Segmented Regression Approach Research Articles

Spatial behaviors of HFMD hospital visits across regions of various urbanicity levels in Nanchang, China

Hand foot mouth disease (HFMD) is one of the widespread transmissible diseases that target preschool children, especially in urban regions in East Asia. Based on the mobile app data, a GIS automated regionalization method is used to define regions of various urbanicity levels. The variability of HFMD patients’ travel behaviors across these regions are examined by the complementary cumulative distribution functions (CCDFs). The travel burden in Nanchang increased as the patients’ residences moved toward regions of more rurality. Specifically, more urbanized regions near the city center (i.e., urban core and its surrounding urban) enjoyed better access to the healthcare service by spending an average of about 17-minute drive time. Patients residing in less urbanized regions such as suburbs and downtowns of surrounding rural counties either chose a nearby hospital or journeyed far to the region’s central Children’s Hospital, with average elevated travel time of 25 and 22 min, respectively. Those in rural areas travelled an average of 36 min, the longest among all regions. The study also finds a unique dual-peak pattern across two travel ranges in the study area due to the patients’ dilemma between pursuing high-quality hospitals and accommodating travel burden. Such a pattern mandates the adoption of a segmented regression approach to deriving the best-fitting CCDFs in most regions except for the rural.

Rapid outpatient transient ischemic attack clinic and stroke service activity during the SARS-CoV-2 pandemic: a multicenter time series analysis.

Rapid outpatient evaluation and treatment of TIA in structured clinics have been shown to reduce stroke recurrence. It is unclear whether short-term downtrends in TIA incidence and admissions have had enduring impact on TIA clinic activity. This study aims to measure the impact of the pandemic on hospitals with rapid TIA clinics. Relevant services were identified by literature search and contacted. Three years of monthly data were requested - a baseline pre-COVID period (April 2018 to March 2020) and an intra-COVID period (April 2020 to March 2021). TIA presentations, ischemic stroke presentations, and reperfusion trends inclusive of IV thrombolysis (IVT) and endovascular thrombectomy (EVT) were recorded. Pandemic impact was measured with interrupted time series analysis, a segmented regression approach to test an effect of an intervention on a time-dependent outcome using a defined impact model. Six centers provided data for a total of 6,231 TIA and 13,191 ischemic stroke presentations from Australia (52.1%), Canada (35.0%), Italy (7.6%), and England (5.4%). TIA clinic volumes remained constant during the pandemic (2.9, 95% CI -1.8 to 7.6, p = 0.24), as did ischemic stroke (2.9, 95% CI -7.8 to 1.9, p = 0.25), IVT (-14.3, 95% CI -36.7, 6.1, p < 0.01), and EVT (0, 95% CI -16.9 to 16.9, p = 0.98) counts. Proportion of ischemic strokes requiring IVT decreased from 13.2 to 11.4% (p < 0.05), but those requiring EVT did not change (16.0 to 16.7%, p = 0.33). This suggests that the pandemic has not had an enduring effect on TIA clinic or stroke service activity for these centers. Furthermore, the disproportionate decrease in IVT suggests that patients may be presenting outside the IVT window during the pandemic - delays in seeking treatment in this group could be the target for public health intervention.

K-sharp: A segmented regression approach for image sharpening and normalization

In recent decades, Earth Observation (EO) satellite missions have improved in spatial resolution and revisit times. These missions, traditionally government-funded, utilize state-of-the-art technology and rigorous instrument calibration, with each mission costing millions of dollars. Recently, nano-satellites known as CubeSats are presenting a cost-effective option for EO; their capacity of working as a constellation has brought an unprecedented opportunity for EO in terms of achievable spatial and temporal resolutions, albeit at the cost of decreased accuracy and cross-sensor consistency. As such, CubeSat datasets often require post-calibration approaches before using them for scientific applications. K-sharp is a relatively simple, data-agnostic machine learning approach that combines K-means and partial least squares regression to derive relationships between two sets of images for normalization. This study used Planet's four-band CubeSat imagery to sharpen day-coincident Landsat 8 normalized difference vegetation index, albedo, and the first short-wave infrared (SWIR) band from 30 m to 3 m spatial resolution (it should be noted that the four-band CubeSat product does not include the first SWIR band, and that the calculation of albedo is not directly possible from this product). K-sharp was tested over agricultural, savanna, rainforest, and tundra sites with and without atmospheric correction. Our model reproduced surface conditions with an average r2 of 0.88 (rMAE = 11.39%) across all study sites and target variables when compared against the original Landsat 8 data. These results showcase the promising potential of K-sharp in generating precise, CubeSat-derived datasets with high radiometric quality, which can be incorporated into agricultural or ecological applications to enhance their decision-making process at fine spatial scales.

