Change Point Research Articles

Examined lymph node counts affected the staging and survival in cervical cancer: a retrospective study using the SEER and Chinese cohort

Background The impact of examined lymph node (LN) count on survival in cervical cancer remains understudied, with no consensus on the optimal number required. Objectives We aimed to investigate the role of LN count in postoperative pathological evaluation for cervical cancer patients undergoing surgery. Methods Data from the US SEER database and a retrospective Chinese cohort were analyzed. Multivariable logistic and Cox regression models assessed LN positivity detection and overall survival (OS), respectively. Smoothing spline curves and Chow tests identified structural change points in hazard ratios and LN-positive ratios. Results Among 14,133 SEER and 2,811 Chinese cases, higher LN counts correlated with increased detection of positive LNs (OR: 1.040, 95% CI: 1.019–1.062) and improved OS (HR: 0.990, 95% CI: 0.984–0.996). Structural change points occurred at 20 LNs for LN-negative patients and 13 LNs for LN-positive patients (both P < 0.001). An elevated LN-positive ratio (positive/examined LNs) strongly predicted worse OS (HR: 4.208; 95% CI: 1.454–12.181). Conclusions An increased number of examined LNs significantly contributes to the detection of positive LNs and improved patient survival. For patients with claimed LN-negative and LN-positive disease, a minimum examination of 20 and 13 LNs, respectively, is recommended to ensure adequate LN evaluation. The LN positive ratio is a strong prognostic indicator in patients with LN-positive disease.

Change point detection to analyze air pollution and its economic effects: an exponentially weighted moving average perspective

Air pollution has a direct impact on every society, leading to consequential effects on the economy of a nation. Poor air quality adversely affects human health, resulting in various economic outcomes such as rising healthcare costs, diminished labor productivity, negative impacts on tourism and living standards, increased regulatory expenses for businesses, and heightened economic disparities. Effective control methods are essential to monitor factors influencing the economy, including air quality. The presence of toxic substances in the air reduces air quality, necessitating its monitoring through indices like PM10. Among statistical process control tools, control charts are the most prominent for efficient change point detection. This study introduces a new process monitoring tool that incorporates additional auxiliary information, if available, alongside the main variable of interest. The proposed methodology ensures detection ability remains robust, even under disturbances in the auxiliary variable. Furthermore, mathematical analyses reveal that many existing statistical quality control tools become special cases of the proposed structure for specific sensitivity parameter values. Evaluated through properties of run length distribution, the proposed chart allows control of the robustness-efficiency balance by adjusting its sensitivity parameter. A practical implementation demonstrates the effectiveness of the chart in monitoring air quality data.

Real-time identification of foundation damage in high-Pile Wharves: Nonlinear feature change point analysis in dynamic characteristics under wave excitation

Waves are a common excitation form for wharves. The responses of pile foundation in high-pile wharves under such excitation exhibit pronounced nonlinear and non-stationary characteristics, compromising the robustness of damage detection methods. To address this challenge, this paper first introduces a method using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and spectral feature analysis, aimed at extracting the overall characteristic sub-signals to resolve multi-type signal aliasing. Secondly, the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model is employed to isolate the nonlinear dynamic features of the response under wave excitation. Thirdly, the Weighted Residual Cumulative Sum (WRCUSUM) method is developed to monitor changes in response characteristics online, thereby enabling the identification of damage occurrence and its timing. Further, the efficacy of the proposed method has been validated through high-pile wharf experiments conducted at various damage levels. This approach not only offers a novel solution for online damage detection under wave excitation but also introduces a new strategy for non-destructive testing across offshore engineering applications.

Does how I feel change how I move? The influence of anxiety, self-efficacy and resilience on movement in adults with Developmental Coordination Disorder.

