Wavelet and deep learning-based detection of SARS-nCoV from thoracic X-ray images for rapid and efficient testing.

This paper proposes a wavelet and artificial intelligence-enabled rapid and efficient testing procedure for patients with Severe Acute Respiratory Coronavirus Syndrome (SARS-nCoV) through a deep learning approach from thoracic X-ray images. Presently, the virus infection is diagnosed primarily by a process called the real-time Reverse Transcriptase-Polymerase Chain Reaction (rRT-PCR) based on its genetic prints. This whole procedure takes a substantial amount of time to identify and diagnose the patients infected by the virus. The proposed research uses a wavelet-based convolution neural network architectures to detect SARS-nCoV. CNN is pre-trained on the ImageNet and trained end-to-end using thoracic X-ray images. To execute Discrete Wavelet Transforms (DWT), the available mother wavelet functions from different families, namely Haar, Daubechies, Symlet, Biorthogonal, Coiflet, and Discrete Meyer, were considered. Two-level decomposition via DWT is adopted to extract prominent features peripheral and subpleural ground-glass opacities, often in the lower lobes explicitly from thoracic X-ray images to suppress noise effect, further enhancing the signal to noise ratio. The proposed wavelet-based deep learning models of both, two-class instances (COVID vs. Normal) and four-class instances (COVID-19 vs. PNA bacterial vs. PNA viral vs. Normal) were validated from publicly available databases using k-Fold Cross Validation (k-Fold CV) technique. In addition to these X-ray images, images of recent COVID-19 patients were further used to examine the model's practicality and real-time feasibility in combating the current pandemic situation. It was observed that the Symlet 7 approximation component with two-level manifested the highest test accuracy of 98.87%, followed by Biorthogonal 2.6 with an efficiency of 98.73%. While the test accuracy for Symlet 7 and Biorthogonal 2.6 is high, Haar and Daubechies with two levels have demonstrated excellent validation accuracy on unseen data. It was also observed that the precision, the recall rate, and the dice similarity coefficient for four-class instances were 98%, 98%, and 99%, respectively, using the proposed algorithm.

Delayed haemolysis after treatment with intravenous artesunate in patients with severe malaria in India.

BACKGROUND: Parenteral artesunate is the treatment of choice for severe malaria. It is safe, efficacious and well tolerated anti-malarial. However, delayed haemolysis has been reported in travellers, non-immune individuals and in African children. METHODS: A prospective, observational study was carried out in admitted severe malaria patients receiving parenteral artesunate. The patients were followed up until day 28 for monitoring clinical as well as laboratory parameters for haemolytic anaemia. RESULTS: Twenty-four patients with severe malaria receiving injection artesunate were enrolled in the study. Post-artesunate delayed haemolysis following parenteral artesunate therapy was observed in three of 24 patients (12.5%, 95% confidence interval 4.5-31.2%). Haemolysis was observed in two more patients possibly due to other reasons. The haemoglobin fall ranged from 13.6 to 38.3% from day 7 to day 28 in these patients. CONCLUSION: The possibility of delayed haemolysis should be considered while treating the severe malaria patients with parenteral artesunate. The study highlights the need for further studies in different epidemiological settings.

Ganaplacide (KAF156) plus lumefantrine solid dispersion formulation combination for uncomplicated Plasmodium falciparum malaria: an open-label, multicentre, parallel-group, randomised, controlled, phase 2 trial.

