Big data analysis of electronic hospital records: inpatient trajectories and pharmacological exposures associated with mortality in older adults.

Admissions to National Health Service (NHS) hospitals in England have increased by 28% over the last decade and nearly half of all adults admitted are >=65 years old. Some older adults age robustly but others develop frailty, a condition characterised by reduced ability to withstand stressors such as illness. In addition, approximately a third of adult inpatients have one or more chronic health conditions, and many patients are prescribed multiple long term medications, so called 'polypharmacy'. We aim to understand how older adults use emergency hospital services and journey through the hospital from admission to discharge. We will also explore factors, particularly related to prescription medications, associated with poor hospital outcomes such as inpatient death. The World Health Organisation declared 'Medication without harm' its 3rd global patient safety challenge in 2017 and a report commissioned by the Department of Health Policy Research Programme estimated medication errors cost the NHS £98.5 million per year. Whilst medication related harm is widely recognised, more information is needed about which drugs confer the highest risk in which patients to inform safer prescribing practices.

We will use data from 80 000 inpatient episodes of older adults (>/=65 years old) admitted as an emergency to one tertiary NHS hospital (Addenbrooke's Hospital, Cambridge) over four years. Data is available for large scale retrospective analysis after an electronic patient record system was introduced in 2014. Information describing all aspects of admission from patient characteristics such as age group to information pertaining to bedside observations, prescription medications and blood tests are available. These data will have many repeated measurements over the admission duration, for example blood pressure measurements taken several times each day, leading to a very large and complex dataset. Therefore, anonymised patient records will be transferred to the European Bioinformatics Institute (EBI; Wellcome Genome Campus, Hinxton, Cambridge). EBI is a leading research institution focused on developing cutting-edge technologies to process and manage 'big' data.

We will employ machine learning (ML), a type of artificial intelligence capable of visualising patterns within complex data, to explore the thousands of patient examples in our dataset. We will firstly define how many different types of hospital admission describe the majority of admissions in older adults and characterise these inpatient trajectories. For example, admission episodes may be characterised by their length (short versus prolonged) or hospital operational factors such as number of ward moves. Secondly, we will use ML to study how different prescribed medications, or combinations of medications, represent a pattern that is consistently associated with inpatient death. We can use known associations, such as the use of blood thinning medications and higher likelihood of death from bleeding, to educate the ML process. ML can then identify other prescribing patterns associated with inpatient death and explore whether certain patient characteristics or types of admission make patients more vulnerable. This will build a comprehensive picture of patient, treatment and hospital factors that impact on the eventual hospital outcome. Inpatient death is our primary outcome but other outcomes such as new admission to a care home following discharge can be considered. Finally, ML can simulate how the hospital outcome might change if a hypothetical alternative treatment plan was employed. For example, medications can be substituted with an alternative treatment to see how this would change the likelihood of death occurring.

This research will describe use of acute hospital services by older adults and identify potentially inappropriate medications for further study. The Northeast-Newcastle & North Tyneside research ethics service committee approved the study.

Increasing numbers of older adults require hospital admission. Some older adults age well but others develop frailty, characterised by reduced ability to withstand stressors, and many experience co-morbidity and polypharmacy. We aim to understand how older adults use emergency hospital services by characterising the different inpatient trajectories that describe the majority of admissions. We will also explore if prescribed medications are associated with inpatient mortality to identify potentially inappropriate medications (PIMs).
Data from 80 000 inpatient episodes in older adults (>/=65 years old) admitted as an emergency to Addenbrooke's Hospital (Cambridge) over four years are available for large scale retrospective analysis after the introduction of an electronic patient record. Information describing all aspects of admission from patient characteristics to bedside observations, prescribed medications and laboratory tests are available. These data will have many repeated measurements resulting in a large, complex longitudinal dataset and physicians at Addenbrooke's have collaborated with the European Bioinformatics Institute (Wellcome Genome Campus, Hinxton, Cambridge) to combine clinical and technical expertise.
After anonymization, machine learning (ML) will be used to define the different types of inpatient trajectory. For example, admission episodes may be characterised by their length of stay or operational factors, e.g., number of ward moves. Secondly, ML will model risk factors associated with inpatient mortality with the aim of identifying PIMs and evaluating interactions between PIMs and patient factors or the type of admission in this heterogenous group. Other outcomes such as new institutionalisation will be considered and we will use ML to simulate how the patient outcome might change if a hypothetical alternative treatment plan had been employed.
The Northeast-Newcastle & North Tyneside research ethics service committee approved the study.

We will use electronic hospital data to define the inpatient trajectories that describe the majority of emergency admissions in older adults presenting to a large hospital and identify factors, particularly prescribed medications, associated with negative hospital outcomes. This information will interest frontline National Health Service (NHS) staff, NHS leaders, commissioners and policy makers. For example, the Cambridgeshire and Peterborough Sustainability and Transformation Partnership (STP) has stated five key priorities required to deliver an NHS 'fit for the future'. These include 'Providing safe and effective hospital care when it is needed, including responsive urgent and expert emergency care...' and 'Using technology to modernise health'. Our study will demonstrate the value of technology and, through utilisation of electronic hospital records, will contribute knowledge relevant to the provision of effective emergency care. Current hospital services have evolved from systems designed to diagnose and treat patients presenting with single conditions. Increasing numbers of older adults now present with two or more long term health conditions, polyphamacy and/ or frailty. Characterising the inpatient journeys of this complex patient group will provide insights into how they use emergency hospital care. This will highlight any inefficiencies of current services and inform decisions relating to the development and commissioning of future urgent care.
This study will also generate new hypotheses regarding potentially inappropriate medications (PIMs). PIMs are medications more likely to be associated with harm than clinical benefit and The National Medicines Safety Programme, part of NHS Improvement, has highlighted the need for more information about high risk drugs and vulnerable patient groups. This project will contribute knowledge to both of these domains and will highlight areas for future research. This information will also be of interest to the pharmaceutical industry and will add to the evidence informing safe prescribing and industry led research into medicines safety.
With respect to academia this project will develop the methodology and governance structure for extraction and analysis at scale of electronic inpatient data, collected during routine clinical care. This is a new data resource and this study will define the ethical considerations and processes to address them, such as anonymization protocols and secure data transfer from the NHS to research institutions. This study will also deliver important contributions to machine learning (ML), developing ML methods to analyse data collected at multiple time points and building on current methods which have used healthcare data collected only once. Finally, this study will add to the evidence base describing how routinely collected clinical data can be used to predict health outcomes and it will generate hypotheses regarding care pathways in older adults and PIMs, that can be tested by other service evaluations and research studies.
The impact of this study will be realised through focus groups with patients and the public and direct liaison with the STP, local hospital and clinical commissioning group managers. Study findings will be presented and published in relevant scientific meetings and journals and disseminated through research networks. This activity will occur over the three years of the grant and will continue to inform future research for years after its conclusion.
This proposal will benefit academia by providing a governance structure and developing tools that enable secure data sharing at scale, whilst protecting individual privacy, and will provide methodologies for data analysis applicable across the NHS. It will deliver insights into the use of emergency hospital services by older patients and our understanding of PIMs, an important aspect of patient safety prioritised by NHS Improvement, important to patients and of value to Pharma.