Personalized, intuitive & visual QT-prolongation monitoring using patient-specific QTc threshold with pseudo-coloring and explainable AI.

BACKGROUND: Drug-induced QT-prolongation increases the risk of TdP arrhythmia attacks and sudden cardiac death. However, measuring the QT-interval and determining a precise cut-off QT/QTc value that could put a patient at risk of TdP is challenging and influenced by many factors including female sex, drug-free baseline, age, genetic predisposition, and bradycardia. OBJECTIVES: This paper presents a novel approach for intuitively and visually monitoring QT-prolongation showing a potential risk of TdP, which can be adjusted according to patient-specific risk factors, using a pseudo-coloring technique and explainable artificial intelligence (AI). METHODS: We extended the development and evaluation of an explainable AI-based technique- visualized using pseudo-color on the ECG signal, thus intuitively 'explaining' how its decision was made -to detect QT-prolongation showing a potential risk of TdP according to a cut-off personalized QTc value (using Bazett's ∆QTc > 60 ms relative to drug-free baseline and Bazett's QTc > 500 ms as examples), and validated its performance using a large number of ECGs (n = 5050), acquired from a clinical trial assessing the effects of four known QT-prolonging drugs versus placebo on healthy subjects. We compared this new personalized approach to our previous study that used a more general approach using the QT-nomogram. RESULTS AND CONCLUSIONS: The explainable AI-based algorithm can accurately detect QT-prolongation when adjusted to a personalized patient-specific cut-off QTc value showing a potential risk of TdP. Using ∆QTc > 60 ms relative to drug-free baseline and QTc > 500 ms as examples, the algorithm yielded a sensitivity of 0.95 and 0.79, and a specificity of 0.95 and 0.98, respectively. We found that adjusting pseudo-coloring according to Bazett's ∆QTc > 60 ms relative to a drug-free baseline personalized to each patient provides better sensitivity than using Bazett's QTc > 500 ms, which could underestimate a potentially clinically significant QT-prolongation with bradycardia.

Presentation of laboratory test results in patient portals: influence of interface design on risk interpretation and visual search behaviour.

BACKGROUND: Patient portals are considered valuable instruments for self-management of long term conditions, however, there are concerns over how patients might interpret and act on the clinical information they access. We hypothesized that visual cues improve patients' abilities to correctly interpret laboratory test results presented through patient portals. We also assessed, by applying eye-tracking methods, the relationship between risk interpretation and visual search behaviour. METHODS: We conducted a controlled study with 20 kidney transplant patients. Participants viewed three different graphical presentations in each of low, medium, and high risk clinical scenarios composed of results for 28 laboratory tests. After viewing each clinical scenario, patients were asked how they would have acted in real life if the results were their own, as a proxy of their risk interpretation. They could choose between: 1) Calling their doctor immediately (high interpreted risk); 2) Trying to arrange an appointment within the next 4 weeks (medium interpreted risk); 3) Waiting for the next appointment in 3 months (low interpreted risk). For each presentation, we assessed accuracy of patients' risk interpretation, and employed eye tracking to assess and compare visual search behaviour. RESULTS: Misinterpretation of risk was common, with 65% of participants underestimating the need for action across all presentations at least once. Participants found it particularly difficult to interpret medium risk clinical scenarios. Participants who consistently understood when action was needed showed a higher visual search efficiency, suggesting a better strategy to cope with information overload that helped them to focus on the laboratory tests most relevant to their condition. CONCLUSIONS: This study confirms patients' difficulties in interpreting laboratories test results, with many patients underestimating the need for action, even when abnormal values were highlighted or grouped together. Our findings raise patient safety concerns and may limit the potential of patient portals to actively involve patients in their own healthcare.

An explainable algorithm for detecting drug-induced QT-prolongation at risk of torsades de pointes (TdP) regardless of heart rate and T-wave morphology.

