DIGIPREDICT: physiological, behavioural and environmental predictors of asthma attacks-a prospective observational study using digital markers and artificial intelligence-study protocol.

INTRODUCTION: Asthma attacks are a leading cause of morbidity and mortality but are preventable in most if detected and treated promptly. However, the changes that occur physiologically and behaviourally in the days and weeks preceding an attack are not always recognised, highlighting a potential role for technology. The aim of this study 'DIGIPREDICT' is to identify early digital markers of asthma attacks using sensors embedded in smart devices including watches and inhalers, and leverage health and environmental datasets and artificial intelligence, to develop a risk prediction model to provide an early, personalised warning of asthma attacks. METHODS AND ANALYSIS: A prospective sample of 300 people, 12 years or older, with a history of a moderate or severe asthma attack in the last 12 months will be recruited in New Zealand. Each participant will be given a smart watch (to assess physiological measures such as heart and respiratory rate), peak flow meter, smart inhaler (to assess adherence and inhalation) and a cough monitoring application to use regularly over 6 months with fortnightly questionnaires on asthma control and well-being. Data on sociodemographics, asthma control, lung function, dietary intake, medical history and technology acceptance will be collected at baseline and at 6 months. Asthma attacks will be measured by self-report and confirmed with clinical records. The collected data, along with environmental data on weather and air quality, will be analysed using machine learning to develop a risk prediction model for asthma attacks. ETHICS AND DISSEMINATION: Ethical approval has been obtained from the New Zealand Health and Disability Ethics Committee (2023 FULL 13541). Enrolment began in August 2023. Results will be presented at local, national and international meetings, including dissemination via community groups, and submission for publication to peer-reviewed journals. TRIAL REGISTRATION NUMBER: Australian New Zealand Clinical Trials Registry ACTRN12623000764639; Australian New Zealand Clinical Trials Registry.

LSD increases sleep duration the night after microdosing.

Microdosing psychedelic drugs at a level below the threshold to induce hallucinations is an increasingly common lifestyle practice. However, the effects of microdosing on sleep have not been previously reported. Here, we report results from a Phase 1 randomized controlled trial in which 80 healthy adult male volunteers received a 6-week course of either LSD (10 µg) or placebo with doses self-administered every third day. Participants used a commercially available sleep/activity tracker for the duration of the trial. Data from 3231 nights of sleep showed that on the night after microdosing, participants in the LSD group slept an extra 24.3 min per night (95% Confidence Interval 10.3-38.3 min) compared to placebo-with no reductions of sleep observed on the dosing day itself. There were no changes in the proportion of time spent in various sleep stages or in participant physical activity. These results show a clear modification of the physiological sleep requirements in healthy male volunteers who microdose LSD. The clear, clinically significant changes in objective measurements of sleep observed are difficult to explain as a placebo effect. Trial registration: Australian New Zealand Clinical Trials Registry: A randomized, double-blind, placebo-controlled trial of repeated microdoses of lysergic acid diethylamide (LSD) in healthy volunteers; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=381476 ; ACTRN12621000436875.

An open-label pilot trial assessing tolerability and feasibility of LSD microdosing in patients with major depressive disorder (LSDDEP1).

BACKGROUND: Globally, an estimated 260 million people suffer from depression [1], and there is a clear need for the development of new, alternative antidepressant therapies. In light of problems with the tolerability and efficacy of available treatments [2], a global trend is emerging for patients to self-treat depression with microdoses of psychedelic drugs such as lysergic acid diethylamide (LSD) and psilocybin [3]. Beyond anecdotal reports from those who self-medicate in this way, few clinical trials have evaluated this practice. In our recently published phase 1 study in healthy volunteers [4], we determined that LSD microdosing was relatively safe and well tolerated in that cohort. Furthermore, the data demonstrated that conducting such microdosing trials is broadly feasible, with excellent adherence and compliance to the regimen observed. In this open-label pilot trial of patients with major depressive disorder (LSDDEP1), we will test the tolerability and feasibility of an 8-week regimen of LSD microdosing in this patient group prior to a larger subsequent randomised controlled trial (LSDDEP2). METHODS: Twenty patients meeting the DSM-5 criteria for major depressive disorder will receive an 8-week LSD microdosing treatment regimen. The treatment protocol will use a sublingual formulation of LSD (MB-22001) delivered twice per week under a titration schedule using a dose of 5-15 µg. Tolerability will be assessed by quantifying the percentage of participants who withdraw from the trial due to adverse events attributable to the treatment regimen, while feasibility will be assessed by quantifying the percentage of attended clinic visits once enrolled. To determine whether there is any antidepressant response to the LSD microdosing regimen, MADRS scores will be assessed at baseline and 2, 4, 6, and 8 weeks after the commencement of the regimen. DISCUSSION: The results of LSDDEP1 will provide valuable information regarding the tolerability and feasibility of a proposed LSD microdosing regimen in patients with MDD. Such information is critically important to optimise trial design prior to commencing a subsequent and more resource-intensive randomised controlled trial. TRIAL REGISTRATION: ANZCTR, ACTRN12623000486628. Registered on 12 May 2023.

