Chemotherapy is the treatment of disease using chemical substances, commonly used to treat cancer. Chemotherapy is often cytotoxic and two common risks relate to kidney and liver damage. Affected patients may require delays or changes to treatment and even treatment suspension. Whilst only <10% of patients will encounter kidney and/or liver damage, current best practice requires monitoring for all patients with regular blood testing. There is currently no way to stratify risk in individual patients. **The vision for this project is to accurately predict the risk of kidney and liver damage in patients receiving chemotherapy**. The result of this prediction will mean low risk patients can be saved unnecessary trips to hospital for blood tests and monitoring whilst high risk patients can receive more appropriate management. To date, computer scientists at Durham University, working closely with pharmacists at University College London Hospital (UCLH) have developed a machine learning algorithm to accurately predict liver and kidney function. Results have been shared at a number of key conferences and stakeholder events and there is strong clinical interest in utilising this algorithm in clinical practice. **The main area of focus for this project will be a prospective diagnostic accuracy study**. This will produce a commercial proof-of-concept (POC) software application that will allow the validated algorithm, produced by Durham University academics, to be used in live clinical practice. Key objectives will include: \* Develop POC software to allow algorithm to be tested in a live clinical setting \* Rapid iterative development of POC to enable commercial launch \* Data collection to validation algorithm \* Identification of third-party software interface opportunities (particularly chemotherapy e-prescribing systems) \* Development of commercialisation plan Currently ~375k patients are diagnosed with cancer every year in the UK, with ~28% of these expected to receive chemotherapy for their primary disease[\[1\]][0]. With similar rates of cancer incidence across the Western world, this innovation could personalise care for millions globally. [\[1\]][1] https://www.cancerresearchuk.org/health-professional/cancer-statistics/incidence [0]: #_ftn1 [1]: #_ftnref1

To enhance the management of outpatient follow-up by improved identification and treatment of radiotherapy side effects using machine learning and artificial intelligence.

"Cievert is a digital health SME specialising in designing and implementing innovative software in the health sector. Established in 2011 by a former NHS radiographer, Cievert software can now be found in 20% of all NHS cancer centres. In England alone, there are 100million NHS outpatient appointments every year\*. These cost an estimated £10billion, require significant clinical input and infrastructure, can often be a source of anxiety for patients, and a significant proportion (approx. 20%) of these appointments are not attended. With a growing elderly population and more people living with a long-term condition, the demand for outpatient appointments is predicted to grow. This growth will add to the demand of already-stretched, finite clinical resources. A large number of outpatient appointments are used for routine follow-up. Clinicians would rather see patients when they need to be seen, not on the arbitrary time-based schedule currently used. Assessing patients remotely using Artificial Intelligence (AI) would free up clinicians' time and allow them to concentrate on patients that really do require face-to-face follow-up. We aim to automate out-patient follow-up using AI, making it more efficient and effective. This project will focus on cancer outpatient appointments, specifically patients receiving radiotherapy, of which there are approximately 140,000 per year in the UK\*\*. We will develop software to replace the routine clinical follow-up appointment with a view to better identifying those patients in need of clinical intervention. This will result in patients with a clinical need being assessed more quickly and enable them to be seen by an appropriate clinical team member, sooner. This will free up precious clinical staff and resources, reduce costs, reduce waiting times, and radically change how routine outpatient follow-up care is delivered. Whilst AI is rapidly developing in the field of diagnostics, there is little work being done in using this technology during a course of treatment, such as radiotherapy, post-diagnosis and follow-up. This project will result in a commercially ready solution that will put an end to time-based routine follow-up and will be replaced by a proactive system based on clinical need. \*Source: NHS Digital Website, 'Hospital outpatients: Appointments top 100 million for first time in 2013-14' (http://www.hscic.gov.uk/article/6068/Hospital-outpatients-Appointments-top-100-million-for-first-time-in-2013-14). 26th Feb 2015\. \*\*Source: Cancer Research UK website (http://www.cancerresearchuk.org/health-professional/cancer-statistics-for-the-uk)"