Trajectory Classification Research Articles

4D live tracing reveals distinct movement trajectories of meiotic chromosomes

Abstract Proper chromosome alignment at the spindle equator is a prerequisite for accurate chromosome segregation during cell division. However, the chromosome movement trajectories prior to alignment remain elusive. Here, we establish a 4D imaging analysis framework to visualize chromosome dynamics and develop a deep-learning model for chromosome movement trajectory classification. Our data reveal that chromosomes follow at least three distinct movement trajectories (retracing, congressing, and quasi-static) to arrive at the equator. We further revealed the distinct roles of multiple kinesin superfamily proteins (KIFs) in coordinating and maintaining the chromosome movement trajectories. In summary, we have presented an efficient and unbiased approach to studying chromosome dynamics during cell division, thereby uncovering a variety of chromosome movement trajectories that precede alignment.

A general image classification model for agricultural machinery trajectory mode recognition

Field-road trajectory classification is a crucial task for agricultural machinery behavior mode recognition, aiming to distinguish field operation mode and road driving mode automatically. However, the imbalanced distribution of agricultural machine trajectories brings challenges for the field-road trajectory classification task. Additionally, most existing field-road trajectory classification methods have certain shortcomings. For instance, they encounter difficulties in accurately representing the state of agricultural machinery movement using the current features. The data transformation process often leads to information loss, and the model’s generalization capabilities are limited. The performance of the models is constrained by each of these elements. To address these shortcomings, this paper introduces a general image classification model for agricultural machinery trajectory mode recognition named ATRNet. First, to address the issue of imbalanced field-road proportions in agricultural machinery trajectory data, a Conditional Tabular Generative Adversarial Network (CTGAN) is employed to generate quasi trajectories, balancing the distribution of positive and negative samples in the data. This step aims to eliminate biases during the model training process. Second, to accurately characterize the motion status of agricultural machinery, we propose a multiangle feature enhancement method to extract rich spatiotemporal features from trajectory data. Finally, different from conventional field-road trajectory classification models that primarily rely on spatial and temporal information for identifying trajectories, we present a lossless trajectory data representation paradigm. This paradigm maps each trajectory point into a “feature map” and uses an image classification model to capture latent feature representations of trajectory points for the recognition of different behavior modes of agricultural machinery. This paradigm can generalize image classification networks to the field-road trajectory classification task, providing a general vision model solution for agricultural machinery trajectory mode recognition. To validate the effectiveness of the ATRNet model, experiments were conducted on real corn and wheat harvester trajectory datasets. The results demonstrate that the proposed model achieves remarkable performance improvements over the state-of-the-art (SOTA) models. In the corn harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.34%, surpassing existing SOTA models by 3.12% and 12.46%, respectively. Similarly, in the wheat harvester trajectory dataset, ATRNet achieves an accuracy of 92.36% and an F1-score of 92.33%, outperforming the existing optimal algorithm by 4.76% and 18.18%, respectively.

Trajectory and predictors of post-stroke depression among patients with newly diagnosed stroke: A prospective longitudinal study