Anxiety and movement consistency both influence movement in individuals with Developmental Coordination Disorder (DCD). This study investigated the influence of anxiety, self-efficacy, resilience and movement variability on perceptions and actions of adults with and without DCD. 17 adults with DCD and 17 adults with typical motor skills (TMS) (age and sex-matched) completed a questionnaire and three experimental tasks: two perceptual judgement tasks (static and dynamic conditions), and an executed action task involving judging and walking through different-sized gaps between doors. No significant relationships were detected between general or movement-specific anxiety, self-efficacy or resilience and perceptual judgement or movement behaviour; however, movement consistency did significantly relate to movement execution in both groups. Correlations showed adults with DCD with lower movement-specific self-efficacy left bigger safety margins, and indicated stronger links between perception and action in TMS adults. In the adults with DCD there was no significant correlation between the point of behaviour change (critical ratio) in the perceptual judgement and executed action tasks, suggesting a less smoothly linked perception-action cycle than in the TMS adults. Results highlight the importance of movement variability and motor control in the movement behaviour of adults with DCD, while illustrating the importance of studying perception and action together, especially when comparing populations, to elucidate how these may be constrained differently by individual-, task- and environmental-based constraints.

Change point detection in brucellosis time series from 2010 to 2023 in Xinjiang China using the BEAST algorithm.

Brucellosis is a significant global challenge, but there has been a lack of epidemiological studies on brucellosis in Xinjiang from a change point perspective. This study aims to bridge this gap by employing sequence decomposition and identifying significant change points, with datasets sourced from the Xinjiang Disease Prevention and Control Information System. This study employed the BEAST algorithm to decompose the brucellosis time series in Xinjiang from 2010 to 2023, while simultaneously identifying change points in the decomposed seasonal and trend components. The probability of four change points occurring within the seasonal component is 0.8950. And the locations where these four change points occur and the probabilities associated with each change point are August 2013 ([Formula: see text]), August 2017 ([Formula: see text]), February 2022 ([Formula: see text]), and May 2023 ([Formula: see text]), respectively. The probability of the existence of five change points in the trend factors of brucellosis in Xinjiang is highest ([Formula: see text]). The times at which these five change points occur, along with the probabilities of change at those moments, are as follows: March 2013 ([Formula: see text]), August 2015 ([Formula: see text]), July 2017 ([Formula: see text]), February 2020 ([Formula: see text]), and May 2023 ([Formula: see text]). Change point analysis holds significant utility within the field of epidemiology. These discoveries furnish pivotal insights for epidemiological investigations and the development of early warning systems tailored to brucellosis.

Impact of Regulatory Action on Dose Maximalization for Vitamin B6 Dietary Supplements on the Reporting Pattern for Neuropathy.

Vitamin B6 deficiency is linked to neurological disorders. However, supplementation with high doses of vitamin B6 has also been linked to neuropathy as an adverse drug reaction. Review of cases from the Dutch Spontaneous Reporting System (SRS) and other data led to a regulatory action to lower the maximum daily dose (DD) of vitamin B6 in supplements to 21 mg/day from October 1, 2018. The aim of this study was to investigate if there was an effect of the regulatory action in 2018 on maximum daily dosage for vitamin B6 on the reporting pattern of neuropathy to the SRS in the Netherlands. We investigated trends in the number of reports received until December 31, 2023, DD mentioned in the reports, and the correlation between DD and plasma vitamin B6 levels. A change point analysis was used to get insight into the pattern of reports over time. Two hundred and twenty-four reports were included. After the regulatory action for dose maximization from October 2018, only one report mentions a dosage which is much higher than the recommended 21 mg DD. Only 15% of the variability in plasma levels mentioned in reports can be explained by the DD. Twelve statistical change points were noted, especially around some peaks in the reporting pattern for instance in 2018. However, from the second half of 2019, the number of reports on vitamin B6 and neuropathy per time period is lower and no change points were detected. Although our study has limitations, we clearly see an effect of regulatory action on the doses of vitamin B6 used in neuropathy reports. However, some cases describing neuropathy related to vitamin B6 supplementation with lower doses are still reported after the regulatory action in 2018. Therefore, the association between low-dose vitamin B6 products and neuropathy should be studied further.