Torsade de points (TdP), a life-threatening arrhythmia that can increase the risk of sudden cardiac death, is associated with drug-induced QT-interval prolongation on the electrocardiogram (ECG). While many modern ECG machines provide automated measurements of the QT-interval, these automated QT values are usually correct only for a noise-free normal sinus rhythm, in which the T-wave morphology is well defined. As QT-prolonging drugs often affect the morphology of the T-wave, automated QT measurements taken under these circumstances are easily invalidated. An additional challenge is that the QT-value at risk of TdP varies with heart rate, with the slower the heart rate, the greater the risk of TdP. This paper presents an explainable algorithm that uses an understanding of human visual perception and expert ECG interpretation to automate the detection of QT-prolongation at risk of TdP regardless of heart rate and T-wave morphology. It was tested on a large number of ECGs (n=5050) with variable QT-intervals at varying heart rates, acquired from a clinical trial that assessed the effect of four known QT-prolonging drugs versus placebo on healthy subjects. The algorithm yielded a balanced accuracy of 0.97, sensitivity of 0.94, specificity of 0.99, F1-score of 0.88, ROC (AUC) of 0.98, precision-recall (AUC) of 0.88, and Matthews correlation coefficient (MCC) of 0.88. The results indicate that a prolonged ventricular repolarisation area can be a significant risk predictor of TdP, and detection of this is potentially easier and more reliable to automate than measuring the QT-interval distance directly. The proposed algorithm can be visualised using pseudo-colour on the ECG trace, thus intuitively 'explaining' how its decision was made, which results of a focus group show may help people to self-monitor QT-prolongation, as well as ensuring clinicians can validate its results.

Pseudo-colouring an ECG enables lay people to detect QT-interval prolongation regardless of heart rate.

Drug-induced long QT syndrome (diLQTS), characterized by a prolongation of the QT-interval on the electrocardiogram (ECG), is a serious adverse drug reaction that can cause the life-threatening arrhythmia Torsade de Points (TdP). Self-monitoring for diLQTS could therefore save lives, but detecting it on the ECG is difficult, particularly at high and low heart rates. In this paper, we evaluate whether using a pseudo-colouring visualisation technique and changing the coordinate system (Cartesian vs. Polar) can support lay people in identifying QT-prolongation at varying heart rates. Four visualisation techniques were evaluated using a counterbalanced repeated measures design including Cartesian no-colouring, Cartesian pseudo-colouring, Polar no-colouring and Polar pseudo-colouring. We used a multi-reader, multi-case (MRMC) receiver operating characteristic (ROC) study design within a psychophysical paradigm, along with eye-tracking technology. Forty-three lay participants read forty ECGs (TdP risk n = 20, no risk n = 20), classifying each QT-interval as normal/abnormal, and rating their confidence on a 6-point scale. The results show that introducing pseudo-colouring to the ECG significantly increased accurate detection of QT-interval prolongation regardless of heart rate, T-wave morphology and coordinate system. Pseudo-colour also helped to reduce reaction times and increased satisfaction when reading the ECGs. Eye movement analysis indicated that pseudo-colour helped to focus visual attention on the areas of the ECG crucial to detecting QT-prolongation. The study indicates that pseudo-colouring enables lay people to visually identify drug-induced QT-prolongation regardless of heart rate, with implications for the more rapid identification and management of diLQTS.

Investigating the effect of clinical history before electrocardiogram interpretation on the visual behavior and interpretation accuracy of clinicians.

