# Performance of a smartphone-based malaria screener in detecting malaria in people living with Sickle cell disease

## TL;DR

A smartphone app for malaria detection was tested in people with sickle cell disease in Ghana, showing good sensitivity but needing confirmation due to lower accuracy.

## Contribution

The study evaluates the NLM malaria screener app's performance in diagnosing malaria in sickle cell disease patients, a population with unique diagnostic challenges.

## Key findings

- The NLM app detected 36.2% positive malaria cases, the highest among tested methods.
- The app had a sensitivity of 89.5% but a lower specificity of 67.4% compared to PCR.
- Confirmatory testing is needed to avoid overdiagnosis with the NLM app.

## Abstract

Novel automated digital malaria diagnostic tests are being developed with the advancement of diagnostic tools. Whilst these tools are being evaluated and implemented in the general population, there is the need to focus on special populations such as individuals with Sickle Cell Disease (SCD) who have altered red blood cell morphology and atypical immune responses, which can obscure parasite detection. This study aimed to evaluate the diagnostic performance of one of such tools, the National Library of Medicine (NLM) malaria screener app in people living with sickle cell disease in a malaria-endemic country, Ghana. A descriptive cross-sectional study was conducted among SCD patients attending the Sickle Cell Clinic at Korle Bu Teaching Hospital in Accra, Ghana. Following informed consent, whole blood samples were collected and analyzed using the NLM malaria screener app, conventional microscopy, RDT, and Polymerase Chain Reaction (PCR), with PCR as the reference standard. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of each diagnostic method were compared against PCR results. The NLM app identified the highest number of positive malaria cases, with 110 positive cases (36.2%), while both RDT and microscopy reported the highest number of negatives, with 287 negative cases (94.4%). Compared to PCR, the NLM app demonstrated a sensitivity of 89.5% and a specificity of 67.4%. RDT and microscopy displayed the same sensitivity as the NLM app, each achieving 89.5%. However, while RDT and microscopy had a specificity of 100%, the NLM app had a considerably lower specificity of 67.4%.The NLM malaria screener app shows promise as a preliminary screening tool for malaria in individuals with SCD. However, its lower specificity indicates a need for confirmatory testing to avoid potential overdiagnosis and mismanagement. Enhancements in the app’s specificity could further support its utility in rapid and accessible malaria diagnosis for people with SCD, aiding in timely management and treatment.

Malaria and sickle cell disease (SCD) are co-located in tropic regions globally. This can bring about interactions in the diagnosis, treatment and management of both diseases. Early detection of malaria parasites with accurate diagnostic tests can prevent severe crises and death in people living with SCD. The National Library of Medicine (NLM) malaria screener app is a new smart phone-based tool that is affordable and available for use in low resource areas and can be downloaded from the app store. We evaluated its performance among SCD patients at Korle Bu Teaching Hospital in Ghana. Our study compared results from the NLM app with other diagnostic tests, specifically, rapid diagnostic tests (RDT), microscopy, and Polymerase Chain Reaction (PCR), using PCR as the reference standard. The NLM app’s sensitivity was comparable to RDT and microscopy, however, its specificity was lower than the other methods. While the app identified the highest number of positive malaria cases (36.2%), its lower specificity suggests a need for confirmatory testing to prevent overdiagnosis. Our findings highlight the potential of digital malaria diagnostic tools for rapid screening in vulnerable populations such as people with SCD, with necessary refinements to improve accuracy.