An interventional study of VectorCam and Routine Entomological Surveillance in Malaria, Surveillance and Entomology, sponsored by Johns Hopkins University. Completed at 1 site in Uganda. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-11-02.
Sponsored by Johns Hopkins University · Not applicable, Interventional, and Health services research
Mosquitoes spread diseases such as malaria, but tracking mosquito populations is often slow and depends on a small number of highly trained specialists. VectorCam is a smartphone-based tool that uses artificial intelligence (AI) to help identify mosquitoes from photographs and automatically report surveillance information. In this study, community health workers in Uganda used VectorCam during routine mosquito collection activities, while a comparison group followed standard methods that required mosquito identification by trained specialists using microscopes. The study evaluated how accurately mosquitoes could be identified, how quickly information could be reported, how complete the collected data were, and how easy the system was to use. The goal was to determine whether AI-enabled technology could help communities collect and share mosquito surveillance information more quickly and efficiently, while maintaining data quality under real-world conditions.
This randomized controlled trial evaluated whether VectorCam, a smartphone-based artificial intelligence (AI) tool for mosquito surveillance, can support a task-shifting model in Uganda. In this model, routine entomological surveillance moves from trained Vector Control Officers (VCOs) to community-based Village Health Teams (VHTs) who have no formal entomology training. VectorCam lets users photograph mosquito specimens, classify them automatically with AI, and report surveillance data electronically.
The study compared surveillance by VHTs using VectorCam (the task-shifting model) with standard surveillance by VCOs. The primary objective was to find out whether VHTs, supported by VectorCam, could perform routine mosquito surveillance with accuracy, completeness, timeliness, cost-effectiveness, and feasibility comparable to standard VCO-led surveillance under real-world field conditions.
VectorCam is a smartphone-based mosquito surveillance platform that combines specimen imaging, artificial intelligence (AI)-based classification, and digital reporting tools. The system was developed to support routine entomological surveillance by enabling community-based personnel to identify and report mosquito specimens using a smartphone.
This randomized controlled trial was conducted in Adjumani and Mayuge districts in Uganda. Village Health Teams (VHTs) in the intervention arm used VectorCam during routine mosquito surveillance activities, while the control arm followed standard surveillance procedures conducted by trained Vector Control Officers (VCOs).
Mosquito specimens collected through routine surveillance methods were classified using VectorCam and compared with conventional morphological identification using a microscope and molecular verification methods. The study evaluated the accuracy of mosquito identification, completeness of surveillance data, timeliness of reporting, and the cost associated with the tool.
The findings will help determine whether AI-enabled digital tools can support task-shifting of mosquito surveillance to community health workers and strengthen entomological surveillance systems in malaria-endemic settings.
1,184 studies on the registry are indexed under Malaria; 79 are open to participants now.
This study's enrollment of 48 is below the median of 252 across 937 interventional studies indexed under Malaria.
Browse Malaria studies →Johns Hopkins University is the lead sponsor of 1,815 studies on the registry; 315 are open to participants now.
Of its 208 completed or terminated interventional studies of FDA-regulated products, 144 (69%) have results posted.
Counted across the registry records on this site, refreshed daily.
Inclusion Criteria for VHTs, VCOs, and Household Owners:
Households' owners additionally:
Exclusion Criteria for VHTs and VCOs:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Participants assigned to the intervention arm conducted routine mosquito surveillance using VectorCam, an artificial intelligence (AI)-enabled smartphone platform. Village Health Teams (VHTs) collected mosquito specimens, captured specimen images using the VectorCam device, received automated mosquito classifications, and electronically submitted surveillance data through the mobile application. Mosquito specimens were retained for subsequent morphological and molecular validation by the district entomologist for validation purposes.
Device: VectorCam
Participants assigned to the control arm conducted routine mosquito surveillance according to standard Ministry of Health procedures. Village Health Teams (VHTs) collected mosquito specimens and submitted them to district Vector Control Officers (VCOs) for species identification using paper-based and microscopy methods. Surveillance data were recorded in paper and later on submitted through the existing Ministry of Health reporting systems (DHIS2)
Other: Routine Entomological Surveillance
VectorCam is an artificial intelligence (AI)-enabled mosquito surveillance platform designed to support community-based entomological surveillance through task shifting. The system enables trained Village Health Teams (VHTs) to image mosquito specimens using a smartphone-based device and receive automated classifications without internet connectivity. During this study, the AI model classified specimens into seven categories: Anopheles gambiae s.l., Anopheles funestus s.l., Anopheles Other, Culex spp., Mansonia spp., Aedes spp., and Non-Mosquito specimens. The platform incorporates digital reporting workflows aligned with Uganda Ministry of Health surveillance requirements, allowing mosquito surveillance data to be collected and electronically reported. The intended use of VectorCam is to expand access to routine mosquito surveillance by enabling community health workers to perform species identification and reporting activities traditionally conducted by trained entomologists.
