition screening and timely intervention may increase the overall effectiveness of the MAPU clinic through avoidance of hospital readmission at 90 days.

scholarly journals Heart Score for Predicting in Hospital Major Cardiovascular Event in Patient with Non ST Segment Elevation Acute Coronary Syndrome

2020 ◽  
Vol 6 (2) ◽  
pp. 85-90
Author(s):  
Kamal Kharrazi Ilyas ◽  
Sutomo Kasiman ◽  
Harris Hasan ◽  
Zulfikri Mukhtar ◽  
Refli Hasan ◽  
...  
Keyword(s):  
Acute Coronary Syndrome ◽  
General Hospital ◽  
Cardiovascular Event ◽  
Roc Curve ◽  
Predictive Value ◽  
Predictive Ability ◽  
St Segment Elevation ◽  
Heart Score ◽  
Coronary Syndrome ◽  
St Segment

Background: Acute Coronary Syndrome (ACS) is one of the main problems in the field of cardiovascular diseases because of high hospitalization rate, high mortality and high medical cost. Rapid and accurate risk stratification is needed to calculate the risk of complication and right now exist two most used score which is GRACE and TIMI. Heart score has 5 simple variables that can be calculated easily and this score considered to have better predictive ability compared to other score. The aim of this study is to examine HEART score as a predictor for in hospital Major Cardiovascular Event (MACE) in patient diagnosed as Non ST Segment Elevation Acute Coronary Syndrome (NSTEACS) that hospitalized at Haji Adam Malik (HAM) General Hospital Medan. Methods: This is a prospective cohort study that includes 52 NSTEACS patient that hospitalized at HAM General Hospital since November 2018 until January 2019. Patient that diagnosed as NSTEACS were calculated for GRACE, TIMI, and HEART score then observed during hospitalization. Outcome of this study is MACE during hospitalization. Statistical analysis was performed to test HEART score as MACE predictor and then comparison was done with GRACE and TIMI Results: By using ROC curve analysis, the cut-off value of HEART score was 5 (AUC 0.947, 95% CI 0.883-0.997, p<0.01). Study subject that experienced MACE with HEART score ≥5 was 21 patients (87.5%) compared to 2 patients (7.1%). HEART score ≥5 can predict MACE with sensitivity 87.5%, specificity 92.9%, negative predictive value (NPV) 89.7% and positive predictive value (PPV) 91.3%. ROC curve comparison was done between HEART with GRACE and TIMI then it was found that HEART score has better predictive ability compared to TIMI and GRACE (AUC 0.947 vs 0.829 vs 0.807, p < 0.01). Conclusion: HEART score can be used as MACE predictor which is relatively simpler but have better predictive ability compared to GRACE and TIMI.

scholarly journals Value of Examination Under Fluoroscopy for the Assessment of Sacroiliac Joint Dysfunction

2015 ◽  
Vol 5;18 (5;9) ◽  
pp. E781-E786
Author(s):  
Burton D Beakley
Keyword(s):  
Sensitivity And Specificity ◽  
Roc Curve ◽  
Predictive Value ◽  
Joint Pain ◽  
Clinical Symptoms ◽  
Small Sample ◽  
Joint Disease ◽  
Pain Clinic ◽  
Predictive Values ◽  
Si Joint

Background: Pain emanating from the sacroiliac (SI) joint can have variable radiation patterns. Single physical examination tests for SI joint pain are inconsistent with multiple tests increasing both sensitivity and specificity. Objective: To evaluate the use of fluoroscopy in the diagnosis of SI joint pain. Study Design: Prospective double blind comparison study Setting: Pain clinic and radiology setting in urban Veterans Administration (VA) in New Orleans, Louisiana. Methods: Twenty-two adult men, patients at a southeastern United States VA interventional pain clinic, presented with unilateral low back pain of more than 2 months’ duration. Patients with previous back surgery were excluded from the study. Each patient was given a Gapping test, Patrick (FABERE) test, and Gaenslen test. A second blinded physician placed each patient prone under fluoroscopic guidance, asking each patient to point to the most painful area. Pain was provoked by applying pressure with the heel of the palm in that area to determine the point of maximum tenderness. The area was marked with a radio-opaque object and was placed on the mark with a fluoroscopic imgage. A site within 1 cm of the SI joint was considered as a positive test. This was followed by a diagnostic injection under fluoroscopy with 1 mL 2% lidocaine. A positive result was considered as more than 2 hours of greater than 75% reduction in pain. Then, in 2-3 days this was followed by a therapeutic injection under fluoroscopy with 1 mL 0.5% bupivacaine and 40 mg methylprednisolone. Results: Each patient was reassessed after 6 weeks. The sensitivity and specificity in addition to the positive and negative predictive values were determined for both the conventional examinations, as well as the examination under fluoroscopy. Finally, a receiver operating characteristic (ROC) curve was constructed to evaluate test performance. The sensitivity and specificity of the fluoroscopic examination were 0.82 and 0.80 respectively; Positive predictive value and negative predictive value were 0.93 and 0.57 respectively. The area under ROC curve was 0.812 which is considered a “good” test; however the area under ROC for the conventional examination were between 0.52 -0.58 which is considered “poor to fail”. Limitations: Variation in anatomy of the SI joint, small sample size. Conclusions: Multiple structures of the SI joint complex can result in clinical symptoms of pain. These include intra-articular structures (degenerative arthritis, and inflammatory conditions) as well as extraarticular structures (ligaments, muscles, etc.). Key words: Sacroilliac joint disease, radicular pain, thigh thrust test, compression test, distraction test, Gaenslen test, Patrick test (FABER test)

