Archive | Safety Informatics RSS feed for this section

Safety Informatics lead elected to American College of Medical Informatics

16 Nov

ACMI Award NP_cropped

Safety Informatics lead Niels Peek was recently elected to membership in the American College of Medical Informatics (ACMI). This is a college of elected Fellows who have made significant and sustained contributions to the field of medical informatics. It is the central body for a community of scholars and practitioners who are committed to advancing the informatics field. The membership award was handed out during the annual symposium of the American Medical Informatics Association in San Francisco, 3-7 November 2018.

If a computer gives you a diagnosis, should it also give you an explanation?

15 Nov
Citizens Jury_cropped

Jurors from previous Citizens’ Juries

by Malcolm Oswald

Artificial intelligence (AI) plays an increasing role in our daily lives. Computers are being trained how to do many things, including making medical diagnoses. For example, AI can diagnose skin cancer from skin images as reliably as dermatologists, and this clever software is only going to get better. But how do we know whether a diagnosis we get is accurate? If we are given it by a human doctor, we can ask for an explanation. However, the most advanced AI systems are very complex and do not just act according to pre-defined rules, but continue to “learn”, and it may not be possible to explain to a patient how the computer reached its diagnosis.

If you were given a diagnosis by a computer, and were given the choice, would you always prefer to be given an explanation of how the computer reached its diagnosis even if that meant the computer’s diagnosis was likely to be a little less accurate?

That is one question being put to two “citizens’ juries” being commissioned by the NIHR Greater Manchester Patient Safety Translational Research Centre (Greater Manchester PSTRC) in early 2019. Citizens Juries c.i.c. will recruit 18 people from around Manchester – chosen to represent a cross-section of the public – to come together for five days to hear expert evidence and tackle difficult questions concerning how AI should be used within healthcare. The process will then be repeated with 18 different people from around Coventry to see whether they reach the same conclusions.

The Greater Manchester PSTRC is collaborating on this project with the Information Commissioner’s Office which has the challenging task of regulating the use of AI. The results of the juries will feed directly into national guidance that the Information Commissioner’s Office has to produce on citizens’ rights to an explanation when decisions that affect people are made using AI.

For more information about citizens’ juries, see the Citizens Juries c.i.c. website, or if you have a specific enquiry about this project, email Dr Malcolm Oswald or the principal investigator, Prof Niels Peek.

Using Artificial Intelligence to help primary care triage

5 Oct

Working on laptop, close up of business man

by Ben Brown

Researchers at The University of Manchester and Spectra Analytics are developing an Artificial Intelligence (AI) system to help support GP practices triage requests for appointments – the Patient Automated Triage and Clinical Hub Scheduling (PATCHS) system.

It’s often difficult to get an appointment with a GP, and it’s estimated that over a quarter of GP appointments could have been dealt with in an alternative way, for example by another clinician (such as a nurse) or through patient self-care. One solution may therefore be to allocate GP appointments to patients that really need them.

While receptionists at GP practices can direct patients to the most appropriate care provider, not all practices do this, and often patients are unwilling to disclose their problems to them. PATCHS plans to tackle this by providing an online tool that will efficiently direct patients to the right place, 24 hours a day. Patients will input their reasons for requesting a GP appointment, and PATCHS will analyse this request, taking into account the patient’s medical history, in addition to other factors such as the weather, to come to a triage decision. It is hoped the system could ultimately be integrated into practice websites and medical records, ensuring effective triage at the beginning of a patient’s care pathway.

The project is funded by Innovate UK and is currently in the development stage: PATCHS is currently learning from existing data about how patients are triaged when booking a GP appointment. However, the team are looking for volunteers – both patients and doctors – to participate in the project. If you’d like to know more please contact Dr Ben Brown on benjamin.brown@manchester.ac.uk.

Past PhD Fellows: Where are they now? Paolo Fraccaro

2 Aug

In this series, we catch up with past Greater Manchester PSTRC PhD Fellows to see what they are doing now and how their PhD projects affected patient safety. This edition, our past PhD Fellow is Paolo Fraccaro.

Paolo Fraccaro_cropped

What did you learn during your PhD?