BackgroundPost-stroke depression (PSD) is the most prevalent neuropsychological disorder among stroke patients, affecting approximately one-third of stroke survivors at any one time after a stroke. We identified between-person associations between post-stroke depression trajectories across 3 timepoints and predictors affecting trajectory classification among stroke patients. MethodsThis is a prospective longitudinal study using a convenience sample of 119 participants from 2 tertiary hospitals from March 2022 to September 2022. Clinical assessments and data collection were performed at diagnosis (T1), 3 months (T2), and 6 months (T3) after diagnosis. The instruments were Demographic and Disease Information Sheet and PROMIS-Depression 8a. Data were analyzed using SPSS 27.0 for descriptive statistics, logistic regression, and the Mplus program for growth mixture model analysis. ResultsTwo stroke survivors depression trajectory classes (Class 1, moderate level decreasing- [37.8 %], and Class 2, high level increasing- [62.2%]) were delineated. Class 1 experienced moderate depression post-stroke, with a smooth diminishing pattern at T2 and T3, while Class 2 had a higher baseline depressive score and a significant increase at T2 and T3. The best growth mixture model was Class 2 model (LMR, p=0.010, BLRT, p≤0.01, AIC=2611.934, BIC=2650.842, aBIC=2606.583, Entropy= 0.944). The logistic regression results revealed that Class 2 of depression trajectory had a significant association with a lower score on cognitive function (B=-5.29, 95%CI: -8.80, -1.78, p <0.05) compared with Class 1. The stroke type, marital status, and monthly income were predictors of the Class 2 depression trajectory group among stroke patients. Precisely, ischemic stroke is associated with lower risk of class 2 trajectory. ConclusionThe trajectory of post-stroke depression changes over time. This research has the potential to serve as a foundation for the assessment of high-risk stroke patients, the development of precise management programs, the implementation of risk stratification, and the enhancement of prognosis.

Evaluation of Trajectory and Destination Prediction Models: A Systematic Classification and Analysis of Methodologies and Recent Results

Predicting trajectories and destinations is of considerable relevance in the context of urban mobility, as it can be useful for suggesting detours, avoiding congestion, and optimizing people's commutes. Therefore, this research performs a classification and analysis of trajectory and destination prediction models in articles published from 2017 to 2023. These models were mapped considering: authors; the existence of more than one geographic scenario; the type of forecast; the use of semantic and contextual data; and description of the algorithms. The result consists of discussions of representative works, based on classification, with grouping of techniques. Furthermore, there is a focus on works that used contextual and/or semantic data, from which another framework was developed, specifying the titles of the articles, and whether the methodology involved the use of points or areas of interest, and a reference to how they were generated. This focus expands the previous framework, specifying the differences of a portion of published studies.

6602 Classification of TSH Trajectories During Levothyroxine Treatment in the ELSA-Brasil Cohort

Abstract Disclosure: M.D. Ettleson: None. G.C. Penna: Consulting Fee; Self; Ipsen, Bayer, Inc.. W. Wan: None. I.M. Bensenor: None. N. Laiteerapong: None. A.C. Bianco: Consulting Fee; Self; Abbvie. Classification of TSH Trajectories During Levothyroxine Treatment in the ELSA-Brasil Cohort Introduction: Hypothyroidism is a common endocrine disorder for which levothyroxine (LT4) serves as the primary treatment. Periods during which thyroid stimulating hormone (TSH) levels are outside the normal range have been associated with adverse cardiovascular outcomes, including mortality. In practice, serial TSH levels are measured over time to ensure therapeutic LT4 treatment is maintained. However, there is no measure of the quality of treatment maintenance over time. TSH trajectory classification represents a novel approach to define the adequacy of LT4 treatment for hypothyroidism over time utilizing multiple observation points. Methods: With longitudinal clinical data, including thyroid function from a large prospective study, we aimed to define classes of TSH trajectories and examine changes in cardiovascular (CV) health markers over a 9 year study period with three observation points. Growth mixture modeling (GMM), including latent class growth analysis (LCGA), was used to classify LT4-treated individuals participating in the Longitudinal Study of Adult Health in Brazil (ELSA-Brasil) based on serial TSH levels. Repeated measure analyses were then utilized to measure within-class changes in blood pressure, lipid levels, hemoglobin A1c, and CV-related medication utilization. Results: From the 621 LT4-treated study participants, the best-fit GMM approach identified four TSH trajectory classes, as defined by their relationship to the normal TSH range: 1) High-high normal TSH, 2) Normal TSH, 3) Normal-to-low TSH, and 4) Low-to-normal TSH. Notably, the average baseline LT4 dose was lowest in the high-high normal TSH group (77.7 mcg, p &amp;lt;0.001). There were no significant differences in CV health markers between the classes at baseline. At least one significant difference in CV markers occurred in all classes, highlighted by the low-to-normal class, in which total and HDL cholesterol, triglycerides, and A1c all increased significantly (p = 0.049, p &amp;lt;0.001, p &amp;lt;0.001, and p = 0.001, respectively). Medication utilization increased in all classes over the study period. Conclusion: GMM/LCGA represents a viable approach to define and examine LT4 treatment by TSH trajectory. In the future, more comprehensive datasets will allow for more complex trajectory modeling and analysis of clinical outcome differences between trajectory classes. Defining the adequacy of LT4 treatment using a longitudinal scope could allow clinicians to more accurately communicate treatment progress and identify patients at risk for adverse CV outcomes. Presentation: 6/3/2024

