Brodbeck, Dominique
E-Mail-Adresse
Geburtsdatum
Suchergebnisse
Solving the explainable AI conundrum by bridging clinicians’ needs and developers’ goals
Explainable artificial intelligence (XAI) has emerged as a promising solution for addressing the implementation challenges of AI/ML in healthcare. However, little is known about how developers and clinicians interpret XAI and what conflicting goals and requirements they may have. This paper presents the findings of a longitudinal multi-method study involving 112 developers and clinicians co-designing an XAI solution for a clinical decision support system. Our study identifies three key differences between developer and clinician mental models of XAI, including opposing goals (model interpretability vs. clinical plausibility), different sources of truth (data vs. patient), and the role of exploring new vs. exploiting old knowledge. Based on our findings, we propose design solutions that can help address the XAI conundrum in healthcare, including the use of causal inference models, personalized explanations, and ambidexterity between exploration and exploitation mindsets. Our study highlights the importance of considering the perspectives of both developers and clinicians in the design of XAI systems and provides practical recommendations for improving the effectiveness and usability of XAI in healthcare.
Cloud-based three-dimensional pattern analysis and classification of proximal humeral fractures – A feasibility study
For the complex clinical issue of treatment decision for proximal humeral fractures, dedicated software based on three-dimensional (3D) computer tomography (CT) models would potentially allow for a more accurate fracture classification and help to plan the surgical strategy needed to reduce the fracture in the operating theatre. The aim of this study was to elaborate the feasibility of implementation of such software using state-of-the-art cloud technology to enable access to its functionalities in a distributed manner. Feasibility was studied by implementation of a prototype application, which was tested in a usability study with five biomedical engineers. Implementation of a cloud-based solution was feasible using state-of-the-art technology under application of a specific software architectural approach allowing to distribute computational load between client and server. Mean System Usability Scale (SUS) Score for the developed application was determined to be 63 (StDev 20.4). These results can be interpreted as a medium low usability with high standard deviation of the measured SUS score. We conclude that more test subjects should be included in future studies and the developed application should be evaluated with a representative user group such as orthopaedic shoulder surgeons in a clinical setting.
Backtrainer. Computer-aided therapy system with augmented feedback for the lower back
Low back pain is an important problem in industrialized countries. Two key factors limit the effectiveness of physiotherapy: low compliance of patients with repetitive movement exercises, and inadequate awareness of patients of their own posture. The Backtrainer system addresses these problems by real-time monitoring of the spine position, by providing a framework for most common physiotherapy exercises for the low back, and by providing feedback to patients in a motivating way. A minimal sensor configuration was identified as two inertial sensors that measure the orientation of the lower back at two points with three degrees of freedom. The software was designed as a flexible platform to experiment with different hardware, and with various feedback modalities. Basic exercises for two types of movements are provided: mobilizing and stabilizing. We developed visual feedback - abstract as well as in the form of a virtual reality game - and complemented the on-screen graphics with an ambient feedback device. The system was evaluated during five weeks in a rehabilitation clinic with 26 patients and 15 physiotherapists. Subjective satisfaction of subjects was good, and we interpret the results as encouraging indication for the adoption of such a therapy support system by both patients and therapists.
RWD-Cockpit. Application for quality assessment of real-world data
Digital technologies are transforming the health care system. A large part of information is generated as real-world data (RWD). Data from electronic health records and digital biomarkers have the potential to reveal associations between the benefits and adverse events of medicines, establish new patient-stratification principles, expose unknown disease correlations, and inform on preventive measures. The impact for health care payers and providers, the biopharmaceutical industry, and governments is massive in terms of health outcomes, quality of care, and cost. However, a framework to assess the preliminary quality of RWD is missing, thus hindering the conduct of population-based observational studies to support regulatory decision-making and real-world evidence.
