Comparison of visual and automated Deki Reader interpretation of malaria rapid diagnostic tests in rural Tanzanian military health facilities
Bibliographic record
Abstract
BACKGROUND: Although microscopy is a standard diagnostic tool for malaria and the gold standard, it is infrequently used because of unavailability of laboratory facilities and the absence of skilled readers in poor resource settings. Malaria rapid diagnostic tests (RDT) are currently used instead of or as an adjunct to microscopy. However, at very low parasitaemia (usually < 100 asexual parasites/µl), the test line on malaria rapid diagnostic tests can be faint and consequently hard to visualize and this may potentially affect the interpretation of the test results. Fio Corporation (Canada), developed an automated RDT reader named Deki Reader™ for automatic analysis and interpretation of rapid diagnostic tests. This study aimed to compare visual assessment and automated Deki Reader evaluations to interpret malaria rapid diagnostic tests against microscopy. Unlike in the previous studies where expert laboratory technicians interpreted the test results visually and operated the device, in this study low cadre health care workers who have not attended any formal professional training in laboratory sciences were employed. METHODS: Finger prick blood from 1293 outpatients with fever was tested for malaria using RDT and Giemsa-stained microscopy for thick and thin blood smears. Blood samples for RDTs were processed according to manufacturers' instructions automated in the Deki Reader. Results of malaria diagnoses were compared between visual and the automated devise reading of RDT and microscopy. RESULTS: The sensitivity of malaria rapid diagnostic test results interpreted by the Deki Reader was 94.1% and that of visual interpretation was 93.9%. The specificity of malaria rapid diagnostic test results was 71.8% and that of human interpretation was 72.0%. The positive predictive value of malaria RDT results by the Deki Reader and visual interpretation was 75.8 and 75.4%, respectively, while the negative predictive values were 92.8 and 92.4%, respectively. The accuracy of RDT as interpreted by DR and visually was 82.6 and 82.1%, respectively. CONCLUSION: There was no significant difference in performance of RDTs interpreted by either automated DR or visually by unskilled health workers. However, despite the similarities in performance parameters, the device has proven useful because it provides stepwise guidance on processing RDT, data transfer and reporting.
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 | 0.001 | 0.002 |
| 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".