Contextual design requirements for decision-support tools involved in weaning patients from mechanical ventilation in intensive care units.

Weaning patients from ventilation in intensive care units (ICU) is a complex task. There is a growing desire to build decision-support tools to help clinicians during this process, especially those employing Artificial Intelligence (AI). However, tools built for this purpose should fit within and ideally improve the current work environment, to ensure they can successfully integrate into clinical practice. To do so, it is important to identify areas where decision-support tools may aid clinicians, and associated design requirements for such tools. This study analysed the work context surrounding the weaning process from mechanical ventilation in ICU environments, via cognitive task and work domain analyses. In doing so, both what cognitive processes clinicians perform during weaning, and the constraints and affordances of the work environment itself, were described. This study found a number of weaning process tasks where decision-support tools may prove beneficial, and from these a set of contextual design requirements were created. This work benefits researchers interested in creating human-centred decision-support tools for mechanical ventilation that are sensitive to the wider work system.

Building on a novel bootstrapping modelling technique to predict region-wide critical care capacity requirements over the next decade.

We have previously described an open-source data-driven modelling technique that has been used to model critical care resource provision as well as expanded to elective surgery and even whole-hospital modelling. Here, we describe the use of this technique to model patient flow and resource use across the West Yorkshire Critical Care Network, with the advantage that recommendations can be made at an individual unit level for future resource provision, taking into account changes in population numbers and demography over the coming decade. We will be using this approach in other regions around the UK to help predict future critical care capacity requirements.

The impact of hospital command centre on patient flow and data quality: findings from the UK National Health Service.

In the last 6 years, hospitals in developed countries have been trialling the use of command centres for improving organizational efficiency and patient care. However, the impact of these command centres has not been systematically studied in the past. It is a retrospective population-based study. Participants were patients who visited the Bradford Royal Infirmary hospital, Accident and Emergency (A&E) Department, between 1 January 2018 and 31 August 2021. Outcomes were patient flow (measured as A&E waiting time, length of stay, and clinician seen time) and data quality (measured by the proportion of missing treatment and assessment dates and valid transition between A&E care stages). Interrupted time-series segmented regression and process mining were used for analysis. A&E transition time from patient arrival to assessment by a clinician marginally improved during the intervention period; there was a decrease of 0.9 min [95% confidence interval (CI): 0.35-1.4], 3 min (95% CI: 2.4-3.5), 9.7 min (95% CI: 8.4-11.0), and 3.1 min (95% CI: 2.7-3.5) during 'patient flow program', 'command centre display roll-in', 'command centre activation', and 'hospital wide training program', respectively. However, the transition time from patient treatment until the conclusion of consultation showed an increase of 11.5 min (95% CI: 9.2-13.9), 12.3 min (95% CI: 8.7-15.9), 53.4 min (95% CI: 48.1-58.7), and 50.2 min (95% CI: 47.5-52.9) for the respective four post-intervention periods. Furthermore, the length of stay was not significantly impacted; the change was -8.8 h (95% CI: -17.6 to 0.08), -8.9 h (95% CI: -18.6 to 0.65), -1.67 h (95% CI: -10.3 to 6.9), and -0.54 h (95% CI: -13.9 to 12.8) during the four respective post-intervention periods. It was a similar pattern for the waiting and clinician seen times. Data quality as measured by the proportion of missing dates of records was generally poor (treatment date = 42.7% and clinician seen date = 23.4%) and did not significantly improve during the intervention periods. The findings of the study suggest that a command centre package that includes process change and software technology does not appear to have a consistent positive impact on patient safety and data quality based on the indicators and data we used. Therefore, hospitals considering introducing a command centre should not assume there will be benefits in patient flow and data quality.

Descriptive account of the first use of the LeVe CPAP System, a new frugal CPAP System, in adult patients with COVID-19 Pneumonitis in Uganda.

