Linking Spontaneous Behavioral Changes to Disease Transmission Dynamics: Behavior Change Includes Periodic Oscillation.

Behavior change significantly influences the transmission of diseases during outbreaks. To incorporate spontaneous preventive measures, we propose a model that integrates behavior change with disease transmission. The model represents behavior change through an imitation process, wherein players exclusively adopt the behavior associated with higher payoff. We find that relying solely on spontaneous behavior change is insufficient for eradicating the disease. The dynamics of behavior change are contingent on the basic reproduction number R a corresponding to the scenario where all players adopt non-pharmaceutical interventions (NPIs). When R a < 1 , partial adherence to NPIs remains consistently feasible. We can ensure that the disease stays at a low level or maintains minor fluctuations around a lower value by increasing sensitivity to perceived infection. In cases where oscillations occur, a further reduction in the maximum prevalence of infection over a cycle can be achieved by increasing the rate of behavior change. When R a > 1 , almost all players consistently adopt NPIs if they are highly sensitive to perceived infection. Further consideration of saturated recovery leads to saddle-node homoclinic and Bogdanov-Takens bifurcations, emphasizing the adverse impact of limited medical resources on controlling the scale of infection. Finally, we parameterize our model with COVID-19 data and Tokyo subway ridership, enabling us to illustrate the disease spread co-evolving with behavior change dynamics. We further demonstrate that an increase in sensitivity to perceived infection can accelerate the peak time and reduce the peak size of infection prevalence in the initial wave.

Longitudinal Assessment of SARS-CoV-2-Specific T Cell Cytokine-Producing Responses for 1 Year Reveals Persistence of Multicytokine Proliferative Responses, with Greater Immunity Associated with Disease Severity.

Cell-mediated immunity is critical for long-term protection against most viral infections, including coronaviruses. We studied 23 severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected survivors over a 1-year post-symptom onset (PSO) interval by ex vivo cytokine enzyme-linked immunosorbent spot assay (ELISpot) assay. All subjects demonstrated SARS-CoV-2-specific gamma interferon (IFN-γ), interleukin 2 (IL-2), and granzyme B (GzmB) T cell responses at presentation, with greater frequencies in severe disease. Cytokines, mainly produced by CD4+ T cells, targeted all structural proteins (nucleocapsid, membrane, and spike) except envelope, with GzmB and IL-2 greater than IFN-γ. Mathematical modeling predicted that (i) cytokine responses peaked at 6 days for IFN-γ, 36 days for IL-2, and 7 days for GzmB, (ii) severe illness was associated with reduced IFN-γ and GzmB but increased IL-2 production rates, and (iii) males displayed greater production of IFN-γ, whereas females produced more GzmB. Ex vivo responses declined over time, with persistence of IL-2 in 86% and of IFN-γ and GzmB in 70% of subjects at a median of 336 days PSO. The average half-life of SARS-CoV-2-specific cytokine-producing cells was modeled to be 139 days (~4.6 months). Potent T cell proliferative responses persisted throughout observation, were CD4 dominant, and were capable of producing all 3 cytokines. Several immunodominant CD4 and CD8 epitopes identified in this study were shared by seasonal coronaviruses or SARS-CoV-1 in the nucleocapsid and membrane regions. Both SARS-CoV-2-specific CD4+ and CD8+ T cell clones were able to kill target cells, though CD8 tended to be more potent. IMPORTANCE Our findings highlight the relative importance of SARS-CoV-2-specific GzmB-producing T cell responses in SARS-CoV-2 control and shared CD4 and CD8 immunodominant epitopes in seasonal coronaviruses or SARS-CoV-1, and they indicate robust persistence of T cell memory at least 1 year after infection. Our findings should inform future strategies to induce T cell vaccines against SARS-CoV-2 and other coronaviruses.

Assessing transmission risks and control strategy for monkeypox as an emerging zoonosis in a metropolitan area.