Complexity Growth Patterns in the Stelliferous Era of Big History

A previous study compared the symmetries of the cooling after the Big Bang and the development of life, humans, and civilization on Earth. A simple model of the relative rates of change depicts two cones joined at their bases representing the Big Bang expansion and the acceleration of complexity development on earth through life evolution, human evolution, and civilization development. This indicates points of rapid change at both ends corresponding to at the Big Bang and our current technological and demographic change. However, this depiction oversimplifies complexity growth, specifically at where the transitions from the Universe’s decelerating physical complexity development and Earths accelerating complex adaptive systems. This transition is important in both organization and energy flow. In this paper, the build-up of potential variety in elements and chemicals to later build planets and life is the focus. These are mostly derived from stellar formation through the conversion of gravitational and nuclear potential energy into elements through nuclear fusion. Other’s models have been employed to explore the dynamics of this buildup from the first Population I stars, which were large and short-lived, through the Population II stars of galactic spherical bulges and haloes, to the formation of smaller, long-lived stars with a high amount of non-Hydrogen and Helium atoms, called “metals”. The rates of these dynamics during the transition from cosmic development to terrestrial evolution on Earth are explored here.

Change point detection for clustered survival data with marginal proportional hazards model

In survival analysis, models with a change point for independent survival data have been extensively studied. However, few works in the literature focus on clustered survival data with a change point, despite the prevalence of such survival data in clinical research. In this article, we propose the maximal score test, along with its normalized version, to detect the existence of change point effects for the marginal proportional hazards model. We establish the asymptotic distributions of the proposed test statistics under both the null and local alternative hypotheses. To approximate the critical points for the proposed tests, a simple Monte Carlo method is presented. Furthermore, when the null hypothesis of no change point effects is rejected, we propose maximum smoothed partial likelihood estimators for the unknown change point and the regression parameters and derive the asymptotic properties of the estimators. Extensive simulation studies are carried out to evaluate the finite sample performance of the proposed methods. Finally, we illustrate the proposed methods with applications to the breast cancer data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial.

Change Point Estimation Based on a Weighted Consensus Clustering Approach with Multiple Steps (A Real Case in Health Care: Diabetic Patients)

One of the primary objectives of control charts is to accurately detect the occurrence of changes in statistical processes. This enables process analysts to identify the factors responsible for the change and take corrective actions. The clustering method is a practical approach that has been developed to estimate the time of change. In recent years, a new approach called weighted consensus clustering (WCC) has been introduced in the field of clustering analysis. This approach can be utilized to cluster different trends in process parameters, resulting in a final clustering that exhibits higher quality and stability compared to the initial clustering. One of the emerging aspects in the health care field is the use of new statistical approaches to rapid disease diagnosis. In this paper, a novel change point estimation scheme called WCC has been developed to detect changes in the diabetic patients’ processes. In addition, to demonstrate the advantages of the proposed scheme, its performance is compared with an existing method known as maximum likelihood of clusters (CMLE) through simulation studies as well as a real case study in the healthcare system.

Testing for changes in the error distribution in functional linear models

We consider linear models with scalar responses and covariates from a separable Hilbert space. The aim is to detect change points in the error distribution, based on sequential residual empirical distribution functions. Expansions for those estimated functions are more challenging in models with infinite-dimensional covariates than in regression models with scalar or vector-valued covariates due to a slower rate of convergence of the parameter estimators. Yet the suggested change point test is asymptotically distribution-free and consistent for one-change point alternatives. In the latter case we also show consistency of a change point estimator.