BACKGROUND: Continuous positive airway pressure (CPAP) has been a key treatment modality for Coronavirus Disease 2019 (COVID-19) worldwide. Globally, the demand for CPAP outstripped the supply during the pandemic. The LeVe CPAP System was developed to provide respiratory support for treatment of COVID-19 and tailored for use in low- and middle-income country (LMIC) settings. Prior to formal trial approval, received in November 2021, these devices were used in extremis to support critically unwell adult patients requiring non-invasive ventilatory support. METHODS: This is a retrospective descriptive review of adult patients with COVID-19 pneumonitis, who were treated with advanced respiratory support (CPAP and/or high-flow nasal oxygen, HFNO) at Mengo Hospital, Uganda. Patients were treated with the LeVe CPAP System, Elisa CPAP and/or AIRVO™ HFNO. Treatment was escalated per standard local protocols for respiratory failure, and CPAP was the maximum respiratory support available. Data were collected on patient characteristics, length of time of treatment, clinical outcome, and any adverse events. RESULTS: Overall 333 patients were identified as COVID-19 positive, 44 received CPAP ± HFNO of which 43 were included in the study. The median age was 58 years (range 28-91 years) and 58% were female. The median duration of advanced respiratory support was 7 days (range 1-18 days). Overall (all device) mortality was 49% and this was similar between those started on the LeVe CPAP System and those started non-LeVe CPAP System devices (50% vs 47%). CONCLUSIONS: The LeVe CPAP system was the most used CPAP device during the pandemic, bringing the hospital's number of available HFNO/CPAP devices from two to 14. They were a critical resource for providing respiratory support to the sickest group of patients when no alternative devices were available. The devices appear to be safe and well-tolerated with no serious adverse events recorded. This study is unable to assess the efficacy of the LeVe CPAP System; therefore, formal comparative studies are required to inform further use.

Predicting Progression of Type 2 Diabetes Using Primary Care Data with the Help of Machine Learning.

Type 2 diabetes is a life-long health condition, and as it progresses, A range of comorbidities can develop. The prevalence of diabetes has increased gradually, and it is expected that 642 million adults will be living with diabetes by 2040. Early and proper interventions for managing diabetes-related comorbidities are important. In this study, we propose a Machine Learning (ML) model for predicting the risk of developing hypertension for patients who already have Type 2 diabetes. We used the Connected Bradford dataset, consisting of 1.4 million patients, as our main dataset for data analysis and model building. As a result of data analysis, we found that hypertension is the most frequent observation among patients having Type 2 diabetes. Since hypertension is very important to predict clinically poor outcomes such as risk of heart, brain, kidney, and other diseases, it is crucial to make early and accurate predictions of the risk of having hypertension for Type 2 diabetic patients. We used Naïve Bayes (NB), Neural Network (NN), Random Forest (RF), and Support Vector Machine (SVM) to train our model. Then we ensembled these models to see the potential performance improvement. The ensemble method gave the best classification performance values of accuracy and kappa values of 0.9525 and 0.2183, respectively. We concluded that predicting the risk of developing hypertension for Type 2 diabetic patients using ML provides a promising stepping stone for preventing the Type 2 diabetes progression.

Effect of a hospital command centre on patient safety: an interrupted time series study.

BACKGROUND: Command centres have been piloted in some hospitals across the developed world in the last few years. Their impact on patient safety, however, has not been systematically studied. Hence, we aimed to investigate this. METHODS: This is a retrospective population-based cohort study. Participants were patients who visited Bradford Royal Infirmary Hospital and Calderdale & Huddersfield hospitals between 1 January 2018 and 31 August 2021. A five-phase, interrupted time series, linear regression analysis was used. RESULTS: After introduction of a Command Centre, while mortality and readmissions marginally improved, there was no statistically significant impact on postoperative sepsis. In the intervention hospital, when compared with the preintervention period, mortality decreased by 1.4% (95% CI 0.8% to 1.9%), 1.5% (95% CI 0.9% to 2.1%), 1.3% (95% CI 0.7% to 1.8%) and 2.5% (95% CI 1.7% to 3.4%) during successive phases of the command centre programme, including roll-in and activation of the technology and preparatory quality improvement work. However, in the control site, compared with the baseline, the weekly mortality also decreased by 2.0% (95% CI 0.9 to 3.1), 2.3% (95% CI 1.1 to 3.5), 1.3% (95% CI 0.2 to 2.4), 3.1% (95% CI 1.4 to 4.8) for the respective intervention phases. No impact on any of the indicators was observed when only the software technology part of the Command Centre was considered. CONCLUSION: Implementation of a hospital Command Centre may have a marginal positive impact on patient safety when implemented as part of a broader hospital-wide improvement programme including colocation of operations and clinical leads in a central location. However, improvement in patient safety indicators was also observed for a comparable period in the control site. Further evaluative research into the impact of hospital command centres on a broader range of patient safety and other outcomes is warranted.

Connected Bradford: a Whole System Data Linkage Accelerator.

