Dustin Dunsmuir

A Knowledge Authoring Tool for Clinical Decision Support

Anesthesiologists in the operating room are unable to constantly monitor all data generated by physiological monitors. They are further distracted by clinical and educational tasks. An expert system would ideally provide assistance to the anesthesiologist in this data-rich environment. Clinical monitoring expert systems have not been widely adopted, as traditional methods of knowledge encoding require both expert medical and programming skills, making knowledge acquisition difficult. A software application was developed for use as a knowledge authoring tool for physiological monitoring. This application enables clinicians to create knowledge rules without the need of a knowledge engineer or programmer. These rules are designed to provide clinical diagnosis, explanations and treatment advice for optimal patient care to the clinician in real time. By intelligently combining data from physiological monitors and demographical data sources the expert system can use these rules to assist in monitoring the patient. The knowledge authoring process is simplified by limiting connective relationships between rules. The application is designed to allow open collaboration between communities of clinicians to build a library of rules for clinical use. This design provides clinicians with a system for parameter surveillance and expert advice with a transparent pathway of reasoning. A usability evaluation demonstrated that anesthesiologists can rapidly develop useful rules for use in a predefined clinical scenario.

Development of mHealth applications for pre-eclampsia triage.

The development of mobile applications for the diagnosis and management of pregnant women with pre-eclampsia is described. These applications are designed for use by community-based health care providers (c-HCPs) in health facilities and during home visits to collect symptoms and perform clinical measurements (including pulse oximeter readings). The clinical data collected in women with pre-eclampsia are used as the inputs to a predictive model providing a risk score for the development of adverse outcomes. Based on this risk, the applications provide recommendations on treatment, referral, and reassessment. c-HCPs can access patient records across multiple visits, using multiple devices that are synchronized using a secure Research Electronic Data Capture server. A unique feature of these applications is the ability to measure oxygen saturation with a pulse oximeter connected to a smartphone (Phone Oximeter). The mobile health application development process, including challenges encountered and solutions are described.

Improving the Accuracy and Efficiency of Respiratory Rate Measurements in Children Using Mobile Devices

The recommended method for measuring respiratory rate (RR) is counting breaths for 60 s using a timer. This method is not efficient in a busy clinical setting. There is an urgent need for a robust, low-cost method that can help front-line health care workers to measure RR quickly and accurately. Our aim was to develop a more efficient RR assessment method. RR was estimated by measuring the median time interval between breaths obtained from tapping on the touch screen of a mobile device. The estimation was continuously validated by measuring consistency (% deviation from the median) of each interval. Data from 30 subjects estimating RR from 10 standard videos with a mobile phone application were collected. A sensitivity analysis and an optimization experiment were performed to verify that a RR could be obtained in less than 60 s; that the accuracy improves when more taps are included into the calculation; and that accuracy improves when inconsistent taps are excluded. The sensitivity analysis showed that excluding inconsistent tapping and increasing the number of tap intervals improved the RR estimation. Efficiency (time to complete measurement) was significantly improved compared to traditional methods that require counting for 60 s. There was a trade-off between accuracy and efficiency. The most balanced optimization result provided a mean efficiency of 9.9 s and a normalized root mean square error of 5.6%, corresponding to 2.2 breaths/min at a respiratory rate of 40 breaths/min. The obtained 6-fold increase in mean efficiency combined with a clinically acceptable error makes this approach a viable solution for further clinical testing. The sensitivity analysis illustrating the trade-off between accuracy and efficiency will be a useful tool to define a target product profile for any novel RR estimation device.

Usability and Feasibility of PIERS on the Move: An mHealth App for Pre-Eclampsia Triage

Background Pre-eclampsia is one of the leading causes of maternal death and morbidity in low-resource countries due to delays in case identification and a shortage of health workers trained to manage the disorder. Pre-eclampsia Integrated Estimate of RiSk (PIERS) on the Move (PotM) is a low cost, easy-to-use, mobile health (mHealth) platform that has been created to aid health workers in making decisions around the management of hypertensive pregnant women. PotM combines two previously successful innovations into a mHealth app: the miniPIERS risk assessment model and the Phone Oximeter. Objective The aim of this study was to assess the usability of PotM (with mid-level health workers) for iteratively refining the system. Methods Development of the PotM user interface involved usability testing with target end-users in South Africa. Users were asked to complete clinical scenario tasks, speaking aloud to give feedback on the interface and then complete a questionnaire. The tool was then evaluated in a pilot clinical evaluation in Tygerberg Hospital, Cape Town. Results After ethical approval and informed consent, 37 nurses and midwives evaluated the tool. During Study 1, major issues in the functionality of the touch-screen keyboard and date scroll wheels were identified (total errors n=212); during Study 2 major improvements in navigation of the app were suggested (total errors n=144). Overall, users felt the app was usable using the Computer Systems Usability Questionnaire; median (range) values for Study 1 = 2 (1-6) and Study 2 = 1 (1-7). To demonstrate feasibility, PotM was used by one research nurse for the pilot clinical study. In total, more than 500 evaluations were performed on more than 200 patients. The median (interquartile range) time to complete an evaluation was 4 min 55 sec (3 min 25 sec to 6 min 56 sec). Conclusions By including target end-users in the design and evaluation of PotM, we have developed an app that can be easily integrated into health care settings in low- and middle-income countries. Usability problems were often related to mobile phone features (eg, scroll wheels, touch screen use). Larger scale evaluation of the clinical impact of this tool is underway.