Towards Personalised Mood Prediction and Explanation for Depression from Biophysical Data.

Digital health applications using Artificial Intelligence (AI) are a promising opportunity to address the widening gap between available resources and mental health needs globally. Increasingly, passively acquired data from wearables are augmented with carefully selected active data from depressed individuals to develop Machine Learning (ML) models of depression based on mood scores. However, most ML models are black box in nature, and hence the outputs are not explainable. Depression is also multimodal, and the reasons for depression may vary significantly between individuals. Explainable and personalised models will thus be beneficial to clinicians to determine the main features that lead to a decline in the mood state of a depressed individual, thus enabling suitable personalised therapy. This is currently lacking. Therefore, this study presents a methodology for developing personalised and accurate Deep Learning (DL)-based predictive mood models for depression, along with novel methods for identifying the key facets that lead to the exacerbation of depressive symptoms. We illustrate our approach by using an existing multimodal dataset containing longitudinal Ecological Momentary Assessments of depression, lifestyle data from wearables and neurocognitive assessments for 14 mild to moderately depressed participants over one month. We develop classification- and regression-based DL models to predict participants' current mood scores-a discrete score given to a participant based on the severity of their depressive symptoms. The models are trained inside eight different evolutionary-algorithm-based optimisation schemes that optimise the model parameters for a maximum predictive performance. A five-fold cross-validation scheme is used to verify the DL model's predictive performance against 10 classical ML-based models, with a model error as low as 6% for some participants. We use the best model from the optimisation process to extract indicators, using SHAP, ALE and Anchors from explainable AI literature to explain why certain predictions are made and how they affect mood. These feature insights can assist health professionals in incorporating personalised interventions into a depressed individual's treatment regimen.

A framework for the design of a closed-loop gastric pacemaker for treating conduction block.

BACKGROUND AND OBJECTIVE: Gastrointestinal (GI) motility disorders can be significantly detrimental to the quality of life. Pacing, or long pulse gastric electrical stimulation, is a potential treatment option for treating GI motility disorders by modulating the slow wave activity. Open-loop pacing of the GI tract is the current standard for modulating dysrhythmic patterns, but it is known to be suboptimal and inefficient. Recent work on sensing intracellular potentials and pacing accordingly in a closed-loop has been shown to be effective at modulating dysrhythmic patterns. However, capturing intracellular potentials in an in-vivo setting is not viable. Therefore a closed-loop gastric electrical stimulation that can sense extracellular potentials and pace accordingly to modulate dysrhythmic patterns is required. This paper presents a closed-loop Gastric Electrical Stimulator (GES) design framework, which comprises of extracellular potential generation, sensing, and closed-loop actuation. METHODS: This work leverages a pre-existing high-fidelity two-dimensional Interstitial Cells of Cajal (ICC) network modeling framework to mimic several normal and dysrhythmic patterns observed in experimental recordings of patients suffering from GI tract diseases. The activation patterns of the of the ICC network are captured by an extracellular potential generation model and is integrated with the GES in a closed-loop to validate the efficacy of the developed pacing algorithms. The proposed GES pacing algorithms extend existing offline filtering and activation detection methods to process the sensed extracellular potentials in real time. The GES detects bradygastric rhythms based on the sensed extracellular potentials and actuates the ICC network via pacing to rectify dysrhythmic patterns. RESULTS: The proposed GES model is able to sense and process the generated noisy extracellular potentials, detect the bradygastric patterns, and modulate the slow wave activities to normal propagation effectively. CONCLUSIONS: A closed-loop GES design, which can be applied in an experimental and clinical setting is developed and validated through the ICC network model. The proposed GES model has the ability to modulate a variety of bradygastric patterns, including conduction block effectively in a closed-loop.