Almost one and a half years after finishing my PhD, I cannot stress enough what a great (although painful at times) experience it has been. I have learned a lot from many different perspectives, including technical and interpersonal skills. Particularly, I have strengthened my skills in health informatics and data science, while learning to be autonomous and to interact with many different professionals with different backgrounds. I also had the opportunity to present my work at international conferences, and visit the USA for two months to work with colleagues overseas. I feel this contributed in broadening my horizons, making me a better researcher.

How has your PhD changed the patient safety landscape?

My PhD helped to show how using technology to contextualise information with technology is essential to improve patient safety. My studies ranged from showing how different presentations of laboratory results influence patient interpretation and actions, to developing and testing computer algorithms that can predict in advance specific outcomes (e.g. death and chronic kidney disease), taking into account the specific patient context (e.g. previous medical history). Such algorithms, if integrated in GPs computer programs, have the potential to support primary care doctors in identifying patients at risk quickly.

What you are doing now and where you see yourself going in your future career?

For the last year and a  half, I have worked as a postdoctoral Research Associate in a project called “The Wearable Clinic” led by Niels Peek in the Centre of Health Informatics at The University of Manchester. The aim of the project is to tailor monitoring and treatment of patients with chronic conditions, by using information from wearable devices (e.g. activity trackers or smartphones) as well as data reported by patients themselves. In September, I will start in a new role as a Data Scientist at IBM Research UK . Although I am sad to leave after five amazing years at The University of Manchester, I am really excited to begin this new adventure in industry!

Connected Health Cities and the Greater Manchester PSTRC

2 Aug

Connected Health Cities logo_cropped

by Niels Peek, Research Lead for Safety Informatics theme, NIHR Greater Manchester PSTRC

The Safety Informatics theme in the Greater Manchester PSTRC extends and translates the principles of ‘learning health systems’ to develop technologies and information behaviours that create safer care systems. It does this by enabling:

  1. continuous professional and organisational learning
  2. accelerated translation of evidence into practice
  3. system-wide patient safety that crosses sector boundaries.

In all these activities, the Safety Informatics theme builds heavily on experiences and achievements in Connected Health Cities (CHC), a programme of work across 4 city regions in North England that is funded by the Department of Health and Social Care and commissioned by the Northern Health Science Alliance (NHSA). This programme aims to optimise care pathways by employing analytical technologies to routinely collected, local health data. In each of the 4 regions several pathways have been selected to develop and test this use of technologies. In addition the programme has extensive workstreams on workforce development, industry partnerships, and public engagement.

In the Greater Manchester Connected Health City (GMCHC), the two main care pathways project focus on:

  1. antibiotic prescribing in primary care (lead: Tjeerd van Staa)
  2. triage, diagnosis, and acute treatment of strokes (lead: Adrian Parry-Jones).

In both pathways there is a trade-off between safety of individual patients and population health generally. This trade-off can only be accurately studied by linking data from across different healthcare sectors, such as primary and secondary care. For instance, ambulance paramedics are sometimes risk averse and tend to bring everyone who might have had a stroke to one of the three specialised acute stroke units in Greater Manchester – but these specialised units have therefore become overburdened. Similarly, our analyses of antibiotic prescribing data indicate that these prescriptions are often not guided by risk of severe infection (e.g. pneumonia) and thus unnecessarily drive antimicrobial resistance in the community. In both care pathways we are now implementing electronic decision support tools for care providers to address the issues.

Greater Manchester provides a unique environment for implementing learning health systems, because the devolution context allows to offset investments in primary care with savings in secondary care and vice versa. Therefore GMCHC works closely with regional partners such as Health Innovation Manchester and the GM Health and Social Care Partnership. Both organisations have embedded the CHC principles in their digital innovation and health intelligence strategies.

 

Coded fairy tales at Medical Informatics Europe conference

16 May

Sleeping Beauty_cropped

by Richard Williams, Software Engineer, NIHR Greater Manchester PSTRC

Niels Peek and Richard Williams from the NIHR Greater Manchester PSTRC’s Safety Informatics theme recently attended Medical Informatics Europe (MIE) in Gothenburg, Sweden. MIE is the leading European health informatics conference and saw delegates attending from all corners of the world. While there, Richard beat off stiff competition to win the prestigious Science Slam – a competition held at MIE where contestants have up to 8 minutes to present their work in a humorous and entertaining way.