Assessing the Incremental Value of Blood Oxygen Saturation (SpO2) in the miniPIERS (Pre-eclampsia Integrated Estimate of RiSk) Risk Prediction Model

OBJECTIVE To assess the incremental value of blood oxygen saturation (SpO(2)) as a predictor in the miniPIERS model, a risk prediction model for adverse outcomes among women with a diagnosis of hypertensive disorder of pregnancy (HDP) in low-resourced settings. METHODS Using data from a prospective cohort including 852 women admitted to hospital for a HDP, the association between SpO(2) and adverse maternal outcome was assessed using logistic regression. The miniPIERS model was recalibrated and extended to include SpO(2). The incremental value of adding SpO(2) to the model was measured using a net reclassification index (NRI), sensitivity, specificity, positive and negative predictive values, and likelihood ratios. RESULTS SpO(2) of < 93% was associated with a 30-fold increase in risk (95% CI 14 to 68) of adverse maternal outcome compared to women with SpO(2) > 97%. After recalibration and extension, the miniPIERS model including SpO(2) (vs. not including SpO(2)) had improved sensitivity (32.8% vs. 49.6%) at the cost of minimally decreased specificity (91.5% vs. 96.2%) with a NRI of 0.122. CONCLUSION SpO(2) is a significant independent predictor of risk in women with a HDP. Adding SpO(2) to the miniPIERS model improved the models ability to correctly identify high-risk patients who would benefit most from interventions.

Experience report: functional programming of mHealth applications

A modular framework for the development of medical applications that promotes deterministic, robust and correct code is presented. The system is based on the portable Gambit Scheme programming language and provides a flexible cross-platform environment for developing graphical applications on mobile devices as well as medical instrumentation interfaces running on embedded platforms. Real world applications of this framework for mobile diagnostics, telemonitoring and automated drug infusions are reported. The source code for the core framework is open source and available at: https://github.com/part-cw/lambdanative.

A smartphone version of the Faces Pain Scale-Revised and the Color Analog Scale for postoperative pain assessment in children.

Effective pain assessment is essential during postoperative recovery. Extensive validation data are published supporting the Faces Pain Scale‐Revised (FPS‐R) and the Color Analog Scale (CAS) in children. Panda is a smartphone‐based application containing electronic versions of these scales.

The PAediatric Risk Assessment (PARA) Mobile App to Reduce Postdischarge Child Mortality: Design, Usability, and Feasibility for Health Care Workers in Uganda

Background Postdischarge death in children is increasingly being recognized as a major contributor to overall child mortality. The PAediatric Risk Assessment (PARA) app is an mHealth tool developed to aid health care workers in resource-limited settings such as Sub-Saharan Africa to identify pediatric patients at high risk of both in-hospital and postdischarge mortality. The intended users of the PARA app are health care workers (ie, nurses, doctors, and clinical officers) with varying levels of education and technological exposure, making testing of this clinical tool critical to successful implementation. Objective Our aim was to summarize the usability evaluation of the PARA app among target users, which consists of assessing the ease of use, functionality, and navigation of the interfaces and then iteratively improving the design of this clinical tool. Methods Health care workers (N=30) were recruited to participate at Mbarara Regional Referral Hospital and Holy Innocents Children’s Hospital in Mbarara, Southwestern Uganda. This usability study was conducted in two phases to allow for iterative improvement and testing of the interfaces. The PARA app was evaluated using quantitative and qualitative measures, which were compared between Phases 1 and 2 of the study. Participants were given two patient scenarios that listed hypothetical information (ie, demographic, social, and clinical data) to be entered into the app and to determine the patient’s risk of in-hospital and postdischarge mortality. Time-to-completion and user errors were recorded for each participant while using the app. A modified computer system usability questionnaire was utilized at the end of each session to elicit user satisfaction with the PARA app and obtain suggestions for future improvements. Results The average time to complete the PARA app decreased by 30% from Phase 1 to Phase 2, following user feedback and modifications. Participants spent the longest amount of time on the oxygen saturation interface, but modifications following Phase 1 cut this time by half. The average time-to-completion (during Phase 2) for doctors/medical students was 3 minutes 56 seconds. All participants agreed they would use the PARA app if available at their health facility. Given a high PARA risk score, participants suggested several interventions that would be appropriate for the sociocultural context in southwestern Uganda, which involved strengthening discharge and referral procedures within the current health care system. Conclusions Through feedback and modifications made during this usability study, the PARA app was developed into a user-friendly app, encompassing user expectations and culturally intuitive interfaces for users with a range of technological exposure. Doctors and medical students had shorter task completion times, though all participants reported the usefulness of this tool to improve postdischarge outcomes.