Development of closed-loop modelling framework for adaptive respiratory pacemakers.

OBJECTIVE: Ventilatory pacing by electrical stimulation of the phrenic nerve has many advantages compared to mechanical ventilation. However, commercially available respiratory pacing devices operate in an open-loop fashion, which require manual adjustment of stimulation parameters for a given patient. Here, we report the model development of a closed-loop respiratory pacemaker, which can automatically adapt to various pathological ventilation conditions and metabolic demands. METHODS: To assist the model design, we have personalized a computational lung model, which incorporates the mechanics of ventilation and gas exchange. The model can respond to the device stimulation where the gas exchange model provides biofeedback signals to the device. We use a pacing device model with a proportional integral (PI) controller to illustrate our approach. RESULTS: The closed-loop adaptive pacing model can provide superior treatment compared to open-loop operation. The adaptive pacing stimuli can maintain physiological oxygen levels in the blood under various simulated breathing disorders and metabolic demands. CONCLUSION: We demonstrate that the respiratory pacing devices with the biofeedback can adapt to individual needs, while the lung model can be used to validate and parametrize the device. SIGNIFICANCE: The closed-loop model-based framework paves the way towards an individualized and autonomous respiratory pacing device development.

Using Acoustic Speech Patterns From Smartphones to Investigate Mood Disorders: Scoping Review.

BACKGROUND: Mood disorders are commonly underrecognized and undertreated, as diagnosis is reliant on self-reporting and clinical assessments that are often not timely. Speech characteristics of those with mood disorders differs from healthy individuals. With the wide use of smartphones, and the emergence of machine learning approaches, smartphones can be used to monitor speech patterns to help the diagnosis and monitoring of mood disorders. OBJECTIVE: The aim of this review is to synthesize research on using speech patterns from smartphones to diagnose and monitor mood disorders. METHODS: Literature searches of major databases, Medline, PsycInfo, EMBASE, and CINAHL, initially identified 832 relevant articles using the search terms "mood disorders", "smartphone", "voice analysis", and their variants. Only 13 studies met inclusion criteria: use of a smartphone for capturing voice data, focus on diagnosing or monitoring a mood disorder(s), clinical populations recruited prospectively, and in the English language only. Articles were assessed by 2 reviewers, and data extracted included data type, classifiers used, methods of capture, and study results. Studies were analyzed using a narrative synthesis approach. RESULTS: Studies showed that voice data alone had reasonable accuracy in predicting mood states and mood fluctuations based on objectively monitored speech patterns. While a fusion of different sensor modalities revealed the highest accuracy (97.4%), nearly 80% of included studies were pilot trials or feasibility studies without control groups and had small sample sizes ranging from 1 to 73 participants. Studies were also carried out over short or varying timeframes and had significant heterogeneity of methods in terms of the types of audio data captured, environmental contexts, classifiers, and measures to control for privacy and ambient noise. CONCLUSIONS: Approaches that allow smartphone-based monitoring of speech patterns in mood disorders are rapidly growing. The current body of evidence supports the value of speech patterns to monitor, classify, and predict mood states in real time. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach and further work is required to build on current research and reduce heterogeneity of methodologies as well as clinical evaluation of the benefits and risks of such approaches.

Compositional cyber-physical epidemiology of COVID-19.

The COVID-19 pandemic has posed significant challenges globally. Countries have adopted different strategies with varying degrees of success. Epidemiologists are studying the impact of government actions using scenario analysis. However, the interactions between the government policy and the disease dynamics are not formally captured. We, for the first time, formally study the interaction between the disease dynamics, which is modelled as a physical process, and the government policy, which is modelled as the adjoining controller. Our approach enables compositionality, where either the plant or the controller could be replaced by an alternative model. Our work is inspired by the engineering approach for the design of Cyber-Physical Systems. Consequently, we term the new framework Compositional Cyber-Physical Epidemiology. We created different classes of controllers and applied these to control the disease in New Zealand and Italy. Our controllers closely follow government decisions based on their published data. We not only reproduce the pandemic progression faithfully in New Zealand and Italy but also show the tradeoffs produced by differing control actions.

