Artemisinin-naphthoquine plus lower-dose primaquine to treat and prevent recurrence of Plasmodium vivax malaria: an open-label randomized and non-inferiority trial.

BACKGROUND: Plasmodium vivax malaria, with the widest geographic distribution, can cause severe disease and death. Primaquine is the main licensed antimalarial drug that can kill hypnozoites. The dose-dependent acute haemolysis in individuals with glucose-6-phospate dehydrogenase (G6PD) deficiency is the main safety concern when using primaquine. The recommended treatment regimen for P. vivax malaria is chloroquine plus primaquine for 14 days (CQPQ14) in Myanmar. The study aimed to evaluate the therapeutic efficacy, safety and adherence for the regimen of artemisinin-naphthoquine plus primaquine for 3 days (ANPQ3) in patients with P. vivax infections compared to those with CQPQ14. METHODS: The patients in the ANPQ3 group were given fixed-dose artemisinin-naphthoquine (a total 24.5 mg/kg bodyweight) plus a lower total primaquine dose (0.9 mg/kg bodyweight) for 3 days. The patients in the CQPQ14 group were given a total chloroquine dose of 30 mg/kg body weight for 3 days plus a total primaquine dose of 4.2 mg/kg bodyweight for 14 days. All patients were followed up for 365 days. RESULTS: A total of 288 patients completed follow-up, 172 in the ANPQ3 group and 116 in the CQPQ14 group. The first recurrence patients were detected by day 58 in both groups. By day 182, 16 recurrences had been recorded: 12 (7.0%) patients in the ANPQ3 group and 4 (3.4%) in the CQPQ14 group. The difference in recurrence-free patients was 3.5 (-8.6 to 1.5) percentage points between ANPQ3 and CQPQ14 group (P = 0.2946). By day 365, the percentage of recurrence-free patients was not significant between the two groups (P = 0.2257). Mean fever and parasite clearance time of ANPQ3 group were shorter than those in CQPQ14 group (P ≤ 0.001). No severe adverse effect was observed in ANPQ3 group, but five (3.9%) patients had acute haemolysis in CQPQ14 group (P = 0.013). Medication percentage of ANPQ3 group was significantly higher than that of CQPQ14 group (P < 0.0001). CONCLUSIONS: Both ANPQ3 and CQPQ14 promised clinical cure efficacy, and the radical cure efficacy was similar between the ANPQ3 and CQPQ14 group. ANPQ3 clears fever and parasites faster than CQPQ14. ANPQ3 is safer and shows better patient adherence to the regimen for treatment of P. vivax malaria along the China-Myanmar border. TRIAL REGISTRATION: ChiCTR-INR-17012523. Registered 31 August 2017, https://www.chictr.org.cn/showproj.html?proj=21352.

Deep learning predicts cervical lymph node metastasis in clinically node-negative papillary thyroid carcinoma.

OBJECTIVES: Precise determination of cervical lymph node metastasis (CLNM) involvement in patients with early-stage thyroid cancer is fairly significant for identifying appropriate cervical treatment options. However, it is almost impossible to directly judge lymph node metastasis based on the imaging information of early-stage thyroid cancer patients with clinically negative lymph nodes. METHODS: Preoperative US images (BMUS and CDFI) of 1031 clinically node negative PTC patients definitively diagnosed on pathology from two independent hospitals were divided into training set, validation set, internal test set, and external test set. An ensemble deep learning model based on ResNet-50 was built integrating clinical variables, BMUS, and CDFI images using a bagging classifier to predict metastasis of CLN. The final ensemble model performance was compared with expert interpretation. RESULTS: The ensemble deep convolutional neural network (DCNN) achieved high performance in predicting CLNM in the test sets examined, with area under the curve values of 0.86 (95% CI 0.78-0.94) for the internal test set and 0.77 (95% CI 0.68-0.87) for the external test set. Compared to all radiologists averaged, the ensemble DCNN model also exhibited improved performance in making predictions. For the external validation set, accuracy was 0.72 versus 0.59 (p = 0.074), sensitivity was 0.75 versus 0.58 (p = 0.039), and specificity was 0.69 versus 0.60 (p = 0.078). CONCLUSIONS: Deep learning can non-invasive predict CLNM for clinically node-negative PTC using conventional US imaging of thyroid cancer nodules and clinical variables in a multi-institutional dataset with superior accuracy, sensitivity, and specificity comparable to experts. CRITICAL RELEVANCE STATEMENT: Deep learning efficiently predicts CLNM for clinically node-negative PTC based on US images and clinical variables in an advantageous manner. KEY POINTS: • A deep learning-based ensemble algorithm for predicting CLNM in PTC was developed. • Ultrasound AI analysis combined with clinical data has advantages in predicting CLNM. • Compared to all experts averaged, the DCNN model achieved higher test performance.