Clinical Evaluation of an AI Risk Prediction System (AI-TRiPS) (AI-TRiPS)
Clinical Evaluation of an AI Risk Prediction and Decision Support System for Early Management of Injured Patients: a Stepped-wedge Cluster Randomised Trial
The goal of this clinical study is to evaluate a software device and its impact on clinician behaviour during the initial management of trauma patients in a real-world clinical setting. Known as the AI-TRiPS Device this software uses real-time prehospital data and machine learning-based risk predictions which are displayed digitally for hospital trauma teams prior patient arrival.
The investigators will use a Stepped Wedge Cluster Randomised Controlled study design with an integrated process evaluation.
The Device will be deployed across the London Major Trauma System where the Major Trauma Centres will be the clusters. Each cluster will transition from control (standard care) to intervention at a pre-specified time (time of transition is randomised).
Primary Outcome: Clinician behaviour, assessed via the accuracy of risk prediction and clinician confidence.
Secondary Outcome: Clinician acceptability, care process metrics, patient outcomes, and safety endpoints.
Primary study population: Hospital trauma clinicians, following initial resuscitation of each eligible trauma patient, who will complete electronic questionnaires.
Secondary study population: Adult trauma patients, data will be collected for the duration of their index admission to hospital, to assess outcomes and enable comparison with clinician risk predictions.
Visão geral do estudo
Status
Intervenção / Tratamento
Descrição detalhada
This project evaluates a bespoke risk prediction system developed by trauma surgeons, pre-hospital clinicians, and computer scientists. The device aims to enhance the situational awareness of hospital trauma teams via a digital display, located in the resuscitation suite, depicting pre-hospital patient status and individualised risk predictions.
Evidence Base and Prior Work
The AI-TRiPS Device builds on an extensive, multi-phase programme of research led by the Centre for Trauma Sciences at Queen Mary University of London, funded by the US Department of Defense, UK Ministry of Defence, and Rosetrees Trust. This programme has:
- Investigated trauma clinical decision-making, demonstrating that situational awareness is often impaired by uncertainty and cognitive load, and highlighting the need for decision support during early trauma resuscitation.
- Developed clinically relevant, explainable Bayesian network models using hybrid data- and knowledge-driven methods, with internal and external validation across large civilian and military trauma datasets.
- Designed and iteratively refined a web-based clinical decision support system (CDSS) to deliver model outputs through an interface tailored to trauma resuscitation workflows, incorporating end-user feedback.
- Conducted simulation and operational studies demonstrating improved clinician performance with the CDSS compared to unaided judgement.
- Contributed methodological work to support the safe and effective translation of prediction algorithms into usable and trustworthy clinical tools, including published frameworks for usability testing, implementation evaluation, and explainability in clinical decision support.
The current stage of development is consistent with early-stage clinical evaluation of a Software as a Medical Device (SaMD) under UK MDR 2002 and ISO 14155.
This trial is designed to evaluate clinical performance and safety in real-world conditions, with a primary focus on effects on clinician behaviour and decision-making. While patient outcomes will be collected, the study is not powered to assess downstream impact on clinical outcomes.
Primary Objective To evaluate the impact of the AI-TRiPS device on clinician behaviour during the initial management of trauma patients in a real-world clinical setting, specifically situational awareness (clinician perception of individual patient risk), associated confidence, and cognitive load, compared with standard unassisted clinician performance.
Hypothesis The investigators hypothesise that delivering accurate, real-time risk estimates to trauma clinicians during the initial phase of trauma care will improve situational awareness - in particular, clinicians' perception of individual patient risks - along with increased confidence and reduced cognitive effort, compared with standard unassisted clinician performance.
Null Hypothesis There is no difference in clinician situational awareness (including perception of risk), confidence, or cognitive load between AI-assisted and unassisted clinician performance during initial trauma care.
Secondary objective(s)
Secondary Objectives
• Evaluate impact on Clinician Decision-Making: To assess the effect of the AI-TRiPS device on clinician decision-making, as a potential downstream effect of changes in clinician risk perception (situational awareness).
• Evaluate impact on Clinical Processes: To assess the effect of the AI-TRiPS device on early trauma care processes, including time to critical interventions and length of stay
• Evaluate Patient Impact: To examine patient outcomes associated with clinician exposure to the AI-TRiPS device, recognising these as indirect effects mediated by altered clinical decision-making.
• Evaluate Real-World System Performance: To assess the real-world performance of the AI-TRiPS device, including prediction calibration and the identification of system errors or underperformance that may affect clinical decision-making.
