Embedded-deep-learning-based sample-to-answer device for on-site malaria diagnosis.

Improvements in digital microscopy are critical for the development of a malaria diagnosis method that is accurate at the cellular level and exhibits satisfactory clinical performance. Digital microscopy can be enhanced by improving deep learning algorithms and achieving consistent staining results. In this study, a novel miLab™ device incorporating the solid hydrogel staining method was proposed for consistent blood film preparation, eliminating the use of complex equipment and liquid reagent maintenance. The miLab™ ensures consistent, high-quality, and reproducible blood films across various hematocrits by leveraging deformable staining patches. Embedded-deep-learning-enabled miLab™ was utilized to detect and classify malarial parasites from autofocused images of stained blood cells using an internal optical system. The results of this method were consistent with manual microscopy images. This method not only minimizes human error but also facilitates remote assistance and review by experts through digital image transmission. This method can set a new paradigm for on-site malaria diagnosis. The miLab™ algorithm for malaria detection achieved a total accuracy of 98.86% for infected red blood cell (RBC) classification. Clinical validation performed in Malawi demonstrated an overall percent agreement of 92.21%. Based on these results, miLab™ can become a reliable and efficient tool for decentralized malaria diagnosis.

Enhancing malaria detection in resource-limited areas: A high-performance colorimetric LAMP assay for Plasmodium falciparum screening.

Malaria eradication efforts in resource-limited areas require a rapid, economical, and accurate tool for detecting of the low parasitemia. The malaria rapid diagnostic test (mRDT) is the most suitable for on-site detection of the deadliest form of malaria, Plasmodium falciparum. However, the deletions of histidine rich protein 2 and 3 genes are known to compromise the effectiveness of mRDT. One of the approaches that have been explored intensively for on-site diagnostics is the loop-mediated isothermal amplification (LAMP). LAMP is a one-step amplification that allows the detection of Plasmodium species in less than an hour. Thus, this study aims to present a new primer set to enhance the performance of a colorimetric LAMP (cLAMP) for field application. The primer binding regions were selected within the A-type of P. falciparum 18S rRNA genes, which presents a dual gene locus in the genome. The test result of the newly designed primer indicates that the optimal reaction condition for cLAMP was 30 minutes incubation at 65°C, a shorter incubation time compared to previous LAMP detection methods that typically takes 45 to 60 minutes. The limit of detection (LoD) for the cLAMP using our designed primers and laboratory-grown P. falciparum (3D7) was estimated to be 0.21 parasites/µL which was 1,000-fold higher than referencing primers. Under optimal reaction condition, the new primer sets showed the sensitivity (100%, 95% CI: 80.49-100%) and specificity (100%, 95% CI: 94.64-100%) with 100% (95% CI: 95.70-100%) accuracy on the detection of dried blood spots from Malawi (n = 84). Briefly, the newly designed primer set for P. falciparum detection exhibited high sensitivity and specificity compared to referenced primers. One great advantage of this tool is its ability to be detected by the naked eye, enhancing field approaches. Thus, this tool has the potential to be effective for accurate early parasite detection in resource-limited endemic areas.

Prevalence of drug resistant TB among outpatients at an HIV/TB clinic in Lilongwe, Malawi.

BACKGROUND: We sought to determine the prevalence of drug resistant TB among outpatients initiating TB treatment in Lilongwe, Malawi. METHODS: This was a prospective cohort study of patients 18 years and older initiating TB treatment at Martin Preuss Centre, the primary integrated HIV/TB clinic in Lilongwe, Malawi, from April 2011 to July 2012. Procedures included questionnaires, physical exam, chest x-ray, full blood count and sputum collection. Sputum samples underwent acid-fast bacilli (AFB) smear testing and culture by Lowenstein-Jensen (LJ) and liquid Mycobacteria Growth Indicator Tube (MGIT) methods. Drug sensitivity was investigated using the Hain GenoType MTBDRplus line probe assay. RESULTS: Of the 702 patients, 219 (31.2%) were female and 653 (93.0%) were presenting for first-time TB treatment. HIV co-infection was present in 420 (59.8%) cases, with 137 (32.6%) of those patients receiving antiretroviral therapy at presentation. TB was culture-confirmed in 375 (53.4%) patients, 349 of which were first time treatment and 26 retreatment. Ten cases of isoniazid-resistant TB (2.9% of culture confirmed cases of newly treated TB), one of rifampin-resistant TB (0.3% culture confirmed cases of newly treated TB) and one of multi-drug resistant TB (MDR-TB) (3.8% of culture confirmed cases of retreatment TB) were detected. CONCLUSIONS: MDR-TB prevalence is low among outpatients initiating TB treatment in Lilongwe.

A phase II randomized controlled trial adding oral flucytosine to high-dose fluconazole, with short-course amphotericin B, for cryptococcal meningitis.