Machine learning to predict outcomes in patients with acute pulmonary embolism who prematurely discontinued anticoagulant therapy.

2021 ◽  
Author(s):  
Damian Mora ◽  
José Antonio Nieto ◽  
Jorge Mateo ◽  
Behnood Bikdeli ◽  
Stefano Barco ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pulmonary Embolism ◽  
Logistic Regression ◽  
Anticoagulant Therapy ◽  
Roc Curve ◽  
Predictive Value ◽  
Support Vector ◽  
Calibration Plot ◽  
Composite Outcome ◽  
Increased Risk

Background: Patients with pulmonary embolism (PE) who prematurely discontinue anticoagulant therapy (<90 days) are at an increased risk for death or recurrences. Methods: We used the data from the RIETE registry to compare the prognostic ability of 5 machine-learning (ML) models and logistic regression to identify patients at increased risk for the composite of fatal PE or recurrent venous thromboembolism (VTE) 30 days after discontinuation. ML models included Decision tree, K-Nearest Neighbors algorithm, Support Vector Machine, Ensemble and Neural Network [NN]. A “full” model with 70 variables and a “reduced” model with 23 were analyzed. Model performance was assessed by confusion matrix metrics on the testing data for each model and a calibration plot. Results: Among 34,447 patients with PE, 1,348 (3.9%) discontinued therapy prematurely. Fifty-one (3.8%) developed fatal PE or sudden death and 24 (1.8%) had non-fatal VTE recurrences within 30 days after discontinuation. ML-NN was the best method for identification of patients experiencing the composite endpoint, predicting the composite outcome with an area under receiver operating characteristics (ROC) curve of 0.96 (95% confidence intervals [CI], 0.95-0.98), using either 70 or 23 variables captured before discontinuation. Similar numbers were obtained for sensitivity, specificity, positive predictive value, negative predictive value and accuracy. The discrimination of logistic regression was inferior (area under ROC curve, 0.76 [95% Cl 0.70-0.81]). Calibration plot showed similar deviations from the perfect line for ML-NN and logistic regression. Conclusions: ML-NN method very well predicted the composite outcome after premature discontinuation of anticoagulation and outperformed traditional logistic regression.

scholarly journals The predictive value of urine specific gravity in the diagnosis of vasovagal syncope in children and adolescents

2021 ◽  
Vol 47 (1) ◽  
Author(s):  
Ping Liu ◽  
Xingfang Zeng ◽  
Wanzhen Mei ◽  
Yuwen Wang ◽  
Runmei Zou ◽  
...  
Keyword(s):  
Specific Gravity ◽  
Children And Adolescents ◽  
Sensitivity And Specificity ◽  
Roc Curve ◽  
Predictive Value ◽  
Vasovagal Syncope ◽  
Urine Specific Gravity ◽  
Tilt Test ◽  
Control Group ◽  
Neurally Mediated Syncope

Abstract Background Vasovagal syncope (VVS) is a kind of common neurally mediated syncope in children and adolescents. Decreased blood volume is one of the pathogenesis of VVS. The diagnosis of VVS is mainly based on head-up tilt test (HUTT), but some complications may easily occur when HUTT induces syncope. To find a simple and safe VVS diagnosis method can improve the VVS diagnosis efficiency. Aims of the study This was a prospective study. The study will explore the predictive value of urine specific gravity (USG) in the diagnosis of VVS in children and adolescents. Patients and methods Ninety-seven cases (43 males and 54 females, aged 4 to 16 years old, with an average age of 10.91 ± 2.18 years old) hospitalized due to unexplained premonitory syncope or syncope and diagnosed with VVS through HUTT from September 2014 to September 2018 were selected as VVS group. During the same period, 91 cases of children and adolescents, including 45 males and 46 females, aged from 5 to 15 years old, who underwent a healthy examination were matched as a control (control group). USG was measured in both groups. Results The USG of VVS group was significantly lower than that of the control group (P < 0.01), and USG of females was lower than that of males in VVS group (P = 0.045). The sensitivity and specificity of USG in predicting VVS were evaluated by ROC curve. The area under the ROC curve was 0.751, standard error was 0.035, and 95% CI (0.683, 0.819) suggested that USG was of moderate predictive value in the diagnosis of VVS. As cut-off value of USG was 1.0185, the sensitivity and specificity and diagnostic coincidence rate of VVS were 74.39, 66.04 and 69.68%, respectively. Conclusion There are less USG in children and adolescents with VVS, especially lower USG in females. Therefore, USG has predictive value in the diagnosis of VVS in children and adolescents.