• Evaluate usability and acceptability (Integrated Process Evaluation): To explore the acceptability, usability, and contextual factors that influence the implementation and adoption of the AI-TRiPS device in real-world clinical settings.
Tipo de estudo
Inscrição (Estimado)
Estágio
- Fase inicial 1
Contactos e Locais
Contato de estudo
- Nome: Dr Mays Jawad
- Número de telefone: +4402078827275
- E-mail: research.governance@qmul.ac.uk
Estude backup de contato
- Nome: Prof. N Tai
- Número de telefone: +4402073777044
- E-mail: bartsheatlh.AITRIPS@nhs.net
Critérios de participação
Critérios de elegibilidade
Idades elegíveis para estudo
- Filho
- Adulto
- Adulto mais velho
Aceita Voluntários Saudáveis
Descrição
Inclusion Criteria:
Clinician Participants
- Senior clinical decision-maker involved in the initial trauma resuscitation (e.g. consultant or senior trainee in emergency medicine, anaesthesia, intensive care medicine, or surgery).
- Based at one of the four participating Major Trauma Centres.
- Able and willing to provide informed consent.
- Completed the required study-specific training.
Trauma Patients
- Aged 16 years and above.
- Treated and transported to a participating Major Trauma Centre by London's Air Ambulance.
- Managed by one or more participating trauma clinicians during the resuscitation.
Exclusion Criteria:
Clinician Participants
● Decline or withdraw informed consent at any stage.
Trauma Patients
- Aged under 16
- Not treated by London's Air Ambulance.
- Transported to a non-participating hospital.
- Not managed by any participating clinicians.
- Presenting with injuries resulting from burns, hangings, drownings, or isolated psychiatric emergencies.
- Have registered a national NHS data opt-out or otherwise requested that their routine clinical data not be used for research.
Plano de estudo
Como o estudo é projetado?
Detalhes do projeto
- Finalidade Principal: Outro
- Alocação: Randomizado
- Modelo Intervencional: Atribuição sequencial
- Mascaramento: Nenhum (rótulo aberto)
Armas e Intervenções
Grupo de Participantes / Braço |
Intervenção / Tratamento |
|---|---|
|
Experimental: AI TRIPS device intervention
Patients who fit the eligibility criteria are triaged and treated at the participating trauma centre by trauma clinicians who have been exposed to the individualised risk predictions for that patient.
|
This is Software as a Medical Device designed to function as an aid to inform clinical situational awareness by presenting predictions of patient trajectory (probability of death, probability of trauma induced coagulopathy, probability of red cell transfusion, probability of acute kidney injury).
|
|
Sem intervenção: Usual Standard Care
Patients who fit the eligibility criteria are triaged and treated at the participating trauma centre by trauma clinicians under standard conditions.
|
O que o estudo está medindo?
Medidas de resultados primários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Clinician Risk Prediction - Mortality, Trauma Induced Coagulopathy, and Acute Kidney Injury
Prazo: Baseline
|
Clinician participants will make probability estimates (0-100%) on index admission in each of the 3 domains.
|
Baseline
|
|
Clinician Risk Prediction - Estimation of Blood Transfusion Volume
Prazo: Baseline
|
Clinicians will estimate the number(n) of packed red blood cell (pRBC) units required for transfusion in the first 24 hours.
The estimation will take place immediately after initial resuscitation.
|
Baseline
|
|
Clinician Confidence
Prazo: Baseline to 24 Hours - Immediately following initial clinician predictions
|
Clinician Participants will self-report their confidence in their predictions using the Post-Task Confidence Scale (PTCS), a Likert scale from 1-7, where the higher the score the higher the level confidence.
|
Baseline to 24 Hours - Immediately following initial clinician predictions
|
|
Clinician Cognitive Effort
Prazo: Baseline to 24 Hours - immediately following risk predictions
|
Clinician participants self-report the mental effort required to make each prediction using the Paas Mental Effort Scale ( Likert Scale 1-9) where a lower score corresponds to low mental effort.
|
Baseline to 24 Hours - immediately following risk predictions
|
|
Risk Prediction Accuracy
Prazo: From Discharge through to study completion, an average of 1 year.
|
For each of the 4 domains in which predictions have been made, accuracy of these predictions will be determined with a comparison to patient outcomes.