The richness of linked population data provides exciting opportunities to understand local health needs, identify and predict those in most need of support and evaluate health interventions. There has been extensive investment to unlock the potential of clinical data for health research in the UK. However, most of the determinants of our health are social, economic, education, environmental, housing, food systems and are influenced by local authorities. The Connected Bradford Whole System Data Linkage Accelerator was set up to link health, education, social care, environmental and other local government data to drive learning health systems, prevention and population health management. Data spanning a period of over forty years has been linked for 800,000 individuals using the pseudonymised NHS number and other data variables. This prospective data collection captures near real time activity. This paper describes the dataset and our Connected Bradford Whole System Data Accelerator Framework that covers public engagement; practitioner and policy integration; legal and ethical approvals; information governance; technicalities of data linkage; data curation and guardianship; data validity and visualisation.

Evaluating the safety and patient impacts of an artificial intelligence command centre in acute hospital care: a mixed-methods protocol.

INTRODUCTION: This paper presents a mixed-methods study protocol that will be used to evaluate a recent implementation of a real-time, centralised hospital command centre in the UK. The command centre represents a complex intervention within a complex adaptive system. It could support better operational decision-making and facilitate identification and mitigation of threats to patient safety. There is, however, limited research on the impact of such complex health information technology on patient safety, reliability and operational efficiency of healthcare delivery and this study aims to help address that gap. METHODS AND ANALYSIS: We will conduct a longitudinal mixed-method evaluation that will be informed by public-and-patient involvement and engagement. Interviews and ethnographic observations will inform iterations with quantitative analysis that will sensitise further qualitative work. Quantitative work will take an iterative approach to identify relevant outcome measures from both the literature and pragmatically from datasets of routinely collected electronic health records. ETHICS AND DISSEMINATION: This protocol has been approved by the University of Leeds Engineering and Physical Sciences Research Ethics Committee (#MEEC 20-016) and the National Health Service Health Research Authority (IRAS No.: 285933). Our results will be communicated through peer-reviewed publications in international journals and conferences. We will provide ongoing feedback as part of our engagement work with local trust stakeholders.

Reduced critical care demand with early CPAP and proning in COVID-19 at Bradford: A single-centre cohort.

Background: Guidance in COVID-19 respiratory failure has favoured early intubation, with concerns over the use of CPAP. We adopted early CPAP and self-proning, and evaluated the safety and efficacy of this approach. Methods: This retrospective observational study included all patients with a positive COVID-19 PCR, and others with high clinical suspicion. Our protocol advised early CPAP and self-proning for severe cases, aiming to prevent rather than respond to deterioration. CPAP was provided outside critical care by ward staff supported by physiotherapists and an intensive critical care outreach program. Data were analysed descriptively and compared against a large UK cohort (ISARIC). Results: 559 patients admitted before 1 May 2020 were included. 376 were discharged alive, and 183 died. 165 patients (29.5%) received CPAP, 40 (7.2%) were admitted to critical care and 28 (5.0%) were ventilated. Hospital mortality was 32.7%, and 50% for critical care. Following CPAP, 62% of patients with S:F or P:F ratios indicating moderate or severe ARDS, who were candidates for escalation, avoided intubation. Figures for critical care admission, intubation and hospital mortality are lower than ISARIC, whilst critical care mortality is similar. Following ISARIC proportions we would have admitted 92 patients to critical care and intubated 55. Using the described protocol, we intubated 28 patients from 40 admissions, and remained within our expanded critical care capacity. Conclusion: Bradford's protocol produced good results despite our population having high levels of co-morbidity and ethnicities associated with poor outcomes. In particular we avoided overloading critical care capacity. We advocate this approach as both effective and safe.

Ethnicity, pre-existing comorbidities, and outcomes of hospitalised patients with COVID-19.

Background: The coronavirus disease 2019 (COVID-19) pandemic has resulted in thousands of deaths in the UK. Those with existing comorbidities and minority ethnic groups have been found to be at increased risk of mortality. We wished to determine if there were any differences in intensive care unit (ICU) admission and 30-day hospital mortality in a city with high levels of deprivation and a large community of people of South Asian heritage.  Methods: Detailed information on 622 COVID-19-positive inpatients in Bradford and Calderdale between February-August 2020 were extracted from Electronic Health Records. Logistic regression and Cox proportional hazards models were used to explore the relationship between ethnicity with admission to ICU and 30-day mortality, respectively accounting for the effect of demographic and clinical confounders. Results: The sample consisted of 408 (70%) White, 142 (24%) South Asian and 32 (6%) other minority ethnic patients. Ethnic minority patients were younger, more likely to live in deprived areas, and be overweight/obese, have type 2 diabetes, hypertension and asthma compared to white patients, but were less likely to have cancer (South Asian patients only) and COPD. Male and obese patients were more likely to be admitted to ICU, and patients of South Asian ethnicity, older age, and those with cancer were less likely. Being male, older age, deprivation, obesity, and cancer were associated with 30-day mortality. The risk of death in South Asian patients was the same as in white patients HR 1.03 (0.58, 1.82). Conclusions: Despite South Asian patients being less likely to be admitted to ICU and having a higher prevalence of diabetes and obesity, there was no difference in the risk of death compared to white patients. This contrasts with other findings and highlights the value of studies of communities which may have different ethnic, deprivation and clinical risk profiles.