The energy consumption of radiology. Energy- and cost-saving opportunities for CT and MRI operation
Background Awareness of energy efficiency has been rising in the industrial and residential sectors but only recently in the health care sector. Purpose To measure the energy consumption of modern CT and MRI scanners in a university hospital radiology department and to estimate energy- and cost-saving potential during clinical operation. Materials and Methods Three CT scanners, four MRI scanners, and cooling systems were equipped with kilowatt-hour energy measurement sensors (2-Hz sampling rate). Energy measurements, the scanners’ log files, and the radiology information system from the entire year 2015 were analyzed and segmented into scan modes, as follows: net scan (actual imaging), active (room time), idle, and system-on and system-off states (no standby mode was available). Per-examination and peak energy consumption were calculated. Results The aggregated energy consumption imaging 40 276 patients amounted to 614 825 kWh, dedicated cooling systems to 492 624 kWh, representing 44.5% of the combined consumption of 1 107 450 kWh (at a cost of U.S. $199 341). This is equivalent to the usage in a town of 852 people and constituted 4.0% of the total yearly energy consumption at the authors' hospital. Mean consumption per CT examination over 1 year was 1.2 kWh, with a mean energy cost (±standard deviation) of $0.22 ± 0.13. The total energy consumption of one CT scanner for 1 year was 26 226 kWh ($4721 in energy cost). The net consumption per CT examination over 1 year was 3580 kWh, which is comparable to the usage of a two-person household in Switzerland; however, idle state consumption was fourfold that of net consumption (14 289 kWh). Mean MRI consumption over 1 year was 19.9 kWh per examination, with a mean energy cost of $3.57 ± 0.96. The mean consumption for a year in the system-on state was 82 174 kWh per MRI examination and 134 037 kWh for total consumption, for an energy cost of $24 127. Conclusion CT and MRI energy consumption is substantial. Considerable energy- and cost-saving potential is present during nonproductive idle and system-off modes, and this realization could decrease total cost of ownership while increasing energy efficiency.
A mobile collaboration and decision support system for the medical emergency departement
A hospital emergency department is a complex work environment, where the availability of the right information at the right time is crucial for efficient and safe operation. The current technology in use for communication and information management is mostly based on telephones and stationary personal computers. Modern smartphones with their computational power, voice, image, and video capabilities have the potential to play a significant role in improving the flow of information in the emergency department. We developed a system that explicitly supports the work flows of an emergency department. In addition to mobile access to patient data and notifications about the availability of diagnostic findings, it provides the possibility to supply media captured on-site to the patient record, and directly supports the consultation process.
ICU Cockpit: a platform for collecting multimodal waveform data, AI-based computational disease modeling and real-time decision support in the intensive care unit
ICU Cockpit: a secure, fast, and scalable platform for collecting multimodal waveform data, online and historical data visualization, and online validation of algorithms in the intensive care unit. We present a network of software services that continuously stream waveforms from ICU beds to databases and a web-based user interface. Machine learning algorithms process the data streams and send outputs to the user interface. The architecture and capabilities of the platform are described. Since 2016, the platform has processed over 89 billion data points (N = 979 patients) from 200 signals (0.5–500 Hz) and laboratory analyses (once a day). We present an infrastructure-based framework for deploying and validating algorithms for critical care. The ICU Cockpit is a Big Data platform for critical care medicine, especially for multimodal waveform data. Uniquely, it allows algorithms to seamlessly integrate into the live data stream to produce clinical decision support and predictions in clinical practice.
A method and tool for strategic hospital planning
We developed a visualization tool and a methodology to support strategic planning of hospital service portfolios. Hospitals in Switzerland are reimbursed with a fixed fee per case. The fixed-fee model makes medical services comparable from a financial point of view. In order to take advantage of this model, the data that characterizes the medical services must be operationalized. The method that we developed, centers around a visual metaphor that provides the basis for strategic thinking. It is complemented by a visualization tool that allows visualization, analysis, and modification of service portfolios. Special features enable the tool to be used during live planning sessions. We describe the method, the tool, and its application in strategy workshops for infrastructure planning, reorganization, and resource optimization decisions.
Augmented feedback system to support physical therapy of non-specific low back pain
Low back pain is an important problem in industrialized countries. Two key factors limit the effectiveness of physiotherapy: low compliance of patients with repetitive movement exercises, and inadequate awareness of patients of their own posture. The Backtrainer system addresses these problems by real-time monitoring of the spine position, by providing a framework for most common physiotherapy exercises for the low back, and by providing feedback to patients in a motivating way. A minimal sensor configuration was identified as two inertial sensors that measure the orientation of the lower back at two points with three degrees of freedom. The software was designed as a flexible platform to experiment with different hardware, and with various feedback modalities. Basic exercises for two types of movements are provided: mobilizing and stabilizing. We developed visual feedback - abstract as well as in the form of a virtual reality game - and complemented the on-screen graphics with an ambient feedback device. The system was evaluated during five weeks in a rehabilitation clinic with 26 patients and 15 physiotherapists. Subjective satisfaction of subjects was good, and we interpret the results as encouraging indication for the adoption of such a therapy support system by both patients and therapists.