Transitions in Suicide Risk from Early Adolescence to Early Adulthood

Objective Understanding patterns of suicide risk over the course of development can aid our ability to prevent suicide. Our community-based study examined changes in suicide risk status and predictors of changes in risk status in a sample of 521 adolescents over six assessments between the start of middle school and young adulthood (ages 12–22). Methods Suicidal thoughts and behaviors (STB) were measured with the Diagnostic Interview Schedule for Children and the Moods and Feelings Questionnaire. Latent transition analysis (LTA) was utilized to evaluate transitions in suicide risk status over the course of development. Nine risk factors’ initial values and change over time were modeled as predictors in the LTA. Results Latent class analysis identified a four-class model of developmental suicide risk patterns: Class 1: Infrequent STB (73–87% of participants), Class 2: Diminishing STB (1–17% of participants), Class 3: Escalating STB (6–16% of participants), and Class 4: Consistently High STB (1–5% of participants). LTA demonstrated that infrequent STB members and escalating STB members were likely to maintain their risk class across time points. Conclusions Classification of STB trajectories demonstrated self-worth and family involvement were salient variables affecting transitions in risk over time and suggest prevention targets early in adolescence that could have impact on suicide risk in adulthood.

PROSPECTIVE TRIAL OF HOME OPTICAL COHERENCE TOMOGRAPHY-GUIDED MANAGEMENT OF TREATMENT EXPERIENCED NEOVASCULAR AGE-RELATED MACULAR DEGENERATION PATIENTS.

To evaluate the impact of home optical coherence tomography (OCT)-guided patient management on treatment burden and visual outcomes. An interventional trial was conducted to compare frequency of treatment and visual acuity for the neovascular age-related macular degeneration patients before and during use of home optical coherence tomography over a period of 6 months. Patient adherence to regular scanning was measured by the number of scans performed per week. The characteristics of episodes of fluid recurrence and classification of typical fluid volume trajectories were performed. Twenty-seven eyes (21 with diagnosis of neovascular age-related macular degeneration and one converted during the study), of 15 patients were monitored for 6 months, scanning at 6.2 times/week per eye and yielding 4,435 scans of which 91.2% were eligible for artificial intelligence-based fluid volume quantification. Total number of monitoring weeks before and during the study were 1,555 and 509. The mean (SD) number of weeks per injection before and during home OCT management were 8.0 (4.7) and 15.3 (8.5) (P = 0.004), respectively. The mean (SD) visual acuity change before and during home OCT-based management was 3.5 (12.0) letters and 0.0 (9.5) letters (P = 0.45), respectively, showing no significant impact on visual acuity. For the first time, remote patient monitoring with a home OCT allowed personalized management of neovascular age-related macular degeneration. This study showed significant reduction in treatment burden while maintaining stable visual acuity.

Vessel trajectory classification via transfer learning with Deep Convolutional Neural Networks.