We examine the impact of the presentation of a patient's clinical history on subsequent visual appraisal and interpretation accuracy of electrocardiograms (ECGs). Healthcare-practitioners (N = 31) skilled in 12-lead ECG interpretation took part in a repeated-measures experiment with counterbalancing viewing 9 ECGs on a computer screen in two separate conditions: with/without an associated patient-history. A Hellinger-distance calculation was applied using a permutation test to eye-movement transitions at two granularity levels: between the ECG leads, and between smaller grid-cells, whose size was determined via data-driven clustering of the fixation points. Findings indicate that presentation of clinical-history does affect accuracy of interpretation in one ECG. Visual-behavior differed as a function of both history presentation and accuracy when considering transitions between the data-driven grid units (using a fine granularity, and able to show attention to parts of the waveform). Differences in visual-behavior at waveform level demonstrate an influence of patient-history and expertise that are not detected at the lead level. Visual-behaviour differs according to whether a patient-history is presented, and whether a clinician provides an accurate interpretation. This difference is evident in how the waveform itself is viewed, and is less present at the coarse granularity of visual transitions between leads. To understand how clinicians interpret ECGs, and potentially other medical images, visual transitions should be considered at a fine level of granularity, determined in a data-driven fashion.

Can laypeople identify a drug-induced QT interval prolongation? A psychophysical and eye-tracking experiment examining the ability of nonexperts to interpret an ECG.

OBJECTIVE: The study sought to quantify a layperson's ability to detect drug-induced QT interval prolongation on an electrocardiogram (ECG) and determine whether the presentation of the trace affects such detection. MATERIALS AND METHODS: Thirty layperson participants took part in a psychophysical and eye-tracking experiment. Following training, participants completed 21 experimental trials, in which each trial consisted of 2 ECGs (a baseline and a comparison stimulus, both with a heart rate of 60 beats/min). The experiment used a 1 alternative forced-choice paradigm, in which participants indicated whether or not they perceived a difference in the QT interval length between the 2 ECGs. The ECG trace was presented in 3 ways: a single complex with the signals aligned by the R wave, a single complex without alignment, and a 10-second rhythm strip. Performance was analyzed using the psychometric function to estimate the just noticeable difference threshold, along with eye-tracking metrics. RESULTS: The just noticeable difference 50% and 75% thresholds were 30 and 88 ms, respectively, showing that the majority of laypeople were able to detect a clinically significant QT-prolongation at a low normal heart rate. Eye movement data indicated that people were more likely to appraise the rhythm strip stimulus systematically and accurately. CONCLUSIONS: People can quickly be trained to self-monitor, which may help with more rapid identification of drug-induced long QT syndrome and prevent the development of life-threatening complications. The rhythm strip is a better form of presentation than a single complex, as it is less likely to be misinterpreted due to artifacts in the signal.

Modelling the interactive behaviour of users with a medication safety dashboard in a primary care setting.

OBJECTIVE: To characterise the use of an electronic medication safety dashboard by exploring and contrasting interactions from primary users (i.e. pharmacists) who were leading the intervention and secondary users (i.e. non-pharmacist staff) who used the dashboard to engage in safe prescribing practices. MATERIALS AND METHODS: We conducted a 10-month observational study in which 35 health professionals used an instrumented medication safety dashboard for audit and feedback purposes in clinical practice as part of a wider intervention study. We modelled user interaction by computing features representing exploration and dwell time through user interface events that were logged on a remote database. We applied supervised learning algorithms to classify primary against secondary users. RESULTS: We observed values for accuracy above 0.8, indicating that 80% of the time we were able to distinguish a primary user from a secondary user. In particular, the Multilayer Perceptron (MLP) yielded the highest values of precision (0.88), recall (0.86) and F-measure (0.86). The behaviour of primary users was distinctive in that they spent less time between mouse clicks (lower dwell time) on the screens showing the overview of the practice and trends. Secondary users exhibited a higher dwell time and more visual search activity (higher exploration) on the screens displaying patients at risk and visualisations. DISCUSSION AND CONCLUSION: We were able to distinguish the interactive behaviour of primary and secondary users of a medication safety dashboard in primary care using timestamped mouse events. Primary users were more competent on population health monitoring activities, while secondary users struggled on activities involving a detailed breakdown of the safety of patients. Informed by these findings, we propose workflows that group these activities and adaptive nudges to increase user engagement.

Using simultaneous scanpath visualization to investigate the relationship between accuracy and eye movement during medical image interpretation.

