Evaluation of an artificial intelligence-based clinical trial matching system in Chinese patients with hepatocellular carcinoma: a retrospective study.

BACKGROUND: Artificial intelligence (AI)-assisted clinical trial screening is a promising prospect, although previous matching systems were developed in English, and relevant studies have only been conducted in Western countries. Therefore, we evaluated an AI-based clinical trial matching system (CTMS) that extracts medical data from the electronic health record system and matches them to clinical trials automatically. METHODS: This study included 1,053 consecutive inpatients primarily diagnosed with hepatocellular carcinoma who were referred to the liver tumor center of an academic medical center in China between January and December 2019. The eligibility criteria extracted from two clinical trials, patient attributes, and gold standard were decided manually. We evaluated the performance of the CTMS against the established gold standard by measuring the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and run time required. RESULTS: The manual reviewers demonstrated acceptable interrater reliability (Cohen's kappa 0.65-0.88). The performance results for the CTMS were as follows: accuracy, 92.9-98.0%; sensitivity, 51.9-83.5%; specificity, 99.0-99.1%; PPV, 75.7-85.1%; and NPV, 97.4-98.9%. The time required for eligibility determination by the CTMS and manual reviewers was 2 and 150 h, respectively. CONCLUSIONS: We found that the CTMS is particularly reliable in excluding ineligible patients in a significantly reduced amount of time. The CTMS excluded ineligible patients for clinical trials with good performance, reducing 98.7% of the work time. Thus, such AI-based systems with natural language processing and machine learning have potential utility in Chinese clinical trials.

[Effects of intercropping on cadmium uptake by maize and tomato].

In order to explore the effect of intercropping on the uptake of heavy metal cadmium (Cd), pot experiments were undertaken using three different planting methods: monoculture, restrictive intercropping and intercropping. The effects of Cd accumulation in different plant parts, and their causes, were examined using a plant species regarded as a relatively high heavy metal accumulator (tomato: Lycopersicon esculentum var. Zhongshu 4) and a species regarded as a relatively low heavy metal accumulator (maize: Zea mays L. var. Jinzhumi). Cd levels for all experiments were 3.70 mg/kg. Results indicate that restricted intercropping and intercropping of tomato and maize increased the accumulation of Cd (from 13.52 mg/kg to 24.94 mg/kg and 27.30 mg/kg in tomato leaf, respectively). Compared with the control group, pH levels in soil surrounding tomato roots in the intercropped samples decreased and the activity of acid phosphatase increased, while the activity of urease decreased. Intercropping can also change the structure of the crop root microorganism population, increase the abundance of microbiological species that promote the uptake of heavy metals, and finally achieve high accumulation of Cd in tomatoes. Our research results provide reference for controlling soil heavy metal pollution and ensuring food safety by using an intercropping model.

Exogenous nitric oxide enhances cadmium tolerance of rice by increasing pectin and hemicellulose contents in root cell wall.

To study the mechanisms of exogenous NO contribution to alleviate the cadmium (Cd) toxicity in rice (Oryza sativa), rice plantlets subjected to 0.2-mM CdCl(2) exposure were treated with different concentrations of sodium nitroprusside (SNP, a NO donor), and Cd toxicity was evaluated by the decreases in plant length, biomass production and chlorophyll content. The results indicated that 0.1 mM SNP alleviated Cd toxicity most obviously. Atomic absorption spectrometry and fluorescence localization showed that treatment with 0.1 mM SNP decreased Cd accumulation in both cell walls and soluble fraction of leaves, although treatment with 0.1 mM SNP increased Cd accumulation in the cell wall of rice roots obviously. Treatment with 0.1 mM SNP in nutrient solution had little effect on the transpiration rate of rice leaves, but this treatment increased pectin and hemicellulose content and decreased cellulose content significantly in the cell walls of rice roots. Based on these results, we conclude that decreased distribution of Cd in the soluble fraction of leaves and roots and increased distribution of Cd in the cell walls of roots are responsible for the NO-induced increase of Cd tolerance in rice. It seems that exogenous NO enhances Cd tolerance of rice by increasing pectin and hemicellulose content in the cell wall of roots, increasing Cd accumulation in root cell wall and decreasing Cd accumulation in soluble fraction of leaves.

Cadmium decreases crown root number by decreasing endogenous nitric oxide, which is indispensable for crown root primordia initiation in rice seedlings.

Cadmium (Cd) is toxic to crown roots (CR), which are essential for maintaining normal growth and development in rice seedlings. Nitric oxide (NO) is an important signaling molecule that plays a pivotal role in plant root organogenesis. Here, the effects of Cd on endogenous NO content and root growth conditions were studied in rice seedlings. Results showed that similar to the NO scavenger, cPTIO, Cd significantly decreased endogenous NO content and CR number in rice seedlings, and these decreases were recoverable with the application of sodium nitroprusside (SNP, a NO donor). Microscopic analysis of root collars revealed that treatment with Cd and cPTIO inhibited CR primordia initiation. In contrast, although SNP partially recovered Cd-caused inhibition of CR elongation, treatment with cPTIO had no effect on CR elongation. L: -NMMA, a widely used nitric oxide synthase (NOS) inhibitor, decreased endogenous NO content and CR number significantly, while tungstate, a nitrate reductase (NR) inhibitor, had no effect on endogenous NO content and CR number. Moreover, enzyme activity assays indicated that treatment with SNP inhibited NOS activity significantly, but had no effect on NR activity. All these results support the conclusions that a critical endogenous NO concentration is indispensable for rice CR primordia initiation rather than elongation, NOS is the main source for endogenous NO generation, and Cd decreases CR number by inhibiting NOS activity and thus decreasing endogenous NO content in rice seedlings.