Noninvasive respiratory support outside the intensive care unit for acute respiratory failure related to coronavirus-19 disease: a systematic review and meta-analysis.

BACKGROUND: Noninvasive respiratory support (NIRS) has been diffusely employed outside the intensive care unit (ICU) to face the high request of ventilatory support due to the massive influx of patients with acute respiratory failure (ARF) caused by coronavirus-19 disease (COVID-19). We sought to summarize the evidence on clinically relevant outcomes in COVID-19 patients supported by NIV outside the ICU. METHODS: We searched PUBMED®, EMBASE®, and the Cochrane Controlled Clinical trials register, along with medRxiv and bioRxiv repositories for pre-prints, for observational studies and randomized controlled trials, from inception to the end of February 2021. Two authors independently selected the investigations according to the following criteria: (1) observational study or randomized clinical trials enrolling ≥ 50 hospitalized patients undergoing NIRS outside the ICU, (2) laboratory-confirmed COVID-19, and (3) at least the intra-hospital mortality reported. Preferred Reporting Items for Systematic reviews and Meta-analysis guidelines were followed. Data extraction was independently performed by two authors to assess: investigation features, demographics and clinical characteristics, treatments employed, NIRS regulations, and clinical outcomes. Methodological index for nonrandomized studies tool was applied to determine the quality of the enrolled studies. The primary outcome was to assess the overall intra-hospital mortality of patients under NIRS outside the ICU. The secondary outcomes included the proportions intra-hospital mortalities of patients who underwent invasive mechanical ventilation following NIRS failure and of those with 'do-not-intubate' (DNI) orders. RESULTS: Seventeen investigations (14 peer-reviewed and 3 pre-prints) were included with a low risk of bias and a high heterogeneity, for a total of 3377 patients. The overall intra-hospital mortality of patients receiving NIRS outside the ICU was 36% [30-41%]. 26% [21-30%] of the patients failed NIRS and required intubation, with an intra-hospital mortality rising to 45% [36-54%]. 23% [15-32%] of the patients received DNI orders with an intra-hospital mortality of 72% [65-78%]. Oxygenation on admission was the main source of between-study heterogeneity. CONCLUSIONS: During COVID-19 outbreak, delivering NIRS outside the ICU revealed as a feasible strategy to cope with the massive demand of ventilatory assistance. REGISTRATION: PROSPERO, https://www.crd.york.ac.uk/prospero/ , CRD42020224788, December 11, 2020.

Prediction of weaning from mechanical ventilation using Convolutional Neural Networks.

Weaning from mechanical ventilation covers the process of liberating the patient from mechanical support and removing the associated endotracheal tube. The management of weaning from mechanical ventilation comprises a significant proportion of the care of critically ill intubated patients in Intensive Care Units (ICUs). Both prolonged dependence on mechanical ventilation and premature extubation expose patients to an increased risk of complications and increased health care costs. This work aims to develop a decision support model using routinely-recorded patient information to predict extubation readiness. In order to do so, we have deployed Convolutional Neural Networks (CNN) to predict the most appropriate treatment action in the next hour for a given patient state, using historical ICU data extracted from MIMIC-III. The model achieved 86% accuracy and 0.94 area under the receiver operating characteristic curve (AUC-ROC). We also performed feature importance analysis for the CNN model and interpreted these features using the DeepLIFT method. The results of the feature importance assessment show that the CNN model makes predictions using clinically meaningful and appropriate features. Finally, we implemented counterfactual explanations for the CNN model. This can help clinicians understand what feature changes for a particular patient would lead to a desirable outcome, i.e. readiness to extubate.

Safety-driven design of machine learning for sepsis treatment.