This will be done using the Brier score, however other metrics of predictive performance may also be used to perform comparisons, including measures of discrimination, calibration, and accuracy (Brier skill Score, Mean Absolute Error)
|
From Discharge through to study completion, an average of 1 year.
|
Medidas de resultados secundários
Medida de resultado |
Descrição da medida |
Prazo |
|---|---|---|
|
Clinician Decision-Making Behaviour - Decision Making
Prazo: From discharge through to study completion, an average of 1 year.
|
Measurement of whether a decision was made (Decision in this case refers to activation of the major haemorrhage protocol, or proceeding directly to definitive haemorrhage control). This data will be extracted from the National Major Trauma Registry and/or patient clinical records. Binary (yes/no) based on whether the outcome was performed. |
From discharge through to study completion, an average of 1 year.
|
|
Clinician Decision-Making Behaviour - Appropriateness of Decision Making
Prazo: From Discharge through to study completion, an average of 1 year.
|
Expert panel review of decision making with regards to activation of major haemorrhage protocol/proceeding directly to definitive haemorrhage control. Expert review of extracted patient data from National Major Trauma Registry and/or Patient clinical records. Binary (Appropriate/Inappropriate) |
From Discharge through to study completion, an average of 1 year.
|
|
Clinician Decision-Making Behaviour - Clinician Confidence
Prazo: Baseline to 24 hours - Immediately following initial clinician decision making
|
Clinician Participants will self-report their confidence in their predictions using the Post-Task Confidence Scale (PTCS), a Likert scale from 1-7, where the higher the score the higher the level confidence.
|
Baseline to 24 hours - Immediately following initial clinician decision making
|
|
Clinician Decision-Making Behaviour - Clinician Cognitive Effort
Prazo: Baseline to 24 Hours - immediately following risk predictions
|
Clinician participants self-report the mental effort required to make each prediction using the Paas Mental Effort Scale ( Likert Scale 1-9) where a lower score corresponds to low mental effort.
|
Baseline to 24 Hours - immediately following risk predictions
|
|
Clinician Decision-Making Behaviour - Time Pressure
Prazo: Baseline to 24 Hours - immediately following decision making
|
Clinicians self report time pressure using the NASA Task Load Index Temporal Demand Subscale (Likert Scale 1-10).
This is measured immediately after each decision.
|
Baseline to 24 Hours - immediately following decision making
|
|
Clinical Process Measures - Time to Major Haemorrhage Protocol(MHP) Activation
Prazo: Baseline - 12 Hours
|
Time to MHP activation in minutes(continuous) from arrival to activation of major haemorrhage protocol. Data collected from National Major Trauma Registry and/or patient hospital records. |
Baseline - 12 Hours
|
|
Clinical Process Measures - Time to Haemorrhage Control
Prazo: Baseline - 12 Hours
|
Time to Haemorrhage control in minutes(continuous) from arrival to start of first definitive haemorrhage control intervention. Data collected from National Major Trauma Registry and/or patient hospital records. |
Baseline - 12 Hours
|
|
Clinical Process Measures - Length of Hospital Stay
Prazo: Discharge through to study completion, an average of 1 year
|
Total number of inpatient hospital days (continuous), measured from index admission to discharge.
Data obtained from National Major Trauma Registry and/or patient clinical records following discharge.
|
Discharge through to study completion, an average of 1 year
|
|
Clinical Process Measures - Intensive Care Unit (ICU) length of stay
Prazo: Discharge through to study completion, an average of 1 year
|
Total number of intensive care unit days (continuous), measured from index admission to discharge.
Data obtained from National Major Trauma Registry and/or patient clinical records following discharge.
|
Discharge through to study completion, an average of 1 year
|
|
Patient Outcome Measure - In Hospital Mortality
Prazo: From Baseline to Discharge/Death
|
Patient death during index hospital admission, Binary (yes/No).
|
From Baseline to Discharge/Death
|
|
Patient Outcome Measure - Trauma Induced Coagulopathy
Prazo: Baseline
|
Trauma-induced coagulopathy will be assessed using the admission prothrombin time ratio (PTr).
