ABSTRACT
Noninvasive, accurate, and simultaneous grading of liver fibrosis, inflammation, and steatosis is valuable for reversing the progression and improving the prognosis quality of chronic liver diseases (CLDs). In this study, we established an artificial intelligence framework for simultaneous grading diagnosis of these three pathological types through fusing multimodal tissue characterization parameters dug by quantitative ultrasound methods derived from ultrasound radiofrequency signals, B-mode images, shear wave elastography images, and clinical ultrasound systems, using the liver biopsy results as the classification criteria. One hundred forty-two patients diagnosed with CLD were enrolled in this study. The results show that for the classification of fibrosis grade ≥ F1, ≥ F2, ≥ F3, and F4, the highest AUCs were respectively 0.69, 0.82, 0.84, and 0.88 with single clinical indicator alone, and were 0.81, 0.83, 0.89, and 0.91 with the proposed method. For the classification of inflammation grade ≥ A2 and A3, the highest AUCs were respectively 0.66 and 0.76 with single clinical indicator alone and were 0.80 and 0.93 with the proposed method. For the classification of steatosis grade ≥ S1 and ≥ S2, the highest AUCs were respectively 0.71 and 0.90 with single clinical indicator alone and were 0.75 and 0.92 with the proposed method. The proposed method can effectively improve the grading diagnosis performance compared with the present clinical indicators and has potential applications for noninvasive, accurate, and simultaneous diagnosis of CLDs.
ABSTRACT
BACKGROUND: Tuberculosis is one of the main infectious diseases threatening human health, especially in HIV co-infected patients. Xpert® MTB/RIF assay amplifies the rpoB gene of MTB was recommended by the World Health Organization as the initial diagnostic test in cases of suspected infections with Mycobacterium tuberculosis (MTB) or HIV-coinfected TB. METHODS: A 44-year-old male HIV-positive patient co-infected with MTB presented with low-grade fever for 3 months. Rifampicin (RIF) resistance was detected in the celiac pus but not in the pleural effusion using Xpert® MTB/RIF assay. The same samples were then sequenced by next-generation sequencing (NGS) and in-house PCR for rpoB gene. RESULTS: The results of NGS and in-house PCR, however, were paradoxical in the same samples with low or no mutation sequences of RIF resistance. The patient's tuberculosis (TB) therapy was optimized based on first-line anti-TB drugs and antiretroviral treatment. The patient improved with this therapy. CONCLUSIONS: Even with high specificity, false positive results remain possible and RIF resistance detection by Xpert must be considered for clinical interpretation.