Machine learning (ML) has the potential to bring significant clinical benefits. However, there are patient safety challenges in introducing ML in complex healthcare settings and in assuring the technology to the satisfaction of the different regulators. The work presented in this paper tackles the urgent problem of proactively assuring ML in its clinical context as a step towards enabling the safe introduction of ML into clinical practice. In particular, the paper considers the use of deep Reinforcement Learning, a type of ML, for sepsis treatment. The methodology starts with the modelling of a clinical workflow that integrates the ML model for sepsis treatment recommendations. Then safety analysis is carried out based on the clinical workflow, identifying hazards and safety requirements for the ML model. In this paper the design of the ML model is enhanced to satisfy the safety requirements for mitigating a major clinical hazard: sudden change of vasopressor dose. A rigorous evaluation is conducted to show how these requirements are met. A safety case is presented, providing a basis for regulators to make a judgement on the acceptability of introducing the ML model into sepsis treatment in a healthcare setting. The overall argument is broad in considering the wider patient safety considerations, but the detailed rationale and supporting evidence presented relate to this specific hazard. Whilst there are no agreed regulatory approaches to introducing ML into healthcare, the work presented in this paper has shown a possible direction for overcoming this barrier and exploit the benefits of ML without compromising safety.

The LeVe CPAP System for Oxygen-Efficient CPAP Respiratory Support: Development and Pilot Evaluation.

Background: The COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has placed a significant demand on healthcare providers (HCPs) to provide respiratory support for patients with moderate to severe symptoms. Continuous Positive Airway Pressure (CPAP) non-invasive ventilation can help patients with moderate symptoms to avoid the need for invasive ventilation in intensive care. However, existing CPAP systems can be complex (and thus expensive) or require high levels of oxygen, limiting their use in resource-stretched environments. Technical Development + Testing: The LeVe ("Light") CPAP system was developed using principles of frugal innovation to produce a solution of low complexity and high resource efficiency. The LeVe system exploits the air flow dynamics of electric fan blowers which are inherently suited to delivery of positive pressure at appropriate flow rates for CPAP. Laboratory evaluation demonstrated that performance of the LeVe system was equivalent to other commercially available systems used to deliver CPAP, achieving a 10 cm H2O target pressure within 2.4% RMS error and 50-70% FiO2 dependent with 10 L/min oxygen from a commercial concentrator. Pilot Evaluation: The LeVe CPAP system was tested to evaluate safety and acceptability in a group of ten healthy volunteers at Mengo Hospital in Kampala, Uganda. The study demonstrated that the system can be used safely without inducing hypoxia or hypercapnia and that its use was well-tolerated by users, with no adverse events reported. Conclusions: To provide respiratory support for the high patient numbers associated with the COVID-19 pandemic, healthcare providers require resource efficient solutions. We have shown that this can be achieved through frugal engineering of a CPAP ventilation system, in a system which is safe for use and well-tolerated in healthy volunteers. This approach may also benefit other respiratory conditions which often go unaddressed in Low and Middle Income Countries (LMICs) for want of context-appropriate technology designed for the limited oxygen resources available.

Artificial intelligence in health care: accountability and safety.

The prospect of patient harm caused by the decisions made by an artificial intelligence-based clinical tool is something to which current practices of accountability and safety worldwide have not yet adjusted. We focus on two aspects of clinical artificial intelligence used for decision-making: moral accountability for harm to patients; and safety assurance to protect patients against such harm. Artificial intelligence-based tools are challenging the standard clinical practices of assigning blame and assuring safety. Human clinicians and safety engineers have weaker control over the decisions reached by artificial intelligence systems and less knowledge and understanding of precisely how the artificial intelligence systems reach their decisions. We illustrate this analysis by applying it to an example of an artificial intelligence-based system developed for use in the treatment of sepsis. The paper ends with practical suggestions for ways forward to mitigate these concerns. We argue for a need to include artificial intelligence developers and systems safety engineers in our assessments of moral accountability for patient harm. Meanwhile, none of the actors in the model robustly fulfil the traditional conditions of moral accountability for the decisions of an artificial intelligence system. We should therefore update our conceptions of moral accountability in this context. We also need to move from a static to a dynamic model of assurance, accepting that considerations of safety are not fully resolvable during the design of the artificial intelligence system before the system has been deployed.