To model the spread of monkeypox (MPX) in a metropolitan area for assessing the risk of possible outbreaks, and identifying essential public health measures to contain the virus spread. The animal reservoir is the key element in the modeling of zoonotic disease. Using a One Health approach, we model the spread of the MPX virus in humans considering potential animal hosts such as rodents (e.g., rats, mice, squirrels, chipmunks, etc.) and emphasize their role and transmission of the virus in a high-risk group, including gay and bisexual men-who-have-sex-with-men (gbMSM). From model and sensitivity analysis, we identify key public health factors and present scenarios under different transmission assumptions. We find that the MPX virus may spill over from gbMSM high-risk groups to broader populations if the efficiency of transmission increases in the higher-risk group. However, the risk of outbreak can be greatly reduced if at least 65% of symptomatic cases can be isolated and their contacts traced and quarantined. In addition, infections in an animal reservoir will exacerbate MPX transmission risk in the human population. Regions or communities with a higher proportion of gbMSM individuals need greater public health attention. Tracing and quarantine (or "effective quarantine" by postexposure vaccination) of contacts with MPX cases in high-risk groups would have a significant effect on controlling the spreading. Also, monitoring for animal infections would be prudent.

Multiple cohort study of hospitalized SARS-CoV-2 in-host infection dynamics: Parameter estimates, identifiability, sensitivity and the eclipse phase profile.

Within-host SARS-CoV-2 modelling studies have been published throughout the COVID-19 pandemic. These studies contain highly variable numbers of individuals and capture varying timescales of pathogen dynamics; some studies capture the time of disease onset, the peak viral load and subsequent heterogeneity in clearance dynamics across individuals, while others capture late-time post-peak dynamics. In this study, we curate multiple previously published SARS-CoV-2 viral load data sets, fit these data with a consistent modelling approach, and estimate the variability of in-host parameters including the basic reproduction number, R0, as well as the best-fit eclipse phase profile. We find that fitted dynamics can be highly variable across data sets, and highly variable within data sets, particularly when key components of the dynamic trajectories (e.g. peak viral load) are not represented in the data. Further, we investigated the role of the eclipse phase time distribution in fitting SARS-CoV-2 viral load data. By varying the shape parameter of an Erlang distribution, we demonstrate that models with either no eclipse phase, or with an exponentially-distributed eclipse phase, offer significantly worse fits to these data, whereas models with less dispersion around the mean eclipse time (shape parameter two or more) offered the best fits to the available data across all data sets used in this work. This manuscript was submitted as part of a theme issue on "Modelling COVID-19 and Preparedness for Future Pandemics".

Monkeypox: a review of epidemiological modelling studies and how modelling has led to mechanistic insight.

Human monkeypox (mpox) virus is a viral zoonosis that belongs to the Orthopoxvirus genus of the Poxviridae family, which presents with similar symptoms as those seen in human smallpox patients. Mpox is an increasing concern globally, with over 80,000 cases in non-endemic countries as of December 2022. In this review, we provide a brief history and ecology of mpox, its basic virology, and the key differences in mpox viral fitness traits before and after 2022. We summarize and critique current knowledge from epidemiological mathematical models, within-host models, and between-host transmission models using the One Health approach, where we distinguish between models that focus on immunity from vaccination, geography, climatic variables, as well as animal models. We report various epidemiological parameters, such as the reproduction number, R0, in a condensed format to facilitate comparison between studies. We focus on how mathematical modelling studies have led to novel mechanistic insight into mpox transmission and pathogenesis. As mpox is predicted to lead to further infection peaks in many historically non-endemic countries, mathematical modelling studies of mpox can provide rapid actionable insights into viral dynamics to guide public health measures and mitigation strategies.

COVID-19 Vaccination and Healthcare Demand.

One of the driving concerns during any epidemic is the strain on the healthcare system. As we have seen many times over the globe with the COVID-19 pandemic, hospitals and ICUs can quickly become overwhelmed by cases. While strict periods of public health mitigation have certainly helped decrease incidence and thus healthcare demand, vaccination is the only clear long-term solution. In this paper, we develop a two-module model to forecast the effects of relaxation of non-pharmaceutical intervention and vaccine uptake on daily incidence, and the cascade effects on healthcare demand. The first module is a simple epidemiological model which incorporates non-pharmaceutical intervention, the relaxation of such measures and vaccination campaigns to predict caseloads into the Fall of 2021. This module is then fed into a healthcare module which can forecast the number of doctor visits, the number of occupied hospital beds, number of occupied ICU beds and any excess demand of these. From this module, we can also estimate the length of stay of individuals in ICU. For model verification and forecasting, we use the four most populous Canadian provinces as a case study.

An HIV stochastic model with cell-to-cell infection, B-cell immune response and distributed delay.