The classification of vessel trajectories using Automatic Identification System (AIS) data is crucial for ensuring maritime safety and the efficient navigation of ships. The advent of deep learning has brought about more effective classification methods, utilizing Convolutional Neural Networks (CNN). However, existing CNN-based approaches primarily focus on either sailing or loitering movement patterns and struggle to capture valuable features and subtle differences between these patterns from input images. In response to these limitations, we firstly introduce a novel framework, Dense121-VMC, based on Deep Convolutional Neural Networks (DCNN) with transfer learning for simultaneous extraction and classification of both sailing and loitering trajectories. Our approach efficiently performs in extracting significant features from input images and in identifying subtle differences in each vessel's trajectory. Additionally, transfer learning effectively reduces data requirements and addresses the issue of overfitting. Through extended experiments, we demonstrate the novelty of proposed Dense121-VMC framework, achieving notable contributions for vessel trajectory classification.

Extreme temperatures, PM2.5 and trajectories of impaired thyroid hormone sensitivity: A longitudinal study of patients with schizophrenia

BackgroundThe climate change scenario has witnessed an increase in extreme temperature events (ETEs), including heat waves and cold spells, and a heightened occurrence of compounding with fine particulate matter (PM2.5). However, the impact of this phenomenon on the sensitivity to thyroid hormones (THs) in humans is unclear, especially in a group as specific as schizophrenia. MethodsA longitudinal study was constructed using longitudinal measurements of thyroid function in schizophrenia in the Anhui Mental Health Center. The latent growth mixture model was applied to assess the optimal trajectory of change in impaired THs sensitivity. We then used logistic regression to explore associations between heat waves, cold spells, and PM2.5 with impaired THs sensitivity trajectories in the total population and different gender and age subgroups. Furthermore, the effect of the frequency, intensity, and duration of ETEs in the above associations was explored, as well as an assessment of the interaction between ETEs and PM2.5. ResultsAmong 931 participants, we identified two classifications of trajectories of impaired THs sensitivity: “Low-stable” (n = 836, 89.80 %) and “Rise-slight down” (n = 95, 10.20 %). Logistic regression showed significant associations between each additional day of heat waves (≥3 days with temperature thresholds above the 95th percentile) and cold spells (≥3 days with temperature thresholds below the 5th percentile) and “Rise-slight down” trajectory, with odds ratios (95 % confidence intervals) of 1.06 (1.02, 1.10) and 1.19 (1.14, 1.24), respectively, and the strength of this association increased with the intensity and duration of ETEs. Subgroup analyses indicated that the association was more pronounced in males and the age group above 40 years. Furthermore, PM2.5 was found to interact with heat waves, with high concentrations exacerbating the effects of heat waves. ConclusionsOur findings suggest that mitigating both ETEs and PM2.5 exposures may bring health co-benefits in preventing thyroid impairment in schizophrenia.

Transient motion classification and segment analysis of diffusive trajectories of G proteins and coupled-receptors in a living cell

The molecular movement in single particle tracking (SPT) experiments shows a crucial role of diffusion in many biological processes such as signaling, cellular organization, transport mechanisms, and more. The SPT analysis detects not only classical Brownian motion but diffusion with other features. These include directed diffusion and confined motion. The behavior remains a challenging problem for several reasons. Due to the action of many physical processes, random trajectories of cellular molecules are segmented in different diffusive modes. Often their study requires sophisticated algorithms for the analysis of statistical properties. In this paper we consider the segment analysis for trajectories of G proteins and coupled-receptors in living cells. Their movement is often transient and switches among free diffusion, confined diffusion, directed diffusion, and immobility. Moreover, the confined segments can have both Gaussian and non-Gaussian statistics. The types of alternation of diffusive modes along the trajectories of G proteins and coupled-receptors are analyzed.