This variable will be recorded as binary (yes/no), with trauma-induced coagulopathy defined as a PTr > 1.2
|
Baseline
|
|
Patient Outcome Measure - Blood Transfusion Volume
Prazo: Baseline to 24 hours
|
The total number (N) of units of packed red blood cells (pRBC) transfused to the patient within the first 24 hours post injury.
|
Baseline to 24 hours
|
|
Patient Outcome Measure - Acute Kidney Injury
Prazo: Baseline to 72 hours
|
The degree of acute kidney injury will be recorded using the Kidney Disease Improving Global Outcomes(KDIGO) stage 1-3, over the first 72 hours post injury.
|
Baseline to 72 hours
|
Colaboradores e Investigadores
Patrocinador
Colaboradores
Investigadores
- Investigador principal: Prof. N Tai, Queen Mary University London
Publicações e links úteis
Publicações Gerais
- Kyrimi E, Neves MR, McLachlan S, Neil M, Marsh W, Fenton N. Medical idioms for clinical Bayesian network development. J Biomed Inform. 2020 Aug;108:103495. doi: 10.1016/j.jbi.2020.103495. Epub 2020 Jun 30.
- McLachlan S, Kyrimi E, Wohlgemut J, Perkins Z, Lagnado D, Marsh W. Explainable AI: Definition and characteristics of a good explanation for health AI. AI and Ethics. 2025:1.
- Wohlgemut JM, Pisirir E, Stoner RS, Perkins ZB, Marsh W, Tai NRM, Kyrimi E. A scoping review, novel taxonomy and catalogue of implementation frameworks for clinical decision support systems. BMC Med Inform Decis Mak. 2024 Nov 1;24(1):323. doi: 10.1186/s12911-024-02739-1.
- Kyrimi E, McLachlan S, Wohlgemut JM, Perkins ZB, Lagnado DA, Marsh W. Explainable AI: definition and attributes of a good explanation for health AI. AI and Ethics. 2025:1-14.
- Pisirir E, Wohlgemut JM, Kyrimi E, et al. A process for evaluating explanations for transparent and trustworthy ai prediction models. IEEE; 2023:388-397.
- Kyrimi E, Stoner RS, Perkins ZB, Pisirir E, Wohlgemut JM, Marsh W, Tai NRM. Updating and recalibrating causal probabilistic models on a new target population. J Biomed Inform. 2024 Jan;149:104572. doi: 10.1016/j.jbi.2023.104572. Epub 2023 Dec 9.
- Wohlgemut JM, Pisirir E, Kyrimi E, Stoner RS, Marsh W, Perkins ZB, Tai NRM. Methods used to evaluate usability of mobile clinical decision support systems for healthcare emergencies: a systematic review and qualitative synthesis. JAMIA Open. 2023 Jul 12;6(3):ooad051. doi: 10.1093/jamiaopen/ooad051. eCollection 2023 Oct.
- Marsden MER, Perkins ZB, Pisirir E, Marsh W, Kyrimi E, Rossetto A, Lyon RL, Weaver A, Davenport R, Tai NR. Early clinical evaluation of a machine-learning system for risk prediction of trauma-induced coagulopathy in the prehospital setting. Emerg Med J. 2025 Sep 24;42(10):654-661. doi: 10.1136/emermed-2024-214396.
- Marsden M, Perkins Z, Marsh W, et al. Evaluation of an Artificial Intelligence (AI) system to augment clinical risk prediction of Trauma Induced Coagulopathy in the pre-hospital setting: a prospective observational study: 3. BMJ Military Health. 2022;168(5):e12.
- Alptekin C, Wohlgemut JM, Perkins ZB, Marsh W, Tai NRM, Yet B. Presenting predictions and performance of probabilistic models for clinical decision support in trauma care. Int J Med Inform. 2025 Feb;194:105702. doi: 10.1016/j.ijmedinf.2024.105702. Epub 2024 Nov 14.
- Wohlgemut JM, Kyrimi E, Stoner RS, Pisirir E, Marsh W, Perkins ZB, Tai NRM. The outcome of a prediction algorithm should be a true patient state rather than an available surrogate. J Vasc Surg. 2022 Apr;75(4):1495-1496. doi: 10.1016/j.jvs.2021.10.059. Epub 2021 Dec 16. No abstract available.
- Tandle S, Wohlgemut JM, Marsden MER, Pisirir E, Kyrimi E, Stoner RS, Marsh W, Perkins ZB, Tai NRM. Enhancing the clinical relevance of haemorrhage prediction models in trauma. Mil Med Res. 2023 Sep 20;10(1):43. doi: 10.1186/s40779-023-00476-6. No abstract available.
- Perkins ZB, Yet B, Sharrock A, Rickard R, Marsh W, Rasmussen TE, Tai NRM. Predicting the Outcome of Limb Revascularization in Patients With Lower-extremity Arterial Trauma: Development and External Validation of a Supervised Machine-learning Algorithm to Support Surgical Decisions. Ann Surg. 2020 Oct;272(4):564-572. doi: 10.1097/SLA.0000000000004132.
