BlackThorn

A hospital faces complexities in accurately predicting medical outcomes, such as the expected hospital length of stay, and deciphering the effects of various medical indicators on these processes.We developed machine learning models for predicting various medical outcomes, integrating feature engineering, model selection, and interpretability techniques for enhanced decision-making in healthcare settings.

The client needed a scalable genome analytics tool to investigate the role of genetic mutations in disease vulnerability. Blackthorn AI developed a fault-tolerant large-scale genome analysis platform capable of handling hundreds of terabytes of raw sequencing data.

A radiologist’s diagnosis is subjective and often inaccurate, leading to up to 30% errors. Patients suffer repeated visits to hospitals, anxiety about diagnosis delays, and false radiologist conclusions.Our team designed and developed an AI-powered medical imaging analysis platform that, when paired with a radiologist, increased breast cancer detection accuracy by 20-30% in clinical trials compared to a radiologist alone.

Systematic reviews are essential for health technology assessments, real-world evidence (RWE) generation, and regulatory submissions — but traditional workflows are slow, inconsistent, and impossible to scale.We rebuilt the Screener tool from scratch using a scalable, cloud-native architecture and modern frontend/backend stack.

The system combined machine learning–based affinity prediction, large-scale virtual screening, and docking simulations (DiffDock) with active learning loops. This allowed scalable identification and prioritization of high-potential ligands while drastically reducing the need for costly wet-lab experiments.

Integrated Care Solutions (ICS) – Dubai-based digital health company focused on enhancing patient outcomes and care coordination.We developed and deployed an AI-based readmission prediction service integrated into ICS’s clinical platform. The system uses 6 years of patient history and real-time episode data to assign readmission risk scores at 3 stages of the care journey.

The goal was to allow users to measure heart rate and oxygen saturation without wearable devices or contact sensors. We developed a cross-platform MVP that uses computer vision and photoplethysmography (rPPG) to extract physiological signals from facial video.

HTG is accelerating precision medicine from diagnosis to treatment by harnessing the power of transcriptome-wide profiling to drive translational research. HTG is accelerating precision medicine from diagnosis to treatment by harnessing the power of transcriptome-wide profiling to drive translational research

We delivered a centralized multi-omics data warehouse, automated complex data processing pipelines, and developed an intuitive web portal for researchers and clients. The system harmonized diverse datasets, eliminated manual processing, and enabled real-time data interaction through dashboards and visualizations.

Closed-loop IOT system for skin care treatment using AI tools for skin diagnostics and serum recommendation.Classification and segmentation ML models were trained on hundreds of thousands of manually annotated dermatology images; AI service recognizing skin condition and severity using patient images overperformed competing solutions on the market by 18% of accuracy.