Development, validation and use of custom software for the analysis of pain trajectories

In chronic musculoskeletal conditions, the prognosis tends to be more informative than the diagnosis for the future course of the disease. Many studies have identified clusters of patients who seemingly share similar pain trajectories. In a dataset of low back pain (LBP) patients, pain trajectories have been identified, and distinct trajectory types have been defined, making it possible to create pattern recognition software that can classify patients into respective pain trajectories reflecting their condition. It has been suggested that the classification of pain trajectories may create clinically meaningful subgroups of patients in an otherwise heterogeneous population of patients with LBP. A software tool was created that combined the ability to recognise the pain trajectory of patients with a system that could create subgroups of patients based on their characteristics. This tool is primarily meant for researchers to analyse trends in large heterogeneous datasets without large losses of data. Prospective analysis of pain trajectories is not directly helpful for clinicians. However, the tool might aid in the identification of patient characteristics which have predictive capabilities of the most likely trajectory a patient might experience in the future. This will help clinicians to tailor their advice and treatment for a specific patient.

Port performance indicators construction based on the AIS-generated trajectory segmentation and classification

AbstractWith coverage of worldwide shipping routes and straightforward accessibility, vessels’ navigational data from AIS have emerged as a potential leading source of knowledge for maritime stakeholders. However, transforming the raw AIS messages into meaningful indicators requires comprehensive work that involves enrichment with multiple relevant data sources. In this study, a fain-grained technique to process AIS tracks for the purpose of constructing port performance indicators is proposed. The technique involves trajectory segmentation to separate the stopping and underway segments of AIS-generated trajectories and trajectory classification to identify moored and at-anchor vessels from the stopping segments. With the fusion of relevant information, the method estimates the port boundary and identifies the associated berthing and anchorage locations to estimate turnaround time and construct port connectivity indicators. AIS datasets recorded over eight months covering the waters of Indonesia, Malaysia, and Singapore, known as one of the world’s busiest shipping routes, are selected to evaluate the proposed method. The trajectory segmentation demonstrated 98–99% accuracy, while the classification achieved 95–97%. The estimation of the vessel turnaround time closely matched the UNCTAD data with an error rate of 2.9%. These results prove the proposed approach’s practicality in contributing to the real-world scenario.

Trajectory Classification and Recognition of Planar Mechanisms Based on ResNet18 Network

Trajectory Classification and Recognition of Planar Mechanisms Based on ResNet18 Network

A trajectory similarity computation method based on GAT-based transformer and CNN model

Trajectory similarity computation is very important for trajectory data mining. It is applied into many trajectory mining tasks, including trajectory clustering, trajectory classification and trajectory search etc. So efficient trajectory similarity computation method is very useful for improving trajectory mining result. Nowadays many trajectory similarity computation methods have been proposed. But most of them can not be applied into long trajectories similarity calculation efficiently. So a new algorithm called TrajGAT is proposed. This algorithm can calculate similarity for long trajectories. It treats long trajectory as a long sequence. By doing so, long-term dependency of long trajectory is considered by this algorithm while computing similarity value. But, the spatial feature of long trajectories is not considered. As long trajectory can be presented in many different shapes, if two long trajectories are judged as similar trajectories, the outline shape of these two trajectories should be similar as well. To solve this problem, a new trajectory similarity computation method is proposed in this paper. This method not only takes the long-term dependence feature into consideration, but also considers the outline feature of long trajectory. The proposed method employs GAT-based transformer to extract long-term dependence feature from long trajectory. And it applies Convolutional Neural Network to extract outline feature.

Personality traits and co-occurrence of depressive symptoms and high BMI: a prospective cohort study.