The control arm followed routine Ministry of Health mosquito surveillance procedures. Village Health Teams (VHTs) collected mosquito specimens using standard collection methods, including pyrethrum spray catches and Centers for Disease Control (CDC) light traps, and recorded household-level surveillance data on paper forms. Specimens were packaged, labeled, and transported to district laboratories, where trained Vector Control Officers (VCOs) conducted morphological identification under light microscopy according to national standard operating procedures. Mosquitoes were classified by species, sex, and abdominal status, and results were manually recorded on surveillance forms. Surveillance data were subsequently entered into DHIS2 platform by district biostatisticians, following existing reporting workflows used within Uganda's national malaria surveillance program.
Mosquito Species Identification Accuracy
Accuracy of mosquito species classification by VectorCam compared to molecular or sequencing results. For each taxonomic class, sensitivity, specificity, positive predictive value (PPV), and overall accuracy were calculated. A weighted F1 score accounting for class imbalance across taxa was additionally reported to provide an aggregate performance measure across species groups.
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Throughput Efficiency (Per-specimen identification time )
Operational throughput was defined as the time required to progress from identification of one mosquito specimen to identification of the subsequent specimen under routine operating conditions.
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Completeness (proportion of required surveillance reporting fields successfully captured and available)
Data completeness was defined as the proportion of required surveillance reporting fields that were successfully captured and available for review within each arm's reporting system. For each routine surveillance data element captured on the paper-based VHT forms and subsequently entered into DHIS2, the corresponding field, if any, collected by the VectorCam application was identified, and vice versa. Data elements that existed in only one system, or that could not be mapped to an equivalent field in the other, were excluded from the completeness comparison; only fields common to both arms were retained.
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Timeliness (delay between field specimen collection and availability of surveillance data)
Timeliness was defined as the elapsed time between surveillance activity and availability of the resulting record in the arm-specific digital reporting system. In the control arm, reporting delay was calculated as the number of days between the field collection date recorded by the VHT and the date on which the corresponding surveillance record became available in Uganda's DHIS2 system. In the study arm, reporting delay was calculated from initiation of the VectorCam imaging session to successful upload of the corresponding record to the secure VectorCam cloud server.
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Classification performance accuracy for mosquito sex
In the VectorCam (study) arm, classification of sex will be compared against morphological identification by trained VCOs under light microscopy for a subset of specimens. Performance will be measured as accuracy: the proportion of specimens correctly classified. For sex, accuracy will be reported overall and separately for females and males.
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Classification performance accuracy for mosquito abdominal status
In the VectorCam (study) arm, classification of abdominal status will be compared against morphological identification by trained VCOs under light microscopy for a subset of specimens. Performance will be measured as accuracy: the proportion of specimens correctly classified.. Abdominal status, will be reported overall and for each category (unfed, fed, and gravid).
Time frame: From the beginning of the steady stage (6 months) up to 12 months
Summative Usability Assessment (SUS Scale)
The SUS questionnaire was administered to all participating VHTs assigned to the intervention arm. Responses were scored according to standard SUS methodology, generating a total usability score ranging from 0 to 100. Results were analyzed descriptively to characterize perceived usability and acceptability. A System Usability Scale (SUS) score is considered good when it is above 68, with scores above 80.3 considered excellent or top-tier.
Time frame: 12 months
Plan to share: No — Individual participant data (IPD) will not be shared to protect participant confidentiality and in accordance with the data governance agreements established with the Uganda Ministry of Health and the study's ethical approvals. De-identified aggregate entomological surveillance data, study protocols, and AI model architectures may be shared upon reasonable request to enable external validation and reproduction of the study findings using independent datasets. Data sharing will be subject to applicable institutional policies, ethical approvals, and data use agreements.
Ran from Sep 2023 to primary completion in Aug 2025, 23 months.
Of 95 non-industry interventional studies with no phase under Malaria, half reached primary completion within 23 months of starting (the median), counting those still running; a quarter within 11 and three quarters within 35. This study's 23 months is close to that.
Counting every sponsor, half of 101 studies reached it within 23 months; a quarter within 8 and three quarters within 33.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is completed, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.