Clinical performance of an automated reader in interpreting malaria rapid diagnostic tests in Tanzania
Bibliographic record
Abstract
BACKGROUND: Parasitological confirmation of malaria is now recommended in all febrile patients by the World Health Organization (WHO) to reduce inappropriate use of anti-malarial drugs. Widespread implementation of rapid diagnostic tests (RDTs) is regarded as an effective strategy to achieve this goal. However, the quality of diagnosis provided by RDTs in remote rural dispensaries and health centres is not ideal. Feasible RDT quality control programmes in these settings are challenging. Collection of information regarding diagnostic events is also very deficient in low-resource countries. METHODS: A prospective cohort of consecutive patients aged more than one year from both genders, seeking routine care for febrile episodes at dispensaries located in the Bagamoyo district of Tanzania, were enrolled into the study after signing an informed consent form. Blood samples were taken for thick blood smear (TBS) microscopic examination and malaria RDT (SD Bioline Malaria Antigen Pf/Pan™ (SD RDT)). RDT results were interpreted by both visual interpretation and Deki Reader™ device. Results of visual interpretation were used for case management purposes. Microscopy was considered the "gold standard test" to assess the sensitivity and specificity of the Deki Reader interpretation and to compare it to visual interpretation. RESULTS: In total, 1,346 febrile subjects were included in the final analysis. The SD RDT, when used in conjunction with the Deki Reader and upon visual interpretation, had sensitivities of 95.3% (95% CI, 90.6-97.7) and 94.7% (95% CI, 89.8-97.3) respectively, and specificities of 94.6% (95% CI, 93.5-96.1) and 95.6% (95% CI, 94.2-96.6), respectively to gold standard. There was a high percentage of overall agreement between the two methods of interpretation. CONCLUSION: The sensitivity and specificity of the Deki Reader in interpretation of SD RDTs were comparable to previous reports and showed high agreement to visual interpretation (>98%). The results of the study reflect the situation in real practice and show good performance characteristics of Deki Reader on interpreting malaria RDTs in the hands of local laboratory technicians. They also suggest that a system like this could provide great benefits to the health care system. Further studies to look at ease of use by community health workers, and cost benefit of the system are warranted.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".