scholarly journals Can Computed Tomography-Based Radiomics Potentially Discrimination Between Anterior Mediastinal Cysts and type B1 and B2 thymomas

2020 ◽  
Author(s):  
Lulu Liu ◽  
Fangxiao Lu ◽  
Peipei Pang ◽  
Guoliang Shao
Keyword(s):  
Computed Tomography ◽  
Sensitivity And Specificity ◽  
Texture Features ◽  
Training Dataset ◽  
Features Selection ◽  
Clinical Factors ◽  
Combined Model ◽  
Test Dataset ◽  
Enhanced Ct ◽  
Mediastinal Cysts

Abstract Background Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resources waste. The purpose of this study was to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas. Methods A group of 188 patients with pathologically confirmed AMC (106 cases mischarged as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the Artificial Intelligence Kit (AK) software. A total of 396 tumor texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis and LASSO were used to features selection and then the radiomics signature (radscore) were obtained. The combined model including radscore and independent clinical factors were developed. The model performances were evaluated on discrimination, calibration curve. Results Two radscore model were constructed from the unenhanced and enhanced phases based on the selected 4 and 3 features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3% and 83.8% in the training dataset and 0.899, 84.6%, 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model). Conclusions The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Concerning the informativeness of the methods for predicting prognosis of peritonitis

2021 ◽  
pp. 6-12
Author(s):  
Nikolay Vyacheslavovich Lebedev ◽  
Vasily Sergeevich Popov ◽  
Alexey Evgenievich Klimov ◽  
Vladimir Alexandrovich Ivanov ◽  
Giorgi Teimurazovich Svanadze
Keyword(s):  
Clinical Practice ◽  
High Risk ◽  
Positive Result ◽  
Sensitivity And Specificity ◽  
Predictive Value ◽  
Predictive Ability ◽  
Secondary Peritonitis ◽  
Risk Of Death ◽  
Correct Forecast

The analysis of literature data on the most common general clinical and specific systems for predicting the outcome of peritonitis was carried out. The informativeness of the methods for predicting the outcome of peritonitis was performed according to the parameters of sensitivity and specificity (Se and Sp). The sum of the proportions of correct forecast results characterizes the accuracy of the method (Ac). We also calculated the predictive value of a positive result (PPV; hereinafter referred to as predictive value), which is the proportion (probability) of unfavorable outcomes among all patients with a high risk of death. The article also demonstrates the assessment of predictive ability using the example of four common scales for predicting the outcome of secondary peritonitis. The results of the study showed that none of the studied systems for predicting the outcome of peritonitis is universal and absolutely reliable. Despite the fact that all the studied systems (scales) are used in clinical practice, none of them can completely satisfy surgeons, primarily in the choice of access, the volume of surgery and the option for its completion.

scholarly journals Can Computed Tomography-Based Radiomics Potentially Discriminate Between Anterior Mediastinal Cysts and type B1 and B2 thymomas?

2020 ◽  
Author(s):  
Lulu Liu ◽  
Fangxiao Lu ◽  
Peipei Pang ◽  
Guoliang Shao
Keyword(s):  
Computed Tomography ◽  
Sensitivity And Specificity ◽  
Texture Features ◽  
Training Dataset ◽  
Features Selection ◽  
Clinical Factors ◽  
Combined Model ◽  
Test Dataset ◽  
Enhanced Ct ◽  
Mediastinal Cysts

Abstract Background: Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resources waste. The purpose of this study is to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas.Methods: A group of 188 patients with pathologically confirmed AMC (106 cases misdiagnosed as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the Artificial Intelligence Kit (AK) software. A total of 396 tumor texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis and LASSO were used to features selection and then the radiomics signature (radscore) were obtained. The combined model including radscore and independent clinical factors were developed. The model performances were evaluated on discrimination, calibration curve.Results: Two radscore model were constructed from the unenhanced and enhanced phases based on the selected 4 and 3 features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3% and 83.8% in the training dataset and 0.899, 84.6%, 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model). Conclusions: The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Sign in / Sign up

Export Citation Format

Share Document