La perspective que les décisions prises par un outil clinique basé sur l'intelligence artificielle puissent porter préjudice aux patients est un concept dont les bonnes pratiques de responsabilité et de sécurité actuelles ne tiennent pas encore compte à travers le monde. Nous nous concentrons sur deux aspects qui caractérisent les décisions de l'intelligence artificielle à usage clinique : la responsabilité morale des préjudices aux patients, et la garantie de sécurité pour protéger les patients contre de tels préjudices. Les outils fondés sur l'intelligence artificielle remettent en cause les pratiques cliniques conventionnelles d'attribution des responsabilités et de garantie de la sécurité. Les décisions formulées par les systèmes d'intelligence artificielle sont de moins en moins soumises au contrôle des médecins et spécialistes de la sécurité, qui ne comprennent et ne maîtrisent pas toujours les subtilités régissant cette prise de décision. Nous illustrons notre analyse en l'appliquant à un exemple de système d'intelligence artificielle développé dans le cadre du traitement des infections. Le présent document se termine par une série de suggestions concrètes servant à identifier de nouveaux moyens de tempérer ces inquiétudes. Nous estimons qu'il est nécessaire d'inclure les développeurs à l'origine de l'intelligence artificielle ainsi que les spécialistes de la sécurité des systèmes dans notre évaluation de la responsabilité morale des préjudices causés aux patients. Car pour l'instant, aucun des acteurs impliqués dans le modèle ne remplit pleinement les conditions traditionnelles de responsabilité morale pour les décisions prises par un dispositif d'intelligence artificielle. Dans ce contexte, il est donc essentiel revoir notre conception de la responsabilité morale. Nous devons également passer d'un modèle de garantie statique à un modèle de garantie dynamique, et accepter que certains impératifs de sécurité ne puissent être entièrement résolus durant l'élaboration du système d'intelligence artificielle, avant sa mise en œuvre.

La perspectiva de que los pacientes sufran daños a causa de por las decisiones tomadas por un instrumento clínico de inteligencia artificial es un aspecto al que todavía no se han ajustado las prácticas actuales de responsabilidad y seguridad en todo el mundo. El presente documento se centra en dos aspectos de la inteligencia artificial clínica utilizada para la toma de decisiones: la responsabilidad moral por el daño causado a los pacientes y la garantía de seguridad para proteger a los pacientes contra dicho daño. Las herramientas de inteligencia artificial están desafiando las prácticas clínicas estándar de asignación de responsabilidades y de garantía de seguridad. Los médicos clínicos y los ingenieros de seguridad de las personas tienen menos control sobre las decisiones que adoptan por los sistemas de inteligencia artificial y menos conocimiento y comprensión de la forma precisa en que los sistemas de inteligencia artificial adoptan sus decisiones. Este análisis se ilustra aplicándolo a un ejemplo de un sistema de inteligencia artificial desarrollado para su uso en el tratamiento de la sepsis. El documento termina con sugerencias prácticas sobre las vías de acción para mitigar estas preocupaciones. Se sostiene la necesidad de incluir a los desarrolladores de inteligencia artificial y a los ingenieros de seguridad de sistemas en las evaluaciones de la responsabilidad moral por los daños causados a los pacientes. Entretanto, ninguno de los actores del modelo cumple sólidamente las condiciones tradicionales de responsabilidad moral por las decisiones de un sistema de inteligencia artificial. En consecuencia, se debería actualizar nuestra concepción de la responsabilidad moral en este contexto. También es preciso pasar de un modelo de garantía estático a uno dinámico, aceptando que las consideraciones de seguridad no se pueden resolver plenamente durante el diseño del sistema de inteligencia artificial antes de que el sistema sea implementado.

Development and piloting of a software tool to facilitate proactive hazard and risk analysis of Health Information Technology.

Health Information Technology is now widely promoted as a means for improving patient safety. The technology could also, under certain conditions, pose hazards to patient safety. However, current definitions of hazards are generic and hard to interpret, particularly for large Health Information Technology in complex socio-technical settings, that is, involving interacting clinical, organisational and technological factors. In this article, we develop a new conceptualisation for the notion of hazards and implement this conceptualisation in a tool-supported methodology called the Safety Modelling, Assurance and Reporting Toolset (SMART). The toolset aims to support clinicians and engineers in performing hazard identification and risk analysis and producing a safety case for Health Information Technology. Through a pilot study, we used and examined the toolset for developing a safety case for electronic prescribing in three acute hospitals. Our results demonstrate the ability of the approach to ensure that the safety evidence is generated based on explicit traceability between the clinical models and Health Information Technology functionality. They also highlight challenges concerning identifying hazards in a consistent way, with clear impact on patient safety in order to facilitate clinically meaningful risk analysis.