On break detection in volatility function of a tau-dependent process

This paper investigates change point detection within financial time series volatility using the NonParametric AutoRegressive Conditionally Heteroscedastic (NPARCH) process. It introduces a classical CUSUM type change point test following the test procedure by [19]. In the absence of change (Null Hypothesis), the test statistic converges to a well-established distribution, simplifying the determination of the critical test value. Conversely, under the Alternative Hypothesis, the probability that the test statistic tends to infinity is one, indicating asymptotic power one. Simulation results are presented to confirm the efficacy of the proposed methodology.

Trend analysis and change point detection in precipitation time series over the Eastern Province of Rwanda during 1981–2021

This study examines trends and change points in agroclimatic variables at 56 meteorological stations’ locations and region levels in Rwanda’s Eastern Province from 1981 to 2021. We used the Mann–Kendall and Regional Kendall tests, along with Sen’s Slope and Sequential Mann–Kendall Rank Statistic tests, to analyse six key agricultural indicators: seasonal rainfall totals, number of rainy days, rainfall intensity (light, moderate, heavy), onset and cessation dates, and season duration. In the March to May (MAM) season, 39 out of 56 stations recorded a decreasing rainfall trend, with significant trends observed at eight stations in the south. Conversely, 17 stations showed increasing trends, with only one in the north being significant. Regionally, the trend was a non-significant decrease. In the September to December (SOND) season, 31 stations (one significant) experienced decreasing rainfall trends. Among the 25 stations showing increasing trends, only one was significant. The regional trend indicates a non-significant increase. Onset days showed a decreasing trend at 41 stations (12 significant) in both MAM and SOND and a significant regional trend in SOND. Season duration increased at 43 stations in MAM (five significant) and 48 stations in SOND (six significant), with the regional trend being significant only in SOND. Heavy rainy days indicate a significantly regional decreasing trend in MAM. The change point of most stations with decreasing and increasing trends occurred between 2000–2020 and 1980–2000, respectively. These fluctuations have affected agricultural practices and led to crop failures, emphasizing the region’s need for better climate information services and adaptation strategies.

Robust ratio-typed test for location change under strong mixing heavy-tailed time series model

. The data distributions of many financial and econometric sequences always exhibit heavy-tailed phenomena, which trigger distinct difficulty in parameter estimation by classical least squares method. This article aims to construct a new ratio-typed test based on least absolute deviation estimation that effectively circumvents the problem of long-run variance estimation and has robustness on detecting structural changes under strong mixing sequences with heavy-tailed innovations. This is because the least absolute deviation estimation can allow for processes within the domain of attraction of a stable law with an index κ ∈ ( 0 , 2 ) , not limited to (1, 2). Under some regular conditions, the asymptotic distribution under the null hypothesis is derived as a functional of Brownian motion, not a functional of lévy process, and the divergence rate under the alternative hypothesis is also provided. Furthermore, the consistency of a ratio-typed change point estimator is given and its convergence rate is established. The numerical simulation indicates that empirical sizes are undistorted, and empirical powers exhibit significant performance. Finally, two practical application examples are presented to illustrate the validity of the proposed test procedures.

The impact of the live broadcast of Stromae's song L'enfer on social media publications, calls to the national helpline, and suicide attempt rates in France.

On January 9, 2022, Belgian pop singer Stromae performed his new hit "L'enfer" live on French TV. The song addresses his personal struggles with suicidal ideation. To evaluate the impact of Stromae's performance, we modeled the evolution of hospital admission rates for suicide attempts (SAs) in France, calls to the national suicide prevention helpline (3114), and Twitter publications mentioning the singer or the helpline. We employed the Gombay test to identify change points within each time series. We identified a significant increase in mean SA rates among women aged 20-24years 6days after the singer's performance. No similar effect was observed in the general population or other young age groups. The show was immediately followed by a peak in tweets referring to the singer, while Twitter activity related to the 3114 remained modest. We did not observe any increase in calls to the helpline. Celebrity testimonies about suicidal experiences can help alleviate stigma but should be accompanied by prevention messages to reduce the risk of contagion.