Richard talked about clinical codes, which clinicians use as a short cut to describe medical concepts e.g. hypertension is represented by the code G2 and Type 2 diabetes by the code C10F. Richard highlighted the absurdity of some clinical codes such as “U102700 – Fall involving ice-skates, skis, roller-skates or skateboards, occurrence on farm”, the dreaded “TE63100 – Moray eel bite”, and that there are no fewer than 11 codes for falling off a cliff including “U10F200 – Fall from cliff, occurrence at school”.

Richard then translated fairy tales into clinical codes – care to guess the following?

1. Female baby (634..12), black magic (13y8.00), wiccan (13yD.00), puberty (ZV21100), accident caused by spinning machine (TG3y500), excessive sleep (1BX1.00), contact with plant thorns and spines and sharp leaves occurrence at other specified place (U12Ay00), concussion with more than 24 hours loss of consciousness and (S603.00)… manual resuscitation (8731.00) …return to pre-existing conscious level (S603.00 cont.), married (1332.00).

2. Newly wed (1332.12), infertility problem (1AZ2.11), specific food craving (E275800), unborn child subject to child protection plan (13Iv000), female baby (634..12), imprisonment (ZV62511), abnormalities of the hair (M242.00), fall from turret (TC25.00), accident caused by plant thorn (TG4y600), foreign body entering into or through eye or natural orifice occurrence at other specified place (U11Qy00), acquired blindness both eyes (F490900), length of time homeless (13D8.00), tearing eyes (1B87.14), patient cured (2129.00).

3. Female baby (634..12), pale colour (1674.00), mother dead (12K3.00), father remarried (13HJ.00), has stepmother (133D100), hunter’s syndrome (C375.12), ran away (13HW.00), mining engineers (058..12), dwarfism (C1z4.00), found dead (R213100), manual resuscitation (8731.00), found dead (R213100), manual resuscitation (8731.00), found dead (R213100), suspected food poisoning (1J8..00), manual resuscitation (8731.00), married (1332.00).

Answers on a postcard.

On a more serious note, the talk also highlighted that the current coding system used in UK general practice (Read Codes) is in the process of changing to SNOMED (an internationally recognised coding system). This is a major project with potential implications for the continuity of patient care if managed poorly, but also with large implications for researchers in the UK who have much experience of working with databases of Read Codes but little experience of working with SNOMED.

What does the future hold? “God only knows (R2yz.11)”.

University of Michigan shares informatics research

18 Apr

michigan medicine-logo_small

In February, researchers Zach Landis-Lewis and Dahee Lee from the University of Michigan, Ann Arbor (USA), visited the NIHR Greater Manchester PSTRC Safety Informatics team at the Health eResearch Centre (HeRC) and gave a seminar on feedback interventions. Zach is Assistant Professor of Learning Health Sciences at the University of Michigan Medical School. Currently he is working on developing a system to support automated tailoring of clinical performance feedback for healthcare professionals. He leads the DISPLAY (Design, Implementation, Systems, Performance, Learning, and Y they matter) lab. Dahee is a MSc student in Health Informatics at the University of Michigan.

Feedback interventions play a key role in the Greater Manchester PSTRC Safety informatics theme; examples are the Salford Medication Safety Dashboard (SMASH) and the Performance Improvement plaN GeneratoR (PINGR), both of which are being used in primary care in Salford.

The work of Zach and Dahee aims to develop a formal knowledge base of feedback interventions, based on psychological theory.  The seminar talk featured:

  • an ongoing project at the University of Michigan looking at antimicrobial stewardship
  • preliminary results on the development of a classification system of performance summary displays
  • a set of mechanisms for tailoring displays to improve how GPs process performance summaries.

The Safety Informatics team is planning to work with Zach and Dahee on the further development of the knowledge base of feedback interventions, involving also collaborators from Amsterdam and Toronto. A meeting has been planned at the Audit & Feedback Summit that will be held in May 2018 in Toronto.