We assess the associations between personality traits and co-occurrence of depressive symptoms and high BMI from adolescence to early adulthood. We employed a nationally representative cohort in China from 2010 to 2020 year. We included adolescents aged 10-19 years without depressive symptoms and unhealthy weight status (obesity, overweight, or thinness) at baseline and excluded those without any measurement of depressive symptoms or BMI at follow-ups. We assessed baseline personality traits in 7 dimensions of conscientiousness, openness, neuroticism, agreeableness, extraversion, self-esteem, and responsibility. We also assessed the combined effects of these 7 dimensions of personality traits by generating individual-level personality trait risk scores based on the weighted sum of all these 7 dimensions of personality traits. We measured the co-occurrence of depressive symptoms and high BMI using both a single measurement of depressive symptoms and BMI at the last follow-up and repeated measurements of them over 10 years. We used the multinomial logistic regression models to examine the exposure-outcome associations. At baseline, we included 1778 individuals (mean age: 14.4 year; female: 853 (48.0%)). At follow-ups, we observed increased risk of co-occurrence of depressive symptoms and high BMI per 1-SD increase in neuroticism score (1.95-2.38 odds ratio) or 1-SD decrease in self-esteem and conscientiousness (0.63-0.80 odds ratio; all P values < 0.05); we observed no evidence of associations between openness, agreeableness, extraversion, or responsibility and the risk of co-occurrence of depressive symptoms and high BMI (all P values > 0.05). For the combined effects of the 7 dimensions of personality traits, we found an elevated risk of co-occurrence of depressive symptoms and high BMI per 1-SD increase in the personality trait risk scores (OR (95% CI), single measurement at the last follow-up: 2.01, 1.66 to 2.43; trajectory classification using the repeated measurements 2.30, 1.55 to 3.42; average level using the repeated measurements: 2.27, 1.93 to 2.67). In this national cohort in China, personality traits were found to be associated with the co-occurrence of depressive symptoms and high BMI from adolescence to early adulthood. These findings highlight the importance of stratifying individuals based on their personality traits and providing targeted interventions for those at risk of comorbid depression and obesity.

Ship Trajectory Classification Prediction at Waterway Confluences: An Improved KNN Approach

This study presents a method to support ship trajectory prediction at waterway confluences using historical Automatic Identification System (AIS) data. The method is meant to improve the recognition accuracy of ship behavior trajectory, assist in the proactive avoidance of collisions, and clarify ship collision responsibility, to ensure the safety of waterway transportation systems in the event of ship encounters induced by waterway confluence or channel limitation. In this study, the ship trajectory based on AIS data is considered from five aspects: time, location, heading, speed, and trajectory by using the piecewise cubic Hermite interpolation method and then quickly clustered by regional navigation rules. Then, an improved K-Nearest Neighbor Algorithm considering the sensitivity of data characteristics (SKNN) is proposed to predict the trajectory of ships, which considers the influence weights of various parameters on ship trajectory prediction. The method is trained and verified using the AIS data of the Yangtze River and Han River intersection in Wuhan. The results show that the accuracy of SKNN is better than that of conventional KNN and Naive Bayes (NB) in the same test case. The accuracy of the ship trajectory prediction method is above 99% and the performance metrics of the SKNN surpass those of both the conventional KNN and NB classifiers, which is helpful for early warning of collision encounters to ensure avoidance.

Fractional Lévy Stable Motion from a Segmentation Perspective

The segmentation analysis of the Golding–Cox mRNA dataset clarifies the description of these trajectories as a Fractional Lévy Stable Motion (FLSM). The FLSM method has several important advantages. Using only a few parameters, it allows for the detection of jumps in segmented trajectories with non-Gaussian confined parts. The value of each parameter indicates the contribution of confined segments. Non-Gaussian features in mRNA trajectories are attributed to trajectory segmentation. Each segment can be in one of the following diffusion modes: free diffusion, confined motion, and immobility. When free diffusion segments alternate with confined or immobile segments, the mean square displacement of the segmented trajectory resembles subdiffusion. Confined segments have both Gaussian (normal) and non-Gaussian statistics. If random trajectories are estimated as FLSM, they can exhibit either subdiffusion or Lévy diffusion. This approach can be useful for analyzing empirical data with non-Gaussian behavior, and statistical classification of diffusion trajectories helps reveal anomalous dynamics.

