Background Accurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming and knowledge-intensive, but is essential for CRC patients’ treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis of CRC based on daily image analyses. Methods Based on a state-of-the-art transfer-learned deep convolutional neural network in artificial intelligence (AI), we proposed a novel patch aggregation strategy for clinic CRC diagnosis using weakly labeled pathological whole-slide image (WSI) patches. This approach was trained and validated using an unprecedented and enormously large number of 170,099 patches, > 14,680 WSIs, from > 9631 subjects that covered diverse and representative clinical cases from multi-independent-sources across China, the USA, and Germany. Results Our innovative AI tool consistently and nearly perfectly agreed with (average Kappa statistic 0.896) and even often better than most of the experienced expert pathologists when tested in diagnosing CRC WSIs from multicenters. The average area under the receiver operating characteristics curve (AUC) of AI was greater than that of the pathologists (0.988 vs 0.970) and achieved the best performance among the application of other AI methods to CRC diagnosis. Our AI-generated heatmap highlights the image regions of cancer tissue/cells. Conclusions This first-ever generalizable AI system can handle large amounts of WSIs consistently and robustly without potential bias due to fatigue commonly experienced by clinical pathologists. It will drastically alleviate the heavy clinical burden of daily pathology diagnosis and improve the treatment for CRC patients. This tool is generalizable to other cancer diagnosis based on image recognition.

This study explores the impact of clopidogrel on the pharmacokinetics of omeprazole related to CYP2C19 genetic polymorphisms. Twelve healthy volunteers (6 CYP2C19*1/*1, 5 CYP2C19*2/*2, and 1 CYP2C19*2/*3) are enrolled in a 2-phase randomized crossover trial. In each phase, the volunteers are administered a single oral dose of omeprazole 40 mg after pretreatment of either placebo or clopidogrel (300 mg on the first day and then 75 mg once daily for 3 consecutive days). Plasma concentrations of omeprazole and its metabolites are quantified by high-performance liquid chromatography with UV detection. After clopidogrel treatment, the AUC(0-infinity) of omeprazole increases by 30.02% +/- 18.03% (P = .004) and that of 5-hydroxyomeprazole decreases by 24.30% +/- 11.66% (P = .032) in CYP2C19*1/*1. The AUC(0-infinity) ratios of omeprazole to 5-hydroxyomeprazole increase by 74.98% +/- 35.48% (P = .001) and those of omeprazole to omeprazole sulfone do not change significantly (P = .832) in CYP2C19*1/*1. No significant alteration is observed in CYP2C19*2/*2 or *3. Clopidogrel inhibits CYP2C19-dependent hydroxylation of omeprazole in CYP2C19*1/*1 and has no impact on CYP3A4-catalyzed sulfoxidation of omeprazole.

The authors investigated the effect of herbal medicine Schisandra chinensis extract (SchE) and Ginkgo biloba extract (GBE) on the oral pharmacokinetics of P-glycoprotein substrate talinolol in humans. Twelve healthy male volunteers took a single 100-mg oral dose of talinolol either alone or after pretreatment with 300 mg SchE twice daily or with 120 mg GBE three times daily for 14 days. On day 14, a single 100-mg oral dose of talinolol was administered. Plasma concentrations of talinolol from zero to 24 h were measured by high-performance liquid chromatography. SchE increased the area under the curve (AUC)(0-24) of talinolol by 47% (90% confidence interval (CI), 18-84%; p = 0.010), and GBE by 21% (90% CI = 11-32%; p = 0.002). The C(max) of talinolol increased by 51% (90% CI = 21-89%; p = 0.007) with SchE treatment and by 33% (90% CI = 18-51%; p = 0.002) with GBE treatment, respectively. The t(1/2) of talinolol increased by 7% (90% CI = -4% to 19%; p = 0.320) with SchE treatment and by 11% (90% CI = -12% to 38%; p = 0.436) with GBE treatment, respectively. The results suggest that both SchE and GBE significantly inhibited P-glycoprotein in humans. Patients receiving either SchE or GBE may require dose adjustments when treated with drugs primarily transported by P-glycoprotein.