In this paper, we explore how a number of novel methods for visualizing and analyzing differences in eye-tracking data, including scanpath length, Levenshtein distance, and visual transition frequency, can help to elucidate the methods clinicians use for interpreting 12-lead electrocardiograms (ECGs). Visualizing the differences between multiple participants' scanpaths simultaneously allowed us to answer questions including: do clinicians fixate randomly on the ECG, or do they apply a systematic approach?; is there a relationship between interpretation accuracy and visual behavior? Results indicate that practitioners have very different visual search strategies. Clinicians who incorrectly interpret the image have greater scanpath variability than those who correctly interpret it, indicating that differences between practitioners in terms of accuracy are reflected in different eye-movement behaviors. The variation across practitioners is likely to be the result of differential training, clinical role and expertise.

Britain Breathing: using the experience sampling method to collect the seasonal allergy symptoms of a country.

Objective: Allergies are increasing, but the reasons for this are unclear. Although environmental factors are thought to be important, there is a lack of data on how they contribute to symptom development. To understand this relationship better, we need accurate data about both symptoms and environmental factors. Our objective here is to ascertain whether experience sampling is a reliable approach for collecting allergy symptom data in the general population, allowing us to map symptoms and understand etiology. Materials and Methods: We conducted a 32-week cross-sectional study where individuals reported their seasonal allergy symptoms and severity via a mobile application. Symptom geographical location and timestamp were also collected automatically. Results: The experience sampling method reliably infers the incidence of seasonal allergies as indicated by the strong correlation (r = 0.93, P < .003) between the reported lack of wellness and the number of antihistamines prescribed by General Practitioners. Discussion and Conclusion: The project has resulted in the first dataset to map allergy symptoms over time and place and reveals periods of peak hay fever symptoms in the UK.

The influence of patient portals on users' decision making is insufficiently investigated: A systematic methodological review.

BACKGROUND: Patient portals are considered valuable conduits for supporting patients' self-management. However, it is unknown why they often fail to impact on health care processes and outcomes. This may be due to a scarcity of robust studies focusing on the steps that are required to induce improvement: users need to effectively interact with the portal (step 1) in order to receive information (step 2), which might influence their decision-making (step 3). We aimed to explore this potential knowledge gap by investigating to what extent each step has been investigated for patient portals, and explore the methodological approaches used. METHODS: We performed a systematic literature review using Coiera's information value chain as a guiding theoretical framework. We searched MEDLINE and Scopus by combining terms related to patient portals and evaluation methodologies. Two reviewers selected relevant papers through duplicate screening, and one extracted data from the included papers. RESULTS: We included 115 articles. The large majority (n = 104) evaluated aspects related to interaction with patient portals (step 1). Usage was most often assessed (n = 61), mainly by analysing system interaction data (n = 50), with most authors considering participants as active users if they logged in at least once. Overall usability (n = 57) was commonly assessed through non-validated questionnaires (n = 44). Step 2 (information received) was investigated in 58 studies, primarily by analysing interaction data to evaluate usage of specific system functionalities (n = 34). Eleven studies explicitly assessed the influence of patient portals on patients' and clinicians' decisions (step 3). CONCLUSIONS: Whereas interaction with patient portals has been extensively studied, their influence on users' decision-making remains under-investigated. Methodological approaches to evaluating usage and usability of portals showed room for improvement. To unlock the potential of patient portals, more (robust) research should focus on better understanding the complex process of how portals lead to improved health and care.

Does descriptive text change how people look at art? A novel analysis of eye - movements using data -driven Units of Interest.