In this study, a delayed HIV stochastic model with virus-to-cell infection, cell-to-cell transmission and B-cell immune response is proposed. We first transform the stochastic differential equation with distributed delay into a high-dimensional degenerate stochastic differential equation, and then theoretically analyze the dynamic behaviour of the degenerate model. The unique global solution of the model is given by rigorous analysis. By formulating suitable Lyapunov functions, the existence of the stationary Markov process is obtained if the stochastic B-cell-activated reproduction number is greater than one. We also use the law of large numbers theorem and the spectral radius analysis method to deduce that the virus can be cleared if the stochastic B-cell-inactivated reproduction number is less than one. Through uncertainty and sensitivity analysis, we obtain key parameters that determine the value of the stochastic B-cell-activated reproduction number. Numerically, we examine that low level noise can maintain the number of the virus and B-cell populations at a certain range, while high level noise is helpful for the elimination of the virus. Furthermore, the effect of the cell-to-cell infection on model behaviour, and the influence of the key parameters on the size of the stochastic B-cell-activated reproduction number are also investigated.

Determination of significant immunological timescales from mRNA-LNP-based vaccines in humans.

A compartment model for an in-host liquid nanoparticle delivered mRNA vaccine is presented. Through non-dimensionalisation, five timescales are identified that dictate the lifetime of the vaccine in-host: decay of interferon gamma, antibody priming, autocatalytic growth, antibody peak and decay, and interleukin cessation. Through asymptotic analysis we are able to obtain semi-analytical solutions in each of the time regimes which allows us to predict maximal concentrations and better understand parameter dependence in the model. We compare our model to 22 data sets for the BNT162b2 and mRNA-1273 mRNA vaccines demonstrating good agreement. Using our analysis, we estimate the values for each of the five timescales in each data set and predict maximal concentrations of plasma B-cells, antibody, and interleukin. Through our comparison, we do not observe any discernible differences between vaccine candidates and sex. However, we do identify an age dependence, specifically that vaccine activation takes longer and that peak antibody occurs sooner in patients aged 55 and greater.

In Elimination Settings, Measles Antibodies Wane After Vaccination but Not After Infection: A Systematic Review and Meta-Analysis.

BACKGROUND: We conducted a systematic review to assess whether measles humoral immunity wanes in previously infected or vaccinated populations in measles elimination settings. METHODS: After screening 16 822 citations, we identified 9 articles from populations exposed to wild-type measles and 16 articles from vaccinated populations that met our inclusion criteria. RESULTS: Using linear regression, we found that geometric mean titers (GMTs) decreased significantly in individuals who received 2 doses of measles-containing vaccine (MCV) by 121.8 mIU/mL (95% confidence interval [CI], -212.4 to -31.1) per year since vaccination over 1 to 5 years, 53.7 mIU/mL (95% CI, -95.3 to -12.2) 5 to 10 years, 33.2 mIU/mL (95% CI, -62.6 to -3.9), 10 to 15 years, and 24.1 mIU/mL (95% CI, -51.5 to 3.3) 15 to 20 years since vaccination. Decreases in GMT over time were not significant after 1 dose of MCV or after infection. Decreases in the proportion of seropositive individuals over time were not significant after 1 or 2 doses of MCV or after infection. CONCLUSIONS: Measles antibody waning in vaccinated populations should be considered in planning for measles elimination.

An investigation of tuberculosis progression revealing the role of macrophages apoptosis via sensitivity and bifurcation analysis.

Mycobacterium tuberculosis infection features various disease outcomes: clearance, latency, active disease, and latent tuberculosis infection (LTBI) reactivation. Identifying the decisive factors for disease outcomes and progression is crucial to elucidate the macrophages-tuberculosis interaction and provide insights into therapeutic strategies. To achieve this goal, we first model the disease progression as a dynamical shift among different disease outcomes, which are characterized by various steady states of bacterial concentration. The causal mechanisms of steady-state transitions can be the occurrence of transcritical and saddle-node bifurcations, which are induced by slowly changing parameters. Transcritical bifurcation, occurring when the basic reproduction number equals to one, determines whether the infection clears or spreads. Saddle-node bifurcation is the key mechanism to create and destroy steady states. Based on these two steady-state transition mechanisms, we carry out two sample-based sensitivity analyses on transcritical bifurcation conditions and saddle-node bifurcation conditions. The sensitivity analysis results suggest that the macrophage apoptosis rate is the most significant factor affecting the transition in disease outcomes. This result agrees with the discovery that the programmed cell death (apoptosis) plays a unique role in the complex microorganism-host interplay. Sensitivity analysis narrows down the parameters of interest, but cannot answer how these parameters influence the model outcomes. To do this, we employ bifurcation analysis and numerical simulation to unfold various disease outcomes induced by the variation of macrophage apoptosis rate. Our findings support the hypothesis that the regulation mechanism of macrophage apoptosis affects the host immunity against tuberculosis infection and tuberculosis virulence. Moreover, our mathematical results suggest that new treatments and/or vaccines that regulate macrophage apoptosis in combination with weakening bacillary viability and/or promoting adaptive immunity could have therapeutic value.

