Comparing machine learning screening approaches using clinical data and cytokine profiles for COVID-19 in resource-limited and resource-abundant settings.

Accurate screening of COVID-19 infection status for symptomatic patients is a critical public health task. Although molecular and antigen tests now exist for COVID-19, in resource-limited settings, screening tests are often not available. Furthermore, during the early stages of the pandemic tests were not available in any capacity. We utilized an automated machine learning (ML) approach to train and evaluate thousands of models on a clinical dataset consisting of commonly available clinical and laboratory data, along with cytokine profiles for patients (n = 150). These models were then further tested for generalizability on an out-of-sample secondary dataset (n = 120). We were able to develop a ML model for rapid and reliable screening of patients as COVID-19 positive or negative using three approaches: commonly available clinical and laboratory data, a cytokine profile, and a combination of the common data and cytokine profile. Of the tens of thousands of models automatically tested for the three approaches, all three approaches demonstrated > 92% sensitivity and > 88 specificity while our highest performing model achieved 95.6% sensitivity and 98.1% specificity. These models represent a potential effective deployable solution for COVID-19 status classification for symptomatic patients in resource-limited settings and provide proof-of-concept for rapid development of screening tools for novel emerging infectious diseases.

Polyostotic Paget's disease.

Paget's disease of bone is a common metabolic bone disease in most of the European countries. The disease has distinct geographical distribution being rare in Asia. We report Paget's disease in a 70 years old Pakistani male who presented with history of pain in right leg with difficulty in walking for the last 5 months. Plain X-ray raised suspicion of Paget's disease of bone. Technetium-99m MDP bone scan showed involvement of multiple bones. Bone biopsy confirmed the diagnosis. This case illustrates that Paget's disease of bone does exist in Pakistan.

Treatment of uncomplicated plasmodium falciparum malaria with quinine-doxycycline combination therapy.

OBJECTIVE: To assess the efficacy and tolerability of quinine-doxycycline combination therapy in uncomplicated falciparum malaria in terms of malarial parasite clearance from peripheral blood. METHODS: One hundred adult males were included in the study. Malarial parasite counts in peripheral blood films were determined at the time of admission and then 12 hourly until clearance and thereafter weekly for 28 days (4 weeks). Treatment was started with quinine sulphate 10 mg of salt/kg body weight 8 hourly orally for a minimum period of 3 days and maximum of 7 days along with doxycycline 100 mg 12 hourly orally for 7 days. Primary efficacy outcome measure was early treatment failure, whereas secondary efficacy outcome measure was late treatment failure. Tolerability outcome measure was the development of treatment related adverse effects resulting in discontinuation from the study. RESULTS: The primary efficacy outcome measure of the study i.e. malarial parasite index declined from a mean of 6.34 (SD +/- 2.83) before treatment to zero at day 7 of treatment. Parasite clearance time was 1-7 days (mean 3.58, SD +/- 1.28). Mean duration of quinine treatment till clearance of malarial parasites was 4.63 days (SD +/- 1.38). Mean duration of fever was 2.96 days (range 1 to 6 days). There was no early or late treatment failure. There was no relapse during the 28 days follow up period. Drug related side effects were mild and did not warrant discontinuation of treatment in any patient. CONCLUSION: Quinine-doxycycline combination is effective in southern Pakistan. Randomized controlled trials are needed to further validate the claim.