Interrupted-time-series analysis of the impact of COVID-19 pandemic on blood culture utilization in Shanghai

BackgroundLimited information is available regarding the changes in blood culture utilization following the COVID-19 pandemic. Blood culture utilization rate is a critical indicator of diagnostic efficiency for infectious diseases. This study aims to describe the impact of the COVID-19 pandemic on blood culture utilization rate in Shanghai.MethodsWe conducted an interrupted time-series analysis based on electronic health records from the Shanghai Changzheng hospital from January 2014 to October 2023. The outcome measure was the rate of blood culture utilization among inpatients with a temperature of ≥ 39.4 °C. The impact of the COVID-19 pandemic on blood culture utilization was quantified by fitting linear segmented regression models and modelling the relative cumulative effect by the end of the study. The pandemic period was defined from February 2020, following the implementation of strict containment measures in Shanghai.ResultsA total of 23,761 inpatients with a temperature of ≥ 39.4 °C were included in the analysis. From 2014 to 2023, the utilization rate of hospital blood cultures increased initially and then declined, with a significant change point following the onset of the COVID-19 pandemic (Cochran-Armitage trend test, P < 0.001). The COVID-19 pandemic was associated with a significant change in the slope of the blood culture utilization rate (pre-COVID-19 vs. during-COVID-19: 0.31% per month vs. -0.30% per month, P < 0.001), resulting in a relative cumulative effect of -12.55% at the end of the study (95% confidence interval, -19.08 to -6.03). This corresponds to 407 inpatients who did not have blood cultures taken during-pandemic, which represents a significant deviation from pre-pandemic trends.ConclusionsThe upward trend in blood culture utilization rate among inpatients stalled during the COVID-19 pandemic and did not return to pre-pandemic levels following the pandemic. These findings suggest that the pandemic had a lasting impact on diagnostic practices. More targeted intervention measures are needed to promote appropriate utilization of blood cultures.

Teacher mobilizers: the power of leading learning and mobilizing teacher communities

Mobilizer teachers are trained and professional teachers who play a strategic role in leading learning and improving the quality of education in schools. Although teacher mobilizers have become a reference point for positive changes in education in Indonesia, their presence is still considered by many to have not contributed to schools. However, there are various different assessments regarding the existence of mobilizer teachers. A number of groups believe that the effectiveness of mobilizer teachers is still low, while others believe that mobilizer teachers have the potential to successfully advance learning in schools. Apart from that, research on mobilizer teachers is still very minimal in Indonesia so it does not provide comprehensive knowledge about the contribution of mobilizer teachers in Indonesia. This research aims to explore the role of mobilizer teachers in leading learning and driving learning communities and their impact on student learning. A qualitative approach was used in this research and a total of 13 teachers were interviewed. The findings of this research indicate that mobilizer teacher leadership is instructional leadership that effectively leads learning and mobilizes the teacher community in the school and region and contributes to student learning.

Change surface regression for nonlinear subgroup identification with application to warfarin pharmacogenomics data.

Pharmacogenomics stands as a pivotal driver toward personalized medicine, aiming to optimize drug efficacy while minimizing adverse effects by uncovering the impact of genetic variations on inter-individual outcome variability. Despite its promise, the intricate landscape of drug metabolism introduces complexity, where the correlation between drug response and genes can be shaped by numerous nongenetic factors, often exhibiting heterogeneity across diverse subpopulations. This challenge is particularly pronounced in datasets such as the International Warfarin Pharmacogenetic Consortium (IWPC), which encompasses diverse patient information from multiple nations. To capture the between-patient heterogeneity in dosing requirement, we formulate a novel change surface model as a model-based approach for multiple subgroup identification in complex datasets. A key feature of our approach is its ability to accommodate nonlinear subgroup divisions, providing a clearer understanding of dynamic drug-gene associations. Furthermore, our model effectively handles high-dimensional data through a doubly penalized approach, ensuring both interpretability and adaptability. We propose an iterative 2-stage method that combines a change point detection technique in the first stage with a smoothed local adaptive majorize-minimization algorithm for surface regression in the second stage. Performance of the proposed methods is evaluated through extensive numerical studies. Application of our method to the IWPC dataset leads to significant new findings, where 3 subgroups subject to different pharmacogenomic relationships are identified, contributing valuable insights into the complex dynamics of drug-gene associations in patients.