- Kyrimi E, Mossadegh S, Tai N, Marsh W. An incremental explanation of inference in Bayesian networks for increasing model trustworthiness and supporting clinical decision making. Artif Intell Med. 2020 Mar;103:101812. doi: 10.1016/j.artmed.2020.101812. Epub 2020 Jan 31.
- Yet B, Perkins ZB, Tai NR, Marsh DWR. Clinical evidence framework for Bayesian networks. Knowledge and Information Systems. 2017;50(1):117-143.
- Yet B, Perkins ZB, Rasmussen TE, Tai NR, Marsh DW. Combining data and meta-analysis to build Bayesian networks for clinical decision support. J Biomed Inform. 2014 Dec;52:373-85. doi: 10.1016/j.jbi.2014.07.018. Epub 2014 Aug 9.
- Yet B, Perkins Z, Fenton N, Tai N, Marsh W. Not just data: a method for improving prediction with knowledge. J Biomed Inform. 2014 Apr;48:28-37. doi: 10.1016/j.jbi.2013.10.012. Epub 2013 Nov 2.
- Perkins ZB, Yet B, Marsden M, Glasgow S, Marsh W, Davenport R, Brohi K, Tai NRM. Early Identification of Trauma-induced Coagulopathy: Development and Validation of a Multivariable Risk Prediction Model. Ann Surg. 2021 Dec 1;274(6):e1119-e1128. doi: 10.1097/SLA.0000000000003771.
- Durrands TH, Murphy M, Wohlgemut JM, De'Ath HD, Perkins ZB. Diagnostic accuracy of clinical examination for identification of life-threatening torsos injuries: a meta-analysis. Br J Surg. 2023 Nov 9;110(12):1885-1886. doi: 10.1093/bjs/znad285. No abstract available.
- Wohlgemut JM, Pisirir E, Stoner RS, Kyrimi E, Christian M, Hurst T, Marsh W, Perkins ZB, Tai NRM. Identification of major hemorrhage in trauma patients in the prehospital setting: diagnostic accuracy and impact on outcome. Trauma Surg Acute Care Open. 2024 Jan 12;9(1):e001214. doi: 10.1136/tsaco-2023-001214. eCollection 2024.
- Marsden MER, Kellett S, Bagga R, Wohlgemut JM, Lyon RL, Perkins ZB, Gillies K, Tai NR. Understanding pre-hospital blood transfusion decision-making for injured patients: an interview study. Emerg Med J. 2023 Nov;40(11):777-784. doi: 10.1136/emermed-2023-213086. Epub 2023 Sep 13.
- Wohlgemut JM, Marsden MER, Stoner RS, Pisirir E, Kyrimi E, Grier G, Christian M, Hurst T, Marsh W, Tai NRM, Perkins ZB. Diagnostic accuracy of clinical examination to identify life- and limb-threatening injuries in trauma patients. Scand J Trauma Resusc Emerg Med. 2023 Apr 7;31(1):18. doi: 10.1186/s13049-023-01083-z.
Datas de registro do estudo
Datas Principais do Estudo
Início do estudo (Estimado)
Conclusão Primária (Estimado)
Conclusão do estudo (Estimado)
Datas de inscrição no estudo
Enviado pela primeira vez
Enviado pela primeira vez que atendeu aos critérios de CQ
Primeira postagem (Real)
Atualizações de registro de estudo
Última Atualização Postada (Real)
Última atualização enviada que atendeu aos critérios de controle de qualidade
Última verificação
Mais Informações
Termos relacionados a este estudo
Palavras-chave
Termos MeSH relevantes adicionais
Outros números de identificação do estudo
- 354225
- 179821 (Outro identificador: Queen Mary University)
Plano para dados de participantes individuais (IPD)
Planeja compartilhar dados de participantes individuais (IPD)?
Informações sobre medicamentos e dispositivos, documentos de estudo
Estuda um medicamento regulamentado pela FDA dos EUA
Estuda um produto de dispositivo regulamentado pela FDA dos EUA
Essas informações foram obtidas diretamente do site clinicaltrials.gov sem nenhuma alteração. Se você tiver alguma solicitação para alterar, remover ou atualizar os detalhes do seu estudo, entre em contato com register@clinicaltrials.gov. Assim que uma alteração for implementada em clinicaltrials.gov, ela também será atualizada automaticamente em nosso site .