A novel approach for model-based design of gastric pacemakers.

Understanding the slow wave propagation patterns of Interstitial Cells of Cajal (ICC) is essential when designing Gastric Electrical Stimulators (GESs) to treat motility disorders. A GES with the ability to both sense and pace, working in closed-loop with the ICC, will enable efficient modulation of Gastrointestinal (GI) dysrhythmias. However, existing GESs targeted at modulating GI dysrhythmias operate in an open-loop and hence their clinical efficacy is uncertain. This paper proposes a novel model-based approach for designing GESs that operate in closed-loop with the GI tract. GES is modelled using Hybrid Input Output Automata (HIOA), a well-known formal model, which is suitable for designing safety-critical systems. A two-dimensional ICC network working in real-time with the GES is developed using the same compositional HIOA framework. The ICC network model is used to simulate normal and diseased action potential propagation patterns akin to those observed during GI dysrhythmias. The efficacy of the proposed GES is then validated by integrating it in closed-loop with the ICC network. Results show that the proposed GES is able to sense the propagation patterns and modulate the dysrhythmic patterns of bradygastria back to its normal state automatically. The proposed design of the GES is flexible enough to treat a variety of diseased dysrhythmic patterns using closed-loop operation.

Cardiac Electrical Modeling for Closed-Loop Validation of Implantable Devices.

OBJECTIVE: Evaluating and testing cardiac electrical devices in a closed-physiologic-loop can help design safety, but this is rarely practical or comprehensive. Furthermore, in silico closed-loop testing with biophysical computer models cannot meet the requirements of time-critical cardiac device systems, while simplified models meeting time-critical requirements may not have the necessary dynamic features. We propose a new high-level (abstracted) physiologically-based computational heart model that is time-critical and dynamic. METHODS: The model comprises cardiac regional cellular-electrophysiology types connected by a path model along a conduction network. The regional electrophysiology and paths are modeled with hybrid automata that capture non-linear dynamics, such as action potential and conduction velocity restitution and overdrive suppression. The hierarchy of pacemaker functions is incorporated to generate sinus rhythms, while abnormal automaticity can be introduced to form a variety of arrhythmias such as escape ectopic rhythms. Model parameters are calibrated using experimental data and prior model simulations. CONCLUSION: Regional electrophysiology and paths in the model match human action potentials, dynamic behavior, and cardiac activation sequences. Connected in closed loop with a pacing device in DDD mode, the model generates complex arrhythmia such as atrioventricular nodal reentry tachycardia. Such device-induced outcomes have been observed clinically and we can establish the key physiological features of the heart model that influence the device operation. SIGNIFICANCE: These findings demonstrate how an abstract heart model can be used for device validation and to design personalized treatment.

Closing the Loop: Validation of Implantable Cardiac Devices With Computational Heart Models.

OBJECTIVE: Cardiovascular Implantable Electronic Devices (CIEDs) are used extensively for treating life-threatening conditions such as bradycardia, atrioventricular block and heart failure. The complicated heterogeneous physical dynamics of patients provide distinct challenges to device development and validation. We address this problem by proposing a device testing framework within the in-silico closed-loop context of patient physiology. METHODS: We develop an automated framework to validate CIEDs in closed-loop with a high-level physiologically based computational heart model. The framework includes test generation, execution and evaluation, which automatically guides an integrated stochastic optimization algorithm for exploration of physiological conditions. CONCLUSION: The results show that using a closed loop device-heart model framework can achieve high system test coverage, while the heart model provides clinically relevant responses. The simulated findings of pacemaker mediated tachycardia risk evaluation agree well with the clinical observations. Furthermore, we illustrate how device programming parameter selection affects the treatment efficacy for specific physiological conditions. SIGNIFICANCE: This work demonstrates that incorporating model based closed-loop testing of CIEDs into their design provides important indications of safety and efficacy under constrained physiological conditions.

Resonant model-A new paradigm for modeling an action potential of biological cells.

