Comparison of deep learning models to traditional Cox regression in predicting survival of colon cancer: Based on the SEER database.

BACKGROUND AND AIM: In this study, a deep learning algorithm was used to predict the survival rate of colon cancer (CC) patients, and compared its performance with traditional Cox regression. METHODS: In this population-based cohort study, we used the characteristics of patients diagnosed with CC between 2010 and 2015 from the Surveillance, Epidemiology and End Results (SEER) database. The population was randomized into a training set (n = 10 596, 70%) and a test set (n = 4536, 30%). Brier scores, area under the (AUC) receiver operating characteristic curve and calibration curves were used to compare the performance of the three most popular deep learning models, namely, artificial neural networks (ANN), deep neural networks (DNN), and long-short term memory (LSTM) neural networks with Cox proportional hazard (CPH) model. RESULTS: In the independent test set, the Brier values of ANN, DNN, LSTM and CPH were 0.155, 0.149, 0.148, and 0.170, respectively. The AUC values were 0.906 (95% confidence interval [CI] 0.897-0.916), 0.908 (95% CI 0.899-0.918), 0.910 (95% CI 0.901-0.919), and 0.793 (95% CI 0.769-0.816), respectively. Deep learning showed superior promising results than CPH in predicting CC specific survival. CONCLUSIONS: Deep learning showed potential advantages over traditional CPH models in terms of prognostic assessment and treatment recommendations. LSTM exhibited optimal predictive accuracy and has the ability to provide reliable information on individual survival and treatment recommendations for CC patients.

Association between anemia and depression: results from NHANES 2005-2018 and mendelian randomization analyses.

BACKGROUND: The relationship between anemia and depression remains controversial. OBJECTIVE: To explore the association between anemia/hemoglobin and depression. METHODS: The data for our cross-sectional study were obtained from the National Health and Nutrition Examination Survey (NHANES) 2005-2018. Weighted multivariate logistic regression was performed to examine the association between anemia/hemoglobin and depression. Inverse variance weighted (IVW), weighted-median, and MR-Egger were used in MR analyses to assess the causal relationship between anemia/hemoglobin and depression. Heterogeneity and directional pleiotropy were assessed using the Cochrane Q test and Egger-intercept test, respectively. Sensitivity analysis was conducted by the leave-one-out approach. All analyses were carried out using IBM SPSS 24.0 and R version 4.2.2. RESULTS: A total of 29,391 NHANES participants were included in this study. After adjusting for all covariates, the association between anemia/hemoglobin and depression was not significant (P < 0.05). IVW estimates revealed that broad anemia had no significant effect on the risk of depression (OR = 1.00, 95% CI = 0.99-1.01, P = 0.432). Findings of weighted median and MR-Egger were consistent with those from IVW (weighted median: OR = 1.00, 95% CI = 0.99-1.02; P = 0.547; MR-Egger: OR = 1.01, 95% CI = 0.98-1.03, P = 0.605). The results of three MR Analyses methods also showed no causal association between hemoglobin and depression. CONCLUSIONS: Our findings do not support a causal association between anemia and depression. The association between hemoglobin concentration and depression was not statistically significant either.

Diagnostic performance of magnetic resonance imaging-based machine learning in Alzheimer's disease detection: a meta-analysis.

PURPOSE: Advanced machine learning (ML) algorithms can assist rapid medical image recognition and realize automatic, efficient, noninvasive, and convenient diagnosis. We aim to further evaluate the diagnostic performance of ML to distinguish patients with probable Alzheimer's disease (AD) from normal older adults based on structural magnetic resonance imaging (MRI). METHODS: The Medline, Embase, and Cochrane Library databases were searched for relevant literature published up until July 2021. We used the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool and Checklist for Artificial Intelligence in Medical Imaging (CLAIM) to evaluate all included studies' quality and potential bias. Random-effects models were used to calculate pooled sensitivity and specificity, and the Deeks' test was used to assess publication bias. RESULTS: We included 24 models based on different brain features extracted by ML algorithms in 19 papers. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and area under the summary receiver operating characteristic curve for ML in detecting AD were 0.85 (95%CI 0.81-0.89), 0.88 (95%CI 0.84-0.91), 7.15 (95%CI 5.40-9.47), 0.17 (95%CI 0.12-0.22), 43.34 (95%CI 26.89-69.84), and 0.93 (95%CI 0.91-0.95). CONCLUSION: ML using structural MRI data performed well in diagnosing probable AD patients and normal elderly. However, more high-quality, large-scale prospective studies are needed to further enhance the reliability and generalizability of ML for clinical applications before it can be introduced into clinical practice.

Identifying depression in the United States veterans using deep learning algorithms, NHANES 2005-2018.

BACKGROUND: Depression is a common mental health problem among veterans, with high mortality. Despite the numerous conducted investigations, the prediction and identification of risk factors for depression are still severely limited. This study used a deep learning algorithm to identify depression in veterans and its factors associated with clinical manifestations. METHODS: Our data originated from the National Health and Nutrition Examination Survey (2005-2018). A dataset of 2,546 veterans was identified using deep learning and five traditional machine learning algorithms with 10-fold cross-validation. Model performance was assessed by examining the area under the subject operating characteristic curve (AUC), accuracy, recall, specificity, precision, and F1 score. RESULTS: Deep learning had the highest AUC (0.891, 95%CI 0.869-0.914) and specificity (0.906) in identifying depression in veterans. Further study on depression among veterans of different ages showed that the AUC values for deep learning were 0.929 (95%CI 0.904-0.955) in the middle-aged group and 0.924(95%CI 0.900-0.948) in the older age group. In addition to general health conditions, sleep difficulties, memory impairment, work incapacity, income, BMI, and chronic diseases, factors such as vitamins E and C, and palmitic acid were also identified as important influencing factors. CONCLUSIONS: Compared with traditional machine learning methods, deep learning algorithms achieved optimal performance, making it conducive for identifying depression and its risk factors among veterans.