What Is the Evidence to Support a Correlate of Protection for Measles? A Systematic Review.

BACKGROUND: Many studies assume that the serologic correlate of protection from measles disease is 120 mIU/mL. We systematically reviewed the literature to examine the evidence supporting this correlate of protection. METHODS: We searched peer-reviewed and gray literature for articles reporting a measles correlate of protection. We excluded studies focusing on special populations, infants aged <9 months, and those using animal models or nonstandard vaccines or administration routes. We extracted and synthesized data from full-text articles that met inclusion criteria. RESULTS: We screened 14 778 articles and included 5 studies in our review. The studies reported either preexposure antibody concentrations of individuals along with a description of symptoms postexposure, or the proportion of measles cases that had preexposure antibody concentrations above a threshold of immunity specified by the authors. Some studies also described secondary antibody responses upon exposure. The variation in laboratory methods between studies made comparisons difficult. Some of the studies that assumed 120 mIU/mL as a correlate of protection identified symptomatic individuals with preexposure titers exceeding this threshold. CONCLUSIONS: Our findings underscore the scant data upon which the commonly used 120 mIU/mL measles threshold of protection is based, suggesting that further work is required to characterize the measles immunity threshold.

Fangcang shelter hospitals during the COVID-19 epidemic, Wuhan, China.

OBJECTIVE: To design models of the spread of coronavirus disease-2019 (COVID-19) in Wuhan and the effect of Fangcang shelter hospitals (rapidly-built temporary hospitals) on the control of the epidemic. METHODS: We used data on daily reported confirmed cases of COVID-19, recovered cases and deaths from the official website of the Wuhan Municipal Health Commission to build compartmental models for three phases of the COVID-19 epidemic. We incorporated the hospital-bed capacity of both designated and Fangcang shelter hospitals. We used the models to assess the success of the strategy adopted in Wuhan to control the COVID-19 epidemic. FINDINGS: Based on the 13 348 Fangcang shelter hospitals beds used in practice, our models show that if the Fangcang shelter hospitals had been opened on 6 February (a day after their actual opening), the total number of COVID-19 cases would have reached 7 413 798 (instead of 50 844) with 1 396 017 deaths (instead of 5003), and the epidemic would have lasted for 179 days (instead of 71). CONCLUSION: While the designated hospitals saved lives of patients with severe COVID-19, it was the increased hospital-bed capacity of the large number of Fangcang shelter hospitals that helped slow and eventually stop the COVID-19 epidemic in Wuhan. Given the current global pandemic of COVID-19, our study suggests that increasing hospital-bed capacity, especially through temporary hospitals such as Fangcang shelter hospitals, to isolate groups of people with mild symptoms within an affected region could help curb and eventually stop COVID-19 outbreaks in communities where effective household isolation is not possible.

Impact of influenza vaccine-modified infectivity on attack rate, case fatality ratio and mortality.

Generally, vaccines are designed to provide protection against infection (susceptibility), disease (symptoms and transmissibility), and/or complications. In a recent study of influenza vaccination, it was observed that vaccinated yet infected individuals experienced increased transmission levels. In this paper, using a mathematical model of infection and transmission, we study the impact of vaccine-modified effects, including susceptibility and infectivity, on important epidemiological outcomes of an immunization program. The balance between vaccine-modified susceptibility, infectivity and recovery needed in preventing an influenza outbreak, or in mitigating the health outcomes of the outbreak is studied using the SIRV-type of disease transmission model. We also investigate the impact of influenza vaccination program on the infection risk of vaccinated and non-vaccinated individuals.

Modeling the waning and boosting of immunity from infection or vaccination.

