Products
Four technologies we own.
Each began inside Scriptics as a research programme with no customer attached. Each is now a system in production. They sit alongside the services work rather than instead of it, and the same engineers built both.
Life sciences
Detection and prediction.
Three problems in clinical detection: resistance, risk and imaging. Different data, different workflows, different regulatory paths.
AMR responsible-protein detection
Identifies the protein responsible for antimicrobial resistance from DNA sequencing samples, including where that protein is absent from the reference catalogue.
Read more →02 PredictionEarly cancer risk prediction
Cervical and breast cancer risk, identified up to three years ahead of clinical presentation. A risk model rather than a diagnostic.
Read more →03 ImagingRadiology AI
Cancer detection from diagnostic imaging, at 96.4% accuracy against radiologist-adjudicated ground truth.
Read more →Dental
Treatment planning.
Planning is where clear-aligner turnaround goes, and where the compute bill goes with it.
Aligner treatment planning
A manufacturable clear-aligner plan in a single day against a three to four week industry norm, on general-purpose CPU hardware, with the clinician inside the loop.
Read more →PracticeThe dental practice
Where the turnaround actually goes, what the compute decision changes commercially, and how to evaluate it on your own cases.
Read more →What we publish
Capability here, evidence under agreement.
All four have patent applications pending. Study design, cohort composition, comparator method and model architecture are the material an examiner cares about, and publishing them before the applications resolve is prior art against our own filings.
Under agreement we share the validation design, the performance data including failure modes by subgroup, and the regulatory position in your market. The fastest evaluation is usually your own data rather than our summary of ours.
Evaluate one of them.
Laboratories, screening programmes and dental groups can run these systems against their own data under agreement.