The Phone Oximeter for Mobile Spot-Check

8 Measuring adeQuacy of analgesia with cardiorespiratory coherence Chris Brouse, Walter Karlen, Guy Dumont, Dorothy Myers, Erin Cooke, Jonathan Stinson, Joanne Lim, J. Mark Ansermino The University of British Columbia, Vancouver, Canada Introduction: An automated nociception monitor would be very useful in general anesthesia, providing anesthesiologists with real-time feedback about the adequacy of analgesia. We have developed an algorithm to measure nociception using respiratory sinus arrhythmia (RSA) in heart rate variability (HRV). We have previously shown that this algorithm can detect patient movement (strongly nociceptive events) during general anesthesia 1. We will now attempt to determine if the algorithm responds to boluses of anesthetic drugs (strongly anti-nociceptive events). Method: Algorithm: The algorithm estimates cardiorespiratory coherence, which is the strength of linear coupling between HR and respiration (one measure of RSA). It measures and combines the spectral power in both signals using wavelet analysis. Coherence is dimensionless, and ranges from 0 (no coherence, strong nociception) to 1 (perfect coherence, no nociception). Data Analysis: Following ethics approval and informed consent, 60 drug bolus events (excluding induction of anesthesia) were recorded in 47 pediatric patients receiving general anesthesia during dental surgery. In post hoc analysis, coherence was averaged over the 60s immediately preceding the bolus dose of drug (nociceptive period). The bolus was given 30s to take effect, after which the coherence was averaged over the following 60s (anti-nociceptive period). The change in average coherence between the two periods was calculated. The change in average HR was also calculated, for comparison. Results: Coherence increased by an average of 0.14 (32%) in response to the bolus dose of anesthetic drug. HR decreased by an average of 4.1 beats/min (3.9%). Discussion: Cardiorespiratory coherence responded much more strongly to the anesthetic boluses than did HR alone. This result, combined with previous work showing that coherence is low during periods of nociception [1], demonstrates that cardiorespiratory coherence can be used to measure the adequacy of analgesia during general anesthesia. We are currently adapting the algorithm so that it can be used in real-time.

A vibro-tactile display for clinical monitoring: real-time evaluation.

BACKGROUND: Vibro-tactile displays use human skin to convey information from physiological monitors to anesthesiologists, providing cues about changes in the status of the patient. In this investigation, we evaluated, in a real-time clinical environment, the usability and wearability of a novel vibro-tactile display belt recently developed by our group, and determined its accuracy in identifying events when used by anesthesiologists. METHODS: A prospective observational study design was used. During routine anesthesia, a standard physiological monitor was connected to a software tool that used algorithms to automatically identify changing trends in mean noninvasive arterial blood pressure, expired minute ventilation, peak airway pressure, and end-tidal carbon dioxide partial pressure. The software was wirelessly interfaced to a vibro-tactile belt worn by the anesthesiologist. Each physiological variable was mapped to 1 of 4 tactor locations within the belt. The direction (increase/decrease) and 2 levels of change (small/large) were encoded in the stimulation patterns. A training session was completed by each anesthesiologist. The system was activated in real-time during anesthesia alongside routine physiological monitors. When the algorithms detected changes in the patient, the belt vibrated at the appropriate location with the pattern corresponding to the level and direction of change. Using a touch screen monitor the anesthesiologist was to enter the vibro-tactile message by first identifying the variable, then identifying the level and direction of change. Usability and wearability questionnaires were to be completed. The percentage of correct identification of the physiological trend, the direction of change, and the level of change were primary outcome variables. The mean usability score and wearability results were secondary outcome variables. We hypothesized that anesthesiologists would correctly identify the events communicated to them through the vibro-tactile belt 90% of the time, and that anesthesiologists would find the vibro-tactile belt usable and wearable. RESULTS: Seventeen anesthesiologists evaluated the display during 57 cases. The belt was operational for a mean (SD) duration of 75 (41) minutes per case. Seven cases were excluded from analysis because of technical failures. Eighty-one percent (confidence interval [CI], 77% to 84%) of all stimuli were decoded. The physiological trend, the direction of change, and the level of change were correctly identified for 97.7% (CI 96%–99%), 94.9% (CI 92%–97%), and 93.5% of these stimuli (CI, 91%–96%), respectively. Fourteen anesthesiologists completed the usability and wearability questionnaires. The mean usability score was 4.8 of a maximum usability score of 7. CONCLUSIONS: Anesthesiologists found a vibro-tactile belt to be wearable and usable and could accurately decode vibro-tactile messages in a real-time clinical environment.