BACKGROUND: Emergence of drug resistance demands novel antimalarial drugs with new mechanisms of action. We aimed to identify effective and well tolerated doses of ganaplacide plus lumefantrine solid dispersion formulation (SDF) in patients with uncomplicated Plasmodium falciparum malaria. METHODS: This open-label, multicentre, parallel-group, randomised, controlled, phase 2 trial was conducted at 13 research clinics and general hospitals in ten African and Asian countries. Patients had microscopically-confirmed uncomplicated P falciparum malaria (>1000 and <150 000 parasites per µL). Part A identified the optimal dose regimens in adults and adolescents (aged ≥12 years) and in part B, the selected doses were assessed in children (≥2 years and <12 years). In part A, patients were randomly assigned to one of seven groups (once a day ganaplacide 400 mg plus lumefantrine-SDF 960 mg for 1, 2, or 3 days; ganaplacide 800 mg plus lumefantrine-SDF 960 mg as a single dose; once a day ganaplacide 200 mg plus lumefantrine-SDF 480 mg for 3 days; once a day ganaplacide 400 mg plus lumefantrine-SDF 480 mg for 3 days; or twice a day artemether plus lumefantrine for 3 days [control]), with stratification by country (2:2:2:2:2:2:1) using randomisation blocks of 13. In part B, patients were randomly assigned to one of four groups (once a day ganaplacide 400 mg plus lumefantrine-SDF 960 mg for 1, 2, or 3 days, or twice a day artemether plus lumefantrine for 3 days) with stratification by country and age (2 to <6 years and 6 to <12 years; 2:2:2:1) using randomisation blocks of seven. The primary efficacy endpoint was PCR-corrected adequate clinical and parasitological response at day 29, analysed in the per protocol set. The null hypothesis was that the response was 80% or lower, rejected when the lower limit of two-sided 95% CI was higher than 80%. This study is registered with EudraCT (2020-003284-25) and ClinicalTrials.gov (NCT03167242). FINDINGS: Between Aug 2, 2017, and May 17, 2021, 1220 patients were screened and of those, 12 were included in the run-in cohort, 337 in part A, and 175 in part B. In part A, 337 adult or adolescent patients were randomly assigned, 326 completed the study, and 305 were included in the per protocol set. The lower limit of the 95% CI for PCR-corrected adequate clinical and parasitological response on day 29 was more than 80% for all treatment regimens in part A (46 of 50 patients [92%, 95% CI 81-98] with 1 day, 47 of 48 [98%, 89-100] with 2 days, and 42 of 43 [98%, 88-100] with 3 days of ganaplacide 400 mg plus lumefantrine-SDF 960 mg; 45 of 48 [94%, 83-99] with ganaplacide 800 mg plus lumefantrine-SDF 960 mg for 1 day; 47 of 47 [100%, 93-100] with ganaplacide 200 mg plus lumefantrine-SDF 480 mg for 3 days; 44 of 44 [100%, 92-100] with ganaplacide 400 mg plus lumefantrine-SDF 480 mg for 3 days; and 25 of 25 [100%, 86-100] with artemether plus lumefantrine). In part B, 351 children were screened, 175 randomly assigned (ganaplacide 400 mg plus lumefantrine-SDF 960 mg once a day for 1, 2, or 3 days), and 171 completed the study. Only the 3-day regimen met the prespecified primary endpoint in paediatric patients (38 of 40 patients [95%, 95% CI 83-99] vs 21 of 22 [96%, 77-100] with artemether plus lumefantrine). The most common adverse events were headache (in seven [14%] of 51 to 15 [28%] of 54 in the ganaplacide plus lumefantrine-SDF groups and five [19%] of 27 in the artemether plus lumefantrine group) in part A, and malaria (in 12 [27%] of 45 to 23 [44%] of 52 in the ganaplacide plus lumefantrine-SDF groups and 12 [50%] of 24 in the artemether plus lumefantrine group) in part B. No patients died during the study. INTERPRETATION: Ganaplacide plus lumefantrine-SDF was effective and well tolerated in patients, especially adults and adolescents, with uncomplicated P falciparum malaria. Ganaplacide 400 mg plus lumefantrine-SDF 960 mg once daily for 3 days was identified as the optimal treatment regimen for adults, adolescents, and children. This combination is being evaluated further in a phase 2 trial (NCT04546633). FUNDING: Novartis and Medicines for Malaria Venture.