Joseph Nawar APPLIED AI · MACHINE LEARNING
All selected work
PROJECT 03 / MULTIMODAL MACHINE LEARNING RESEARCH

RuralStroke Triage

A multimodal smartphone screening-support research prototype that combines independent proxy signals using interpretable, missing-modality-aware late fusion.

Explore the case study
Role
Research author and system engineer
Paper
Accepted and presented · MIUCC 2026
Stack
Python · PyTorch · Scikit-learn · OpenCV
Original visual, speech, metadata, and symptom branches in the research screening system.

Original project artwork illustrating the research prototype’s independent evidence branches and late-fusion concept.

0.9809Visual ROC-AUC · held-out proxy image test
0.9426Speech ROC-AUC · speaker-disjoint proxy task
276/276Deterministic fusion audit checks passed
01 / RESEARCH QUESTION

What if the evidence is incomplete?

Prehospital stroke screening in resource-constrained settings involves limited connectivity, noisy recordings, and missing information. A system cannot assume all evidence sources are available or that model outputs from unrelated datasets can be treated as a calibrated clinical probability.

RuralStroke-Triage is a non-diagnostic research prototype that integrates smartphone-compatible visual, speech, patient-context, and FAST/BE-FAST symptom evidence through interpretable late fusion and deterministic escalation logic.

The goal is auditable screening support under uncertainty—not autonomous diagnosis or clinically validated stroke prediction.
02 / METHODOLOGY

Independent evidence branches, interpretable fusion.

The accepted manuscript describes a frozen MobileNetV2 image branch for facial asymmetry, a Random Forest over engineered dysarthric-speech features, a logistic-regression metadata model for contextual risk, and a deterministic symptom branch.

Independent branch scores are combined through manually specified late-fusion weights. Missing modalities are omitted and the remaining weights renormalized; acute FAST findings can trigger deterministic escalation. Outputs remain non-clinical evidence scores rather than jointly calibrated diagnosis probabilities.

Original RuralStroke artwork showing independent visual, speech, context, and late-fusion branches
Original project artwork illustrating the research prototype’s four proxy evidence branches. It is not a reproduction of a manuscript figure.
03 / REPORTED RESULTS

Proxy-task performance, with explicit limits.

The reported held-out ROC-AUC results were 0.9809 for the visual branch, 0.9426 for the speech branch, and 0.8338 for the metadata branch. The work additionally passed 33/33 symptom scenarios and 276/276 deterministic fusion checks.

These results are not end-to-end clinical accuracy. The branches use independent proxy datasets with different labels, participants, and protocols. In particular, TORGO dysarthria is not an acute-stroke-specific label.

Safety and scope: The paper explicitly states that no synchronized, patient-level multimodal cohort with confirmed stroke outcomes was available. The system is a decision-support research prototype. External calibration, robustness testing, and prospective clinical validation would be needed before any clinical use.
04 / THE TRADE-OFFS

Designing for what the data can support.

  • Late fusion over learned joint fusion: linked multimodal patient data was unavailable, so jointly training fusion would have introduced unsupported relationships.
  • Transparent escalation: deterministic FAST rules make high-priority evidence auditable rather than leaving it entirely to a learned threshold.
  • Separate branch metrics: performance is reported for each modality rather than misrepresented as end-to-end diagnostic accuracy.

The research was authored and presented at MIUCC 2026. Its status is: Accepted and presented — IEEE Xplore publication forthcoming.

Next case study
OpsFlow AI ↗
View publications ↑
04 / LET'S CONNECT

Let’s build AI
that matters.

Hiring for applied AI or machine-learning engineering? I’m interested in remote-first teams, research collaborations, and carefully scoped engineering work. My inbox is open.

joe.hany2005@gmail.com

Elsewhere on the internet

Based in Cairo, Egypt.
Interested in remote-first opportunities.