A multi-city COVID-19 forecasting model utilizing wastewater-based epidemiology.

The COVID-19 pandemic highlighted shortcomings in forecasting models, such as unreliable inputs/outputs and poor performance at critical points. As COVID-19 remains a threat, it is imperative to improve current forecasting approaches by incorporating reliable data and alternative forecasting targets to better inform decision-makers. Wastewater-based epidemiology (WBE) has emerged as a viable method to track COVID-19 transmission, offering a more reliable metric than reported cases for forecasting critical outcomes like hospitalizations. Recognizing the natural alignment of wastewater systems with city structures, ideal for leveraging WBE data, this study introduces a multi-city, wastewater-based forecasting model to categorically predict COVID-19 hospitalizations. Using hospitalization and COVID-19 wastewater data for six US cities, accompanied by other epidemiological variables, we develop a Generalized Additive Model (GAM) to generate two categorization types. The Hospitaization Capacity Risk Categorization (HCR) predicts the burden on the healthcare system based on the number of available hospital beds in a city. The Hospitalization Rate Trend (HRT) Categorization predicts the trajectory of this burden based on the growth rate of COVID-19 hospitalizations. Using these categorical thresholds, we create probabilistic forecasts to retrospectively predict the risk and trend category of six cities over a 20-month period for 1, 2, and 3week forecasting windows. We also propose a new methodology to measure forecasting model performance at change points, or time periods where sudden changes in outbreak dynamics occurred. We also explore the influence of wastewater as a predictor for hospitalizations, showing its inclusion positively impacts the model's performance. With this categorical forecasting study, we are able to predict hospital capacity risk and disease trends in a novel and useful way, giving city decision-makers a new tool to predict COVID-19 hospitalizations.

Hydrological drivers of flooding in Niamey (Niger): the role of the Sirba River

Abstract In recent decades, floods have become a major global concern. In Niamey (Niger) in West Africa, flooding is primarily caused by the significant increase in surface runoff resulting from heavy rainfall occuring between July and September in the upstream river basins of the three major tributaries of the Middle Niger River (Sirba, Gorouol and Dargol catchments). While the Sirba is empirically considered as the largest driver to flooding in Niamey, its contribution have not been precisely established. This study analyzes the influence of these tributaries on the Niger River discharges at Niamey during the rainy season, with a particular focus on the Sirba River basin. Daily annual maximum discharge (AMAX) data from 1990 to 2022 timeseries are used as inputs to various statistical analyses, including trend analyses, change point detection, concordance analysis and flood dependency assessment. The results reveal a significant change point in 2009 and increasing trends between the Sirba and Niger River stations. The flood propagation time delay varies from 1 to 4 days between the upstream river basins tributaries and Niamey station, with a strong concordance in peak discharges, particularly dominant with the Sirba River. The Dynamic Time Warping (DTW) and the Gumbel copula analyses highlighted the significant control of the Sirba River basin on flooding in Niamey, while also highlighting the important roles played by other tributaries. These findings are crucial for improving flood prevention and further refine urban flood management strategies in Niamey and other cities globally, affected by fluvial floods.&amp;#xD;

B-CAVE: A Robust Online Time Series Change Point Detection Algorithm Based on the Between-Class Average and Variance Evaluation Approach

B-CAVE: A Robust Online Time Series Change Point Detection Algorithm Based on the Between-Class Average and Variance Evaluation Approach