Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling.

OBJECTIVES: To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling. METHODS: A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10-3 mm2/s were obtained and compared by the McNemar test. RESULTS: The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883-0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015). CONCLUSION: Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models. KEY POINTS: • When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4-9.7%, at the price of slightly degraded sensitivity by 1.5-1.8%, and overall had improved accuracy by 2.6-2.9%. • When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC. • When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

Association of ACE insertion or deletion polymorphisms with the risk of coronary restenosis after percutaneous coronary intervention: A meta-analysis.

OBJECTIVE: Previous case-control studies on the relationship between the angiotensin-converting enzyme (ACE) gene insertion/deletion (I/D) polymorphisms and coronary restenosis did not reach the same conclusion. In the present study, we aimed to further evaluate the relationship between the ACE gene I/D polymorphisms and coronary restenosis, after percutaneous coronary intervention (PCI). METHODS: By searching PubMed, EMBase, the Chinese Biomedical Literature Database and Wanfang database, we selected 16 case-control studies related to ACE gene I/D polymorphism and coronary restenosis after PCI. To test for heterogeneity in each study, we utilized the Q-test and I(2) test. To merge the odds ratio (OR) and 95% CI, we utilized the random effects model during the analyses. RESULTS: The present study included 4693 subjects: 1241 patients with coronary restenosis and 3452 without coronary restenosis. By meta-analysis, we found there was significant association of ACE gene I/D polymorphism with coronary restenosis (D allele versus I allele: OR = 1.92; 95% CI (1.40-2.43); p < 0.001). A subgroup analysis, by stratification according to ethnicity, also showed that this association was found not only in the Caucasian population ((D allele versus I allele: OR = 1.94; 95% CI (1.38-2.80); p < 0.001)), but also in the Asian population ((D allele versus I allele: OR = 1.83; 95% CI (1.05-3.20); p = 0.03)). After stratification according to age, we found that the D allele carriers have a higher risk for development of coronary restenosis in subjects < 60 years old (OR = 2.13; 95% CI: 1.40-3.24; p = 0.0004); while in the subjects ⩾ 60 years old, the association was present with bordering significance (OR = 1.48; 95%CI: 0.98-2.25; p = 0.06). CONCLUSIONS: The present study suggested that the ACE gene I/D polymorphism was associated with coronary restenosis, regardless of age and ethnicity.

Correlation of ACE gene deletion/insertion polymorphism and risk of pregnancy-induced hypertension: a meta-analysis based on 10,236 subjects.

OBJECTIVES: To clarify the association of angiotensin-converting enzyme (ACE) gene deletion/insertion polymorphism with risk of pregnancy-induced hypertension. METHODS: We systematically searched China National Knowledge Infrastructure, Wanfang database, Chongqing WeiPu database and PubMed up to March 2014 to collect related case-control studies. RevMan 5.0 software was used for meta-analysis after evaluating the quality of enrolled studies and extracting the data. RESULTS: A total of 45 case-control studies was selected, including 10,236 subjects. The meta-analysis was assessed by odds ratios (ORs) and 95% confidence intervals (CIs) after genotype consolidation. In total, D allele vs I allele: OR 1.57, 95% CI 1.33-1.86; genotype DD vs genotype II + DI: OR 1.86, 95% CI 1.48-2.32; genotype II vs genotype DI + DD: OR 0.65, 95% CI 0.53-0.80. In the Asian population, D allele vs I allele: OR 1.80, 95% CI 1.36-2.38; genotype DD vs genotype II + DI: OR 2.25, 95% CI 1.53-3.30; genotype II vs genotype DI + DD: OR 0.56, 95% CI 0.41-0.76. In the Caucasian population, D allele vs. I allele: OR 1.24, 95% CI 1.08-1.44; genotype DD vs. genotype II + DI: OR 1.25, 95% CI 1.10-1.41; genotype II vs. genotype DI + DD: OR 0.96, 95% CI 0.83-1.11. CONCLUSION: The ACE gene insertion/deletion polymorphism is associated with the risk of pregnancy-induced hypertension.