Organ level simulation of bioelectric behavior in the body benefits from flexible and efficient models of cellular membrane potential. These computational organ and cell models can be used to study the impact of pharmaceutical drugs, test hypotheses, assess risk and for closed-loop validation of medical devices. To move closer to the real-time requirements of this modeling a new flexible Fourier based general membrane potential model, called as a Resonant model, is developed that is computationally inexpensive. The new model accurately reproduces non-linear potential morphologies for a variety of cell types. Specifically, the method is used to model human and rabbit sinoatrial node, human ventricular myocyte and squid giant axon electrophysiology. The Resonant models are validated with experimental data and with other published models. Dynamic changes in biological conditions are modeled with changing model coefficients and this approach enables ionic channel alterations to be captured. The Resonant model is used to simulate entrainment between competing sinoatrial node cells. These models can be easily implemented in low-cost digital hardware and an alternative, resource-efficient implementations of sine and cosine functions are presented and it is shown that a Fourier term is produced with two additions and a binary shift.

A Formal Approach for Scalable Simulation of Gastric ICC Electrophysiology.

OBJECTIVE: Efficient and accurate organ models are crucial for closed-loop validation of implantable medical devices. This paper investigates bio-electric slow wave modeling of the stomach, so that gastric electrical stimulator (GES) can be validated and verified prior to implantation. In particular, we consider high-fidelity, scalable, and efficient modeling of the pacemaker, Interstitial cells of Cajal (ICC), based on the formal hybrid input output automata (HIOA) framework. METHODS: Our work is founded in formal methods, a collection of mathematically sound techniques originating in computer science for the design and validation of safety-critical systems. We modeled each ICC cell using an HIOA. We also introduce an HIOA path model to capture the electrical propagation delay between cells in a network. The resultant network of ICC cells can simulate normal and diseased action potential propagation patterns, making it useful for device validation. RESULTS: The simulated slow wave of a single ICC cell had high correlation ( ≈ 0.9) with the corresponding biophysical models. CONCLUSIONS: The proposed model is able to simulate the slow wave activity of a network of ICC cells with high-fidelity for device validation. SIGNIFICANCE: The proposed HIOA model is significantly more efficient than the corresponding biophysical models, scales to larger networks of ICC cells, and is capable of simulating varying propagation patterns. This has the potential to enable verification and validation of implantable GESs in closed-loop with gastrointestinal models in the future.

A Parametric Computational Model of the Action Potential of Pacemaker Cells.

OBJECTIVE: A flexible, efficient, and verifiable pacemaker cell model is essential to the design of real-time virtual hearts that can be used for closed-loop validation of cardiac devices. A new parametric model of pacemaker action potential is developed to address this need. METHODS: The action potential phases are modeled using hybrid automaton with one piecewise-linear continuous variable. The model can capture rate-dependent dynamics, such as action potential duration restitution, conduction velocity restitution, and overdrive suppression by incorporating nonlinear update functions. Simulated dynamics of the model compared well with previous models and clinical data. CONCLUSION: The results show that the parametric model can reproduce the electrophysiological dynamics of a variety of pacemaker cells, such as sinoatrial node, atrioventricular node, and the His-Purkinje system, under varying cardiac conditions. SIGNIFICANCE: This is an important contribution toward closed-loop validation of cardiac devices using real-time heart models.

An intracardiac electrogram model to bridge virtual hearts and implantable cardiac devices.

Virtual heart models have been proposed to enhance the safety of implantable cardiac devices through closed loop validation. To communicate with a virtual heart, devices have been driven by cardiac signals at specific sites. As a result, only the action potentials of these sites are sensed. However, the real device implanted in the heart will sense a complex combination of near and far-field extracellular potential signals. Therefore many device functions, such as blanking periods and refractory periods, are designed to handle these unexpected signals. To represent these signals, we develop an intracardiac electrogram (IEGM) model as an interface between the virtual heart and the device. The model can capture not only the local excitation but also far-field signals and pacing afterpotentials. Moreover, the sensing controller can specify unipolar or bipolar electrogram (EGM) sensing configurations and introduce various oversensing and undersensing modes. The simulation results show that the model is able to reproduce clinically observed sensing problems, which significantly extends the capabilities of the virtual heart model in the context of device validation.