Analysis of Indian Port Performance Post Reforms in an Overlapping Hinterland: A Segmented Regression Approach

India has about 12 major ports under the aegis of the Indian Government, in its approximately 7,500 km long coastline and competing with another 200 state- government-run ones. Over the last 20 years, the Indian government has implemented several reforms. This article answers two research questions. RQ1: Have port reforms improved port performance? RQ2: Do ports with overlapping hinterlands compete, or does one port’s performance complement the other? The article proposed a composite operational port performance index (PPI) and carried out a breakpoint (segmented) regression analysis to study the impact of port reforms. This article makes three crucial propositions––First, port performance affects its output, that is, the ship calls when competition is high, but the same does not hold if the port enjoys monopoly or oligopoly status or due to other factors such as cargo demand. Second, performance of ports with lower capacity, also referred to as satellite ports, is affected by the performance of its complementing ports with higher capacity. Third, Reforms may lead to competition and cannibalisation of profits and growth of ports in a dynamic environment.

Uptake of evidence by physicians: De-adoption of erythropoiesis-stimulating agents after the TREAT trial

BackgroundVariation in de-adoption of ineffective or unsafe treatments is not well-understood. We examined de-adoption of erythropoiesis-stimulating agents (ESA) in anemia treatment among patients with chronic kidney disease (CKD) following new clinical evidence of harm and ineffectiveness (the TREAT trial) and the FDA’s revision of its safety warning.MethodWe used a segmented regression approach to estimate changes in use of epoetin alfa (EPO) and darbepoetin alfa (DPO) in the commercial, Medicare Advantage (MA) and Medicare fee-for-service (FFS) populations. We also examined how changes in both trends and levels of use were associated with physicians’ characteristics.ResultsUse of DPO and EPO declined over the study period. There were no consistent changes in DPO trend across insurance groups, but the level of DPO use decreased right after the FDA revision in all groups. The decline in EPO use trend was faster after the TREAT trial for all groups. Nephrologists were largely more responsive to evidence than primary care physicians. Differences by physician’s gender, and age were not consistent across insurance populations and types of ESA.ConclusionsPhysician specialty has a dominant role in prescribing decision, and that specializations with higher use of treatment (nephrologists) were more responsive to new evidence of unsafety and ineffectiveness.

Impact of Critical Illness Insurance on the Burden of High-Cost Rural Residents in Central China: An Interrupted Time Series Study.

Critical illness insurance (CII) in China was introduced to protect high-cost groups from health expenditure shocks for the purpose of mutual aid. This study aimed to evaluate the impact of CII on the burden of high-cost groups in central rural China. Data were extracted from the basic medical insurance (BMI) hospitalization database of Xiantao City from January 2010 to December 2016. A total of 77,757 hospitalization records were included in our analysis. The out-of-pocket (OOP) expenses and reimbursement ratio (RR) were the two main outcome variables. Interrupted time series analysis with a segmented regression approach was adopted. Level and slope changes were reported to reflect short- and long-term effects, respectively. Results indicated that the number of high-cost inpatient visits, the average monthly hospitalization expenses, and OOP expenses per high-cost inpatient visit were increased after CII introduction. By contrast, the RR from BMI and non-reimbursable expenses ratio were decreased. The OOP expenses and RR covered by CII were higher than those uncovered. We estimated a significant level decrease in OOP expenses (p < 0.01) and rise in RR (p < 0.01), whereas the slope decreases of OOP expenses (p = 0.19) and rise of RR (p = 0.11) after the CII were non-significant. We concluded that the short-term effect of the CII policy is significant and contributes to decreasing OOP expenses and raising RR for high-cost groups, whereas the long-term effect is non-significant. These findings can be explained by increasing hospitalization expenses, many non-reimbursable expenses, low coverage for high-cost groups, and the unsustainability of the financing methods.

Calendar effects to forecast influenza seasonality: A case study in Milwaukee, WI

Calendar effects to forecast influenza seasonality: A case study in Milwaukee, WI

An electronic cardiac rehabilitation referral system increases cardiac rehabilitation referrals.

Although cardiac rehabilitation attendance is associated with improved clinical outcomes for patients after acute myocardial infarction (AMI), it remains underutilized nationally. We sought to determine whether replacing traditional, paper-based referrals for cardiac rehabilitation for patients with AMI with an electronic referral system would increase utilization. We implemented the change from traditional, paper-based referrals to electronic referrals at the Massachusetts General Hospital on 10 December 2013. Using a segmented regression approach to control for other secular effects, we assessed an association between the intervention and inpatient referrals, total referrals, cardiac rehabilitation attendance at Massachusetts General Hospital, and the rate of inpatient referral to cardiac rehabilitation after AMI. We analyzed 1895 referral records over a 30-month period. After the intervention, the total referrals to our cardiac rehabilitation program increased by a factor of 1.8, largely attributable to a 17-fold increase in inpatient referrals (P<0.0001 for both). Even relative to pre-existing secular trends, switching to an electronic referral system was associated with an increase in referral volume for cardiac rehabilitation for patients with AMI. Electronic care innovations may improve the ability of provider organizations to provide guideline-oriented care for patients with coronary artery disease.