Accuracy of clustered regularly interspaced short palindromic repeats (CRISPR) to diagnose COVID-19, a meta-analysis.

OBJECTIVE: To estimate the accuracy of clustered regularly interspaced short palindromic repeats (CRISPR) in determining coronavirus disease-19 (COVID-19). METHODS: As of January 31, 2022, PubMed, Web of Science, Embase, Science Direct, Wiley and Springer Link were searched. Sensitivity, specificity, likelihood ratio (LR), diagnostic odds ratio (DOR) and area under the summary receiver-operating characteristic (AUC) curve were used to assess the accuracy of CRISPR. RESULTS: According to the inclusion criteria, 5857 patients from 54 studies were included in this meta-analysis. The pooled sensitivity, specificity and AUC were 0.98, 1.00 and 1.00, respectively. For CRISPR-associated (Cas) proteins-12, the sensitivity, specificity was 0.96, 1.00, respectively. For Cas-13, the sensitivity and specificity were 0.99 and 0.99. CONCLUSION: This meta-analysis showed that the diagnostic performance of CRISPR is close to the gold standard, and it is expected to meet the Point of care requirements in resource poor areas.

Diagnostic accuracy of optical coherence tomography for margin assessment in breast-conserving surgery: A systematic review and meta-analysis.

BACKGROUND: Breast cancer is the most common malignant tumor among women, and its incidence is increasing annually. At present, the results of the study on whether optical coherence tomography (OCT) can be used as an intraoperative margin assessment method for breast-conserving surgery (BCS) are inconsistent. We herein conducted this systematic review and meta-analysis to assess the diagnostic value of OCT in BCS. METHODS: PubMed, Web of Science, Cochrane Library, and Embase were used to search relevant studies published up to September 15, 2022. We used Review Manager 5.4, Meta-Disc 1.4, and STATA 16.0 for statistical analysis. RESULTS: The results displayed 18 studies with 782 patients included according to the inclusion and exclusion criteria. Meta-analysis showed the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR) and the area under the curve (AUC) of OCT in the margin assessment of BCS were 0.91 (95% CI 0.88-0.93), 0.88 (95% CI 0.83-0.92), 7.53 (95% CI 5.19-10.93), 0.11(95% CI 0.08-0.14), 70.37 (95% CI 39.78-124.47), and 0.94 (95% CI 0.92-0.96), respectively. CONCLUSIONS: OCT is a promising technique in intraoperative margin assessment of breast cancer patients.

Using machine learning algorithms to identify chronic heart disease: National Health and Nutrition Examination Survey 2011-2018.

OBJECTIVE: The number of heart disease patients is increasing. Establishing a risk assessment model for chronic heart disease (CHD) based on risk factors is beneficial for early diagnosis and timely treatment of high-risk populations. METHODS: Four machine learning models, including logistic regression, support vector machines (SVM), random forests, and extreme gradient boosting (XGBoost), were used to evaluate the CHD among 14 971 participants in the National Health and Nutrition Examination Survey from 2011 to 2018. The area under the receiver-operator curve (AUC) is the indicator that we evaluate the model. RESULTS: In four kinds of models, SVM has the best classification performance (AUC = 0.898), and the AUC value of logistic regression and random forest were 0.895 and 0.894, respectively. Although XGBoost performed the worst with an AUC value of 0.891. There was no significant difference among the four algorithms. In the importance analysis of variables, the three most important variables were taking low-dose aspirin, chest pain or discomfort, and total amount of dietary supplements taken. CONCLUSION: All four machine learning classifiers can identify the occurrence of CHD based on population survey data. We also determined the contribution of variables in the prediction, which can further explore their effectiveness in actual clinical data.

Risk of contralateral ovarian cancer in patients undergoing conservative surgery for ovarian cancer.

BACKGROUND: Among patients with ovarian cancer (OC), the risk of contralateral OC remains controversial and few studies have focused on the occurrence of contralateral OC after conservative surgery. METHODS: Basing on the Surveillance, Epidemiology, and End Results (SEER) database registered between 2000 and 2018, Logistic and Cox regressions were established to test the risk factors of contralateral OC. Kaplan-Meier mothed was used to calculate the cumulative risk curve for contralateral OC and compared using log-rank test. Furthermore, the frequency of contralateral OC and standardized incidence ratios (SIRs) were evaluated. RESULTS: 18807 patients were included, 69 patients developed contralateral OC. Logistic and Cox regressions showed patients diagnosed >50 years had lower risk of contralateral OC (Odds ratio [OR]:0.42, 95% confidence interval [CI]: 0.24-0.73; Hazard ratios [HR]:0.44, 95%CI:0.24-0.77). Patients with radical surgery had lower contralateral OC risk (OR:0.20, 95%CI: 0.11-0.36; HR: 0.17, 95%CI: 0.09-0.30). The SIR for contralateral OC was high in all patients (SIR: 2.37, 95%CI: 1.85-3.00) and highest if patients diagnosed <50 years with conservative surgery (SIR: 27.33, 95%CI: 19.86-36.69). However, the SIR for contralateral OC was low in patients diagnosed ≥50 years with radical surgery (SIR: 0.54, 95%CI: 0.26-1.00). No statistically significant SIRs were observed in patients diagnosed ≥50 years with conservative surgery and patients diagnosed <50 years with radical surgery. CONCLUSIONS: Our study provided some information for clinicians to assess the risk of contralateral OC and suggested young patients should not undergo hysterectomy to prevent contralateral OC. Moreover, clinical surveillance cannot be relaxed.