LPA Customer Applications

Arezzo Clinical Decision Support System

In 1999 Imperial Cancer Research Technology and Dr Alan Montgomery provided seed funding to InferMed Ltd to commercialize Arezzo/PROforma. Work leading to the introduction of PROforma started in the late 1980s with funding from European agencies. PROforma was also supported by Cancer Research UK with the purpose of building decision support and intelligent agents to improve cancer care.

 

PROforma is a first-order logic formalism extended to support decision making and plan execution. It incorporates non-classical logics (e.g., modal logic, temporal logic, deontic logic), LA, logic of argument and LOT (logic of obligation and time) to support decision making and action control.

​

PROforma comprises a formal specification language, a knowledge representation language and a suite of authoring tools and execution software for building applications.

​

PROforma had been developed by the late John Fox when he was at ICRF using LPA Prolog. Over the next 16 years InferMed implemented many solutions using their Arezzo implementation of PROforma. These were used in public health, clinical research, primary and secondary care and included:

• ORAMA (Optimal Renal Anaemia Management Assessment)

• Retrogram (HIV treatment) developed for Roche

• ARNO (for cancer pain control) implemented by Dr Robert Dunlop

• Support for nurses working in remote areas (for Queensland Health, Australia)

• Triage support for nurses handling 111 telephone calls

Several Arezzo apps were consulted millions of times by both care professionals and the public.

MACRO was a web-based clinical trial management system which used PROforma to ensure protocol-compliant collection of clinical trial data. Roche chose InferMed to implement MACRO at scale. For 10 years Roche used MACRO in major clinical trials worldwide.

​

NHS Direct’s symptom checkers aka self-assessment tests (SATS) ran for more than 5 years with zero unplanned outages. The service handled 10.7 million consultations in the first full year of operation, including sharp spikes of calls when flu scares were reported on radio. In that full year NHSD reported an annual saving of £57M to the NHS with the elimination of 1.5 million unnecessary GP appointments, 0.7 million A&E attendances/999 calls, and 0.6 million other face-to-face GP and A&E appointments.

​

Best Practice Advocacy Centre New Zealand 

In use since 2005, and now with over 6 million uses by hundreds of GPs, BPAC provides a wide range of decision support modules for GPs in New Zealand. These were developed by InferMed’s client Murray Tilyard and co-workers at BPAC.

InferMed grew to employ more than 30 people and in 2015 was acquired by Elsevier. In 2022, Ennov acquired MACRO from Elsevier.
In 2021, Elsevier described how "Mobile AI helps health workers deliver prenatal care in rural India" with the aim is to improve the knowledge of frontline non-physician health workers with a mobile, adapted version of the Arezzo Clinical Decision Support System, with a specific focus on prenatal care and care of newborns and children under 5 years of age.
You can read how Elsevier Health’s Artificial Intelligence Catalyst, helps healthcare professionals across India give prenatal care to women. This article describes how between October 2020 and April 2021, 50 healthcare workers were trained in how to use the technology, and more than 4,300 patients were screened. Ultimately, 471 high-risk pregnancies were identified, with 164 patients referred urgently for further treatment. The technology was first developed by Dr Robert Dunlop and Dr Angela Dunlop, who have spent more than 20 years perfecting the AI system — Arezzo — that sits at the heart of the HAIC project. This declarative AI system is able to mirror the way medical experts think by pulling together many different pieces of information to create treatment recommendations tailored for a single patient.