Immunity following natural infection or immunization may wane, increasing susceptibility to infection with time since infection or vaccination. Symptoms, and concomitantly infectiousness, depend on residual immunity. We quantify these phenomena in a model population composed of individuals whose susceptibility, infectiousness, and symptoms all vary with immune status. We also model age, which affects contact, vaccination and possibly waning rates. The resurgences of pertussis that have been observed wherever effective vaccination programs have reduced typical disease among young children follow from these processes. As one example, we compare simulations with the experience of Sweden following resumption of pertussis vaccination after the hiatus from 1979 to 1996, reproducing the observations leading health authorities to introduce booster doses among school-aged children and adolescents in 2007 and 2014, respectively. Because pertussis comprises a spectrum of symptoms, only the most severe of which are medically attended, accurate models are needed to design optimal vaccination programs where surveillance is less effective.

Quantifying the annual incidence and underestimation of seasonal influenza: A modelling approach.

BACKGROUND: Seasonal influenza poses a significant public health and economic burden, associated with the outcome of infection and resulting complications. The true burden of the disease is difficult to capture due to the wide range of presentation, from asymptomatic cases to non-respiratory complications such as cardiovascular events, and its seasonal variability. An understanding of the magnitude of the true annual incidence of influenza is important to support prevention and control policy development and to evaluate the impact of preventative measures such as vaccination. METHODS: We use a dynamic disease transmission model, laboratory-confirmed influenza surveillance data, and randomized-controlled trial (RCT) data to quantify the underestimation factor, expansion factor, and symptomatic influenza illnesses in the US and Canada during the 2011-2012 and 2012-2013 influenza seasons. RESULTS: Based on 2 case definitions, we estimate between 0.42-3.2% and 0.33-1.2% of symptomatic influenza illnesses were laboratory-confirmed in Canada during the 2011-2012 and 2012-2013 seasons, respectively. In the US, we estimate between 0.08-0.61% and 0.07-0.33% of symptomatic influenza illnesses were laboratory-confirmed in the 2011-2012 and 2012-2013 seasons, respectively. We estimated the symptomatic influenza illnesses in Canada to be 0.32-2.4 million in 2011-2012 and 1.8-8.2 million in 2012-2013. In the US, we estimate the number of symptomatic influenza illnesses to be 4.4-34 million in 2011-2012 and 23-102 million in 2012-2013. CONCLUSIONS: We illustrate that monitoring a representative group within a population may aid in effectively modelling the transmission of infectious diseases such as influenza. In particular, the utilization of RCTs in models may enhance the accuracy of epidemiological parameter estimation.

A two-thresholds policy to interrupt transmission of West Nile Virus to birds.

This paper proposes a model of West Nile Virus (WNV) including threshold control policies concerning the culling of mosquitoes and birds under different conditions. Two thresholds are introduced to estimate whether and which control strategy should be implemented. For each mosquito threshold level [Formula: see text] the dynamical behaviour of the proposed non-smooth system is investigated as the bird threshold level [Formula: see text] varies, focusing on the existence of sliding domains, the existence of pseudo-equilibria, real or virtual of the endemic equilibria, global stability of these steady states, and the most interesting case of the occurrence of a novel globally asymptotically stable pseudo-attractor. The model solutions ultimately converge to a real equilibrium or a pseudo-equilibrium (if it exists), or a pseudo-attractor if no equilibrium is real and no pseudo-equilibrium exists. Here within, we show that the free system has a single stable endemic equilibrium under biologically reasonable assumptions, and show that when the control system has: (1) a bird-culling threshold that is above the bird equilibrium, culling has no advantage; (2) a bird-culling threshold that is below the bird equilibrium, but a mosquito-culling threshold that lies above the mosquito equilibrium, the infected bird population can be reduced but the infected mosquito population will remain the same; (3) a bird-culling threshold and a mosquito-culling threshold that both lie below their respective equilibrium values of the free system, then both the infected bird and mosquito populations can be reduced to lower levels. The results suggest that preset levels of the number of infected birds and infected mosquitoes can be maintained simultaneously when threshold values are chosen properly, which provides a possible control strategy when an emergent infectious disease cannot be eradicated immediately.

HPV Screening and Vaccination Strategies in an Unscreened Population: A Mathematical Modeling Study.

Human papillomavirus (HPV), a sexually transmitted infection, is the necessary cause of cervical cancer, the third most common cancer affecting women worldwide. Prevention and control strategies include vaccination, screening, and treatment. While HPV prevention and control efforts are important worldwide, they are especially important in low-income areas with a high infection rate or high rate of cervical cancer. This study uses mathematical modeling to explore various vaccination and treatment strategies to control for HPV and cervical cancer while using Nepal as a case study. Two sets of deterministic models were created with the goal of understanding the impact of various prevention and control strategies. The first set of models examines the relative importance of screening and vaccination in an unscreened population, while the second set examines various screening scenarios. Partial rank correlation coefficients confirm the importance of screening and treatment in the reduction of HPV infections and cancer cases even when vaccination uptake is high. Results also indicate that less expensive screening technologies can achieve the same overall goal as more expensive screening technologies.