Research on A Ship Trajectory Classification Method Based on Deep Learning

The unrestricted development and utilization of marine resources have resulted in a series of practical problems, such as the destruction of marine ecology. The wide application of radar, satellites and other detection equipment has gradually led to a large variety of large-capacity marine spatiotemporal trajectory data from a vast number of sources. In the field of marine domain awareness, there is an urgent need to use relevant information technology means to control and monitor ships and accurately classify and identify ship behavior patterns through multisource data fusion analysis. In addition, the increase in the type and quantity of trajectory data has produced a corresponding increase in the complexity and difficulty of data processing that cannot be adequately addressed by traditional data mining algorithms. Therefore, this paper provides a deep learning-based algorithm for the recognition of four main motion types of the ship from automatic identification system (AIS) data: anchoring, mooring, sailing and fishing. A new method for classifying patterns is presented that combines the computer vision and time series domains. Experiments are carried out on a dataset constructed from the open AIS data of ships in the coastal waters of the United States, which show that the method proposed in this paper achieves more than 95\% recognition accuracy. The experimental results confirm that the method proposed in this paper is effective in classifying ship trajectories using AIS data and that it can provide efficient technical support for marine supervision departments.

BiSAMNet: A Novel Approach in Maritime Data Completion Using Deep Learning and NLP Techniques

In the extensive monitoring of maritime traffic, maritime management frequently encounters incomplete automatic identification system (AIS) data. This deficiency poses significant challenges to safety management, requiring effective methods to infer corresponding ship information. We tackle this issue using a classification approach. Due to the absence of a fixed road network at sea unlike on land, raw trajectories are difficult to convert and cannot be directly fed into neural networks. We devised a latitude–longitude gridding encoding strategy capable of transforming continuous latitude–longitude data into discrete grid points. Simultaneously, we employed a compression algorithm to further extract significant grid points, thereby shortening the encoding sequence. Utilizing natural language processing techniques, we integrate the Word2vec word embedding approach with our novel biLSTM self-attention chunk-max pooling net (biSAMNet) model, enhancing the classification of vessel trajectories. This method classifies targets into ship types and ship lengths within static information. Employing the Taiwan Strait as a case study and benchmarking against CNN, RNN, and methods based on the attention mechanism, our findings underscore our model’s superiority. The biSAMNet achieves an impressive trajectory classification F1 score of 0.94 in the ship category dataset using only five-dimensional word embeddings. Additionally, through ablation experiments, the effectiveness of the Word2vec pre-trained embedding layer is highlighted. This study introduces a novel method for handling ship trajectory data, addressing the challenge of obtaining ship static information when AIS data are unreliable.

TSH Trajectories During Levothyroxine Treatment in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) Cohort.

Thyroid-stimulating hormone (TSH) trajectory classification represents a novel approach to defining the adequacy of levothyroxine (LT4) treatment for hypothyroidism over time. This is a proof of principle study that uses longitudinal clinical data, including thyroid hormone levels from a large prospective study to define classes of TSH trajectories and examine changes in cardiovascular (CV) health markers over the study period. Growth mixture modeling (GMM), including latent class growth analysis (LCGA), was used to classify LT4-treated individuals participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) based on serial TSH levels. Repeated measure analyses were then utilized to assess within-class changes in blood pressure, lipid levels, hemoglobin A1c, and CV-related medication utilization. From the 621 LT4-treated study participants, the best-fit GMM approach identified 4 TSH trajectory classes, as defined by their relationship to the normal TSH range: (1) high-high normal TSH, (2) normal TSH, (3) normal to low TSH, and (4) low to normal TSH. Notably, the average baseline LT4 dose was lowest in the high-high normal TSH group (77.7 µg, P < .001). There were no significant differences in CV health markers between the classes at baseline. At least 1 significant difference in CV markers occurred in all classes, highlighted by the low to normal class, in which total and high-density lipoprotein cholesterol, triglycerides, and A1c all increased significantly (P = .049, P < .001, P < .001, and P = .001, respectively). Utilization of antihypertensive, antihyperlipidemic, and antidiabetes medications increased in all classes. GMM/LCGA represents a viable approach to define and examine LT4 treatment by TSH trajectory. More comprehensive datasets should allow for more complex trajectory modeling and analysis of clinical outcome differences between trajectory classes.