Does reading a description of an artwork affect how a person subsequently views it? In a controlled study, we show that in most cases, textual description does not influence how people subsequently view paintings, contrary to participants' self-report that they believed it did. To examine whether the description affected transition behaviour, we devised a novel analysis method that systematically determines Units of Interest (UOIs), and calculates transitions between these, to quantify the effect of an external factor (a descriptive text) on the viewing pattern of a naturalistic stimulus (a painting). UOIs are defined using a grid-based system, where the cell-size is determined by a clustering algorithm (DBSCAN). The Hellinger distance is computed for the distance between two Markov chains using a permutation test, constructed from the transition matrices (visual shifts between UOIs) of the two groups for each painting. Results show that the description does not affect the way in which people transition between UOIs for all but one of the paintings -- an abstract work -- suggesting that description may play more of a role in determining transition behaviour when a lack of semantic cues means it is unclear how the painting should be interpreted. The contribution is twofold: to the domain of art/curation, we provide evidence that descriptive texts do not effect how people view paintings, with the possible exception of some abstract paintings; to the domain of eye-movement research, we provide a method with the potential to answer questions across multiple research areas, where the goal is to determine whether a particular factor or condition consistently affects viewing behaviour of naturalistic stimuli.

Patient Portal Adoption Rates: A Systematic Literature Review and Meta-Analysis.

Despite the increasing availability of online patient portals that provide access to electronic health records, little is known about their adoption by patients. We systematically reviewed the literature to investigate adoption of patient portals across studies. We searched MEDLINE and Scopus to identify relevant papers. We included 40 studies: 24 were controlled experiments, with prospective data collection in an actively recruited population; 16 were real-world experiments, with adoption being evaluated retrospectively after system deployment in clinical practice. Our meta-analysis showed an overall mean adoption rate of 52% (95% Confidence Interval [CI], 42 to 62%). Rates differed markedly between study types: controlled experiments yielded a mean adoption rate of 71% (95% CI 64 to 79%), compared to 23% (95% CI, 13 to 33%) in real-world experiments. This difference was confirmed in a meta-regression analysis of the influence of study characteristics on adoption rates. Our findings suggest that adoption rates reported in controlled studies do not reflect those in everyday clinical practice. Until we understand how to effectively increase adoption, patient portals are unlikely to consistently lead to improvements in care processes and health outcomes.

Exploring the Relationship Between Eye Movements and Electrocardiogram Interpretation Accuracy.

Interpretation of electrocardiograms (ECGs) is a complex task involving visual inspection. This paper aims to improve understanding of how practitioners perceive ECGs, and determine whether visual behaviour can indicate differences in interpretation accuracy. A group of healthcare practitioners (n = 31) who interpret ECGs as part of their clinical role were shown 11 commonly encountered ECGs on a computer screen. The participants' eye movement data were recorded as they viewed the ECGs and attempted interpretation. The Jensen-Shannon distance was computed for the distance between two Markov chains, constructed from the transition matrices (visual shifts from and to ECG leads) of the correct and incorrect interpretation groups for each ECG. A permutation test was then used to compare this distance against 10,000 randomly shuffled groups made up of the same participants. The results demonstrated a statistically significant (α 0.05) result in 5 of the 11 stimuli demonstrating that the gaze shift between the ECG leads is different between the groups making correct and incorrect interpretations and therefore a factor in interpretation accuracy. The results shed further light on the relationship between visual behaviour and ECG interpretation accuracy, providing information that can be used to improve both human and automated interpretation approaches.

Tool independence for the Web Accessibility Quantitative Metric.

The Web Accessibility Quantitative Metric (WAQM) aims at accurately measuring the accessibility of web pages. One of the main features of WAQM among others is that it is evaluation tool independent for ranking and accessibility monitoring scenarios. This article proposes a method to attain evaluation tool independence for all foreseeable scenarios. After demonstrating that homepages have a more similar error profile than any other web page in a given web site, 15 homepages were measured with 10,000 different values of WAQM parameters using EvalAccess and LIFT, two automatic evaluation tools for accessibility. A similar procedure was followed with random pages and with several test files obtaining several tuples that minimise the difference between both tools. One thousand four hundred forty-nine web pages from 15 web sites were measured with these tuples and those values that minimised the difference between the tools were selected. Once the WAQM was tuned, the accessibility of 15 web sites was measured with two metrics for web sites, concluding that even if similar values can be produced, obtaining the same scores is undesirable since evaluation tools behave in a different way.