Cost-effectiveness of measles control during elimination in Ontario, Canada, 2015.

BackgroundGiven that measles is eliminated in Canada and measles immunisation coverage in Ontario is high, it has been questioned whether Ontario's measles outbreak response is worthwhile.AimOur objective was to determine cost-effectiveness of measles containment protocols in Ontario from the healthcare payer perspective.MethodsWe developed a decision-analysis model comparing Ontario's measles containment strategy (based on actual 2015 outbreak data) with a hypothetical 'modified response'. The modified scenario assumed 10% response costs with reduced case and contact tracing and no outbreak-associated vaccinations; it was based on local and provincial administrative and laboratory data and parameters from peer-reviewed literature. Short- and long-term health outcomes, quality-adjusted life years (QALYs) and costs discounted at 1.5%, were estimated. We conducted one- and two-way sensitivity analyses.ResultsThe 2015 outbreak in Ontario comprised 16 measles cases and an estimated 3,369 contacts. Predictive modelling suggested that the outbreak response prevented 16 outbreak-associated cases at a cost of CAD 1,213,491 (EUR 861,579). The incremental cost-effectiveness ratio was CAD 739,063 (EUR 524,735) per QALY gained for the outbreak response vs modified response. To meet the commonly accepted cost-effectiveness threshold of CAD 50,000 (EUR 35,500) per QALY gained, the outbreak response would have to prevent 94 measles cases. In sensitivity analyses, the findings were robust.ConclusionsOntario's measles outbreak response exceeds generally accepted cost-effectiveness thresholds and may not be the most efficient use of public health resources from a healthcare payer perspective. These findings should be balanced against benefits of increased vaccine coverage and maintaining elimination status.

Defining and Predicting Pain Volatility in Users of the Manage My Pain App: Analysis Using Data Mining and Machine Learning Methods.

BACKGROUND: Measuring and predicting pain volatility (fluctuation or variability in pain scores over time) can help improve pain management. Perceptions of pain and its consequent disabling effects are often heightened under the conditions of greater uncertainty and unpredictability associated with pain volatility. OBJECTIVE: This study aimed to use data mining and machine learning methods to (1) define a new measure of pain volatility and (2) predict future pain volatility levels from users of the pain management app, Manage My Pain, based on demographic, clinical, and app use features. METHODS: Pain volatility was defined as the mean of absolute changes between 2 consecutive self-reported pain severity scores within the observation periods. The k-means clustering algorithm was applied to users' pain volatility scores at the first and sixth month of app use to establish a threshold discriminating low from high volatility classes. Subsequently, we extracted 130 demographic, clinical, and app usage features from the first month of app use to predict these 2 volatility classes at the sixth month of app use. Prediction models were developed using 4 methods: (1) logistic regression with ridge estimators; (2) logistic regression with Least Absolute Shrinkage and Selection Operator; (3) Random Forests; and (4) Support Vector Machines. Overall prediction accuracy and accuracy for both classes were calculated to compare the performance of the prediction models. Training and testing were conducted using 5-fold cross validation. A class imbalance issue was addressed using a random subsampling of the training dataset. Users with at least five pain records in both the predictor and outcome periods (N=782 users) are included in the analysis. RESULTS: k-means clustering algorithm was applied to pain volatility scores to establish a threshold of 1.6 to differentiate between low and high volatility classes. After validating the threshold using random subsamples, 2 classes were created: low volatility (n=611) and high volatility (n=171). In this class-imbalanced dataset, all 4 prediction models achieved 78.1% (611/782) to 79.0% (618/782) in overall accuracy. However, all models have a prediction accuracy of less than 18.7% (32/171) for the high volatility class. After addressing the class imbalance issue using random subsampling, results improved across all models for the high volatility class to greater than 59.6% (102/171). The prediction model based on Random Forests performs the best as it consistently achieves approximately 70% accuracy for both classes across 3 random subsamples. CONCLUSIONS: We propose a novel method for measuring pain volatility. Cluster analysis was applied to divide users into subsets of low and high volatility classes. These classes were then predicted at the sixth month of app use with an acceptable degree of accuracy using machine learning methods based on the features extracted from demographic, clinical, and app use information from the first month.