BACKGROUND: Cryptococcal meningitis in Africa is associated with up to 70% mortality at 3 months and 500 000 deaths annually. We examined strategies to improve on fluconazole (FLU) monotherapy: addition of flucytosine (5-FC) and/or addition of short-course amphotericin B (AmB). METHODS: In step 1, previously reported, patients were randomized to receive FLU 1200 mg per day with or without 5-FC 100 mg/kg per day for 14 days. In step 2, 43 patients were similarly randomized, with addition of AmB 1 mg/kg per day for 7 days to both arms. After 2 weeks, patients received FLU monotherapy and were followed to 10 weeks. The primary endpoint was rate of clearance of infection (early fungicidal activity, EFA). Secondary endpoints related to safety and mortality. RESULTS: Forty patients (25% with Glasgow Coma Scale <15) were analyzed. EFA for the triple combination arm was greater than that for AmB-FLU: -0.50 ±â€Š0.15 log CFU/day vs. -0.38 ±â€Š0.19 log colony forming units per day (P=0.03); and greater than that for step 1 with FLU-5-FC (-0.28 ±â€Š0.17) or FLU alone (-0.11 ±â€Š0.09). Combined analysis across steps revealed that addition of 5-FC and AmB had significant, independent additive effects on EFA, with trends toward fewer early deaths with addition of 5-FC (4/41 vs. 11/39, P = 0.05) and fewer deaths overall with addition of AmB (13/39 vs. 20/40, P = 0.1). CONCLUSION: Addition of 5-FC and short-course AmB to high-dose FLU significantly enhanced EFA and may be associated with favorable trends in survival. Both these strategies should be tested in a larger phase III study.

Tuberculosis drug resistance and outcomes among tuberculosis inpatients in Lilongwe, Malawi.

UNLABELLED: SETTING/OBJECTIVE: We evaluated clinical characteristics, yield of solid vs. liquid culture, polymerase chain reaction (PCR)-based drug-resistance profiles, and clinical outcomes of tuberculosis (TB) inpatients in Lilongwe, Malawi. DESIGN: We enrolled adult patients admitted to the Bwaila TB Ward from Jan-Aug/2010. Evaluations included questionnaires, clinical exam, chest radiograph, HIV status, CD4 lymphocyte count, plasma HIVRNA and sputum analysis including Auramine-O stain, Lowenstein-Jensen (LJ) and Mycobacterial Growth Indicator Tube (MGIT) culture, and susceptibility testing using the HAIN GenoType® MTBDRplus. RESULTS: Eighty-eight patients were enrolled (88% re-treatment, 42% smear positive, 93% pulmonary TB, 74% HIV co-infected). At baseline, 44/88 (50%) MGIT and 28 (32%) LJ cultures were positive with a mean time to positivity of 12.1 (Range 1-42) and 21.5 (Range 7-58) days, respectively. Four percent (3/77) of retreatment patients or 8% of the 38 MGIT+ PCR-confirmed retreatment cases had multi-drug resistant tuberculosis (MDR TB). One MDR TB patient was smear negative and only one MDR patient was identified with LJ. Lower mean hemoglobin at admission was associated with mortality (10.5 vs. 7.5; p<0.01; CI 101 9.8-11.0). CONCLUSIONS: The MDR TB burden among the retreatment population in Lilongwe, Malawi is similar to regional estimates by the WHO (7.7% 95% CI 0-18.1). MDR TB patients are not routinely identified with sputum smear or LJ, suggesting more efficient technology should be adopted.

Combination flucytosine and high-dose fluconazole compared with fluconazole monotherapy for the treatment of cryptococcal meningitis: a randomized trial in Malawi.

BACKGROUND: Cryptococcal meningitis is a major cause of human immunodeficiency virus (HIV)-associated morbidity and mortality in Africa. Improved oral treatment regimens are needed because amphotericin B is neither available nor feasible in many centers. Fluconazole at a dosage of 1200 mg per day is more fungicidal than at a dosage of 800 mg per day, but mortality rates remain unacceptably high. Therefore, we examined the effect of adding oral flucytosine to fluconazole. METHODS: From 13 February through 2 December 2008, HIV-seropositive, antiretroviral-naive patients experiencing their first episode of cryptococcal meningitis were randomized to receive (1) 14 days of fluconazole (1200 mg per day) alone or (2) in combination with flucytosine (100 mg/kg per day) followed by fluconazole (800 mg per day), with both groups undergoing 10 weeks of follow-up. The primary end point was early fungicidal activity, derived from quantitative cerebrospinal fluid cultures on days 1, 3, 7, and 14. Secondary end points were safety and 2- and 10-week mortality. RESULTS: Forty-one patients were analyzed. Baseline mental status, cryptococcal burden, opening pressure, CD4(+) cell count, and HIV load were similar between groups. Combination therapy was more fungicidal than fluconazole alone (mean early fungicidal activity +/- standard deviation -0.28 +/- 0.17 log colony-forming units [CFU]/mL per day vs -0.11 +/- 0.09 log CFU/mL per day; P < .001). The combination arm had fewer deaths by 2 weeks (10% vs 37%) and 10 weeks (43% vs 58%). More patients had grade III or IV neutropenia with combination therapy (5 vs 1, within the first 2 weeks; P = .20), but there was no increase in infection-related adverse events. CONCLUSIONS: The results suggest that optimal oral treatment for cryptococcal meningitis is high-dose fluconazole with flucytosine. Efforts are needed to increase availability of flucytosine in Africa. Clinical trials registration. isrctn.org Identifier: ISRCTN02725351.