Modeling of Gibbs energies of pure elements down to 0 K using segmented regression

A novel thermodynamic modeling strategy of stable solid alloy phases is proposed based on segmented regression approach. The model considers several physical effects (e.g. electronic, vibrational, etc.) and is valid from 0K up to the melting temperature. The preceding approach has been applied for several pure elements. Results show good agreement with experimental data at low and high temperatures. Since it is not a first attempt to propose a “universal” physical-based model down to 0K for the pure elements as an alternative to current SGTE description, we also compare the results to existing models. Analysis of the obtained results shows that the newly proposed model delivers more accurate description down to 0K for all studied pure elements according to several statistical tests.

Evaluation of rate trend patterns via segmented regression: Case study of crime rates of Pakistan

In many practical regression-type problems, one uniform regression function to the data was found inappropriate, since the functional relationship between the response and the regressor(s) changes at certain points of regressors. These points are usually called break points or change points. In such situations, regression models are applied that are obtained by a piecewise definition of the regression function. Simply, by parts regression is used to detect an abrupt change of the response function at an increase or decrease of an influential factor, and named as segmented regression. Theoretical efforts have been made in the subject when parameters of a linear regression system obeying separate regimes. A case study concerning the crime rates in Pakistan is carried out by segmented regression approach as a comparative overview of linear regression approach and the segmented regression approach. Segmented regression approach was found to be more opposite than that of linear regression analysis on the basis of Bayesian information criteria and permutation test criteria. Key words: Change point, permutation test, rate trends, segmented regression.

Short-term Effect of High Temperatures on Mortality in Mediterranean Cities: Results From the Circe Project

O-30A3-6 Background/Aims: Climate change predictions estimate an increase in temperatures and extreme events especially in the Mediterranean area. The impact of high temperatures on mortality in European cities are well known, while the effect in urban areas of North Africa and the Middle East are to date limited. This study, carried out within the CIRCE EU Project, aims to assess the impact of extreme temperatures on mortality in 10 Mediterranean cities (Athens, Bari, Barcelona, Istanbul, Lisbon, Palermo, Rome, Telaviv, Tunis, and Valencia). The analysis allows the comparison of the effect among the more temperate European and drier North African and Middle Eastern areas of the Mediterranean. Methods: Maximum apparent temperature (Tappmax) was chosen as exposure variable to estimate the impact on total mortality (by age groups) during summer. The segmented regression approach was used to identify city-specific threshold values of Tappmax, corresponding to the minimum mortality rate. A time-series approach was used to estimate the percent increase in mortality for 1°C increase in Tappmax above the city-specific threshold. Results: Great heterogeneity among cities was observed in the exposure and in the threshold values, ranging from 25°C in Lisbon to 36°C in Tunis. The Tappmax-mortality relationship showed a J-shaped curve in most cities, with a significant impact of high temperatures on mortality above the threshold, but in the hottest cities as Telaviv, Tunis and Valencia the relationship was weaker. In most cities, the greatest impact of high temperatures on mortality was found in the 65+ age group, ranging from +1.71% in Telaviv to +6.15% in Rome; while in the 0–64 age group the impact was higher in Lisbon (+9.21%) and Telaviv (+3.60%). Conclusion: The impact of high temperatures on mortality was heterogeneous among the Mediterranean cities, although the greatest impact on mortality wasn't in the hottest cities, suggesting local population adaptation to heat.

Using segmented regression to model the density–size relationship in direct-seeded slash pine stands

This study investigated the application of segmented regression techniques to modeling the trajectory of tree density and quadratic mean diameter through time for individual stands. The full model contains three segments for characterizing the three different stages of the trajectory on a log–log scale. The first segment represents precanopy conditions where no mortality is expected after what normally occurs before initial tree establishment. The next two segments are quadratic functions to accommodate two distinct mortality rates if present in the trajectory. Quadratic functions were selected based on published trajectories for loblolly pine ( Pinus taeda L.) and slash pine ( Pinus elliottii var. elliottii Engelm.) in southeastern U.S. A reduced model is formed by simply joining two quadratic segments. Data from direct-seeded slash pine stands used in this study fit the reduced model. The two-segment model requires a join point, which was predicted as a power function of the logarithm of initial stand density. The resulting trajectories matched observed trends in the data reasonably well. The segmented regression approach is appealing for modeling very complicated functional forms such as the density–size relationship presented in this paper.