Disease Trajectory In Patients Research Articles

Towards Predictive Analysis on Disease Progression: A Variational Hawkes Process Model.

Massively available longitudinal data about long-term disease trajectories of patients provides a golden mine for the understanding of disease progression and efficient health service delivery. It calls for quantitative modeling of disease progression, which is a tricky problem due to the complexity of the disease progression process as well as the irregularity of time documented in trajectories. In this study, we tackle the problem with the goal of predictively analyzing disease progression. Specifically, we propose a novel Variational Hawkes Process (VHP) model to generalize disease progression and predict future patient states based on the clinical observational data of past disease trajectories. First, Hawkes Process captures the intensity of irregular visits in a trajectory documented to medical facilities and controls the aforementioned information flowing into future visits. Thereafter, the captured intensity is incorporated into a Variational Auto-Encoder to generate the representation of the future partial disease trajectory for a target patient in a predictive manner. To further improve the prediction performance, we equip the proposed model with a disease trajectory discriminator to distinguish the generated trajectories from real ones. We evaluate the proposed model on two public datasets from the MIMIC-III database pertaining to heart failure and sepsis patients, respectively, and one real-world dataset from a Chinese hospital pertaining to heart failure patients with multiple admissions. Experimental results demonstrate that the proposed model significantly outperforms state-of-the-art baselines, and may derive a set of practical implications that can benefit a wide spectrum of management and applications on disease progression.

Key factors in a rigorous longitudinal image-based assessment of retinopathy of prematurity

To describe a database of longitudinally graded telemedicine retinal images to be used as a comparator for future studies assessing grader recall bias and ability to detect typical progression (e.g. International Classification of Retinopathy of Prematurity (ICROP) stages) as well as incremental changes in retinopathy of prematurity (ROP). Cohort comprised of retinal images from 84 eyes of 42 patients who were sequentially screened for ROP over 6 consecutive weeks in a telemedicine program and then followed to vascular maturation or treatment, and then disease stabilization. De-identified retinal images across the 6 weekly exams (2520 total images) were graded by an ROP expert based on whether ROP had improved, worsened, or stayed the same compared to the prior week’s images, corresponding to an overall clinical “gestalt” score. Subsequently, we examined which parameters might have influenced the examiner’s ability to detect longitudinal change; images were graded by the same ROP expert by image view (central, inferior, nasal, superior, temporal) and by retinal components (vascular tortuosity, vascular dilation, stage, hemorrhage, vessel growth), again determining if each particular retinal component or ROP in each image view had improved, worsened, or stayed the same compared to the prior week’s images. Agreement between gestalt scores and view, component, and component by view scores was assessed using percent agreement, absolute agreement, and Cohen’s weighted kappa statistic to determine if any of the hypothesized image features correlated with the ability to predict ROP disease trajectory in patients. The central view showed substantial agreement with gestalt scores (κ = 0.63), with moderate agreement in the remaining views. Of retinal components, vascular tortuosity showed the most overall agreement with gestalt (κ = 0.42–0.61), with only slight to fair agreement for all other components. This is a well-defined ROP database graded by one expert in a real-world setting in a masked fashion that correlated with the actual (remote in time) exams and known outcomes. This provides a foundation for subsequent study of telemedicine’s ability to longitudinally assess ROP disease trajectory, as well as for potential artificial intelligence approaches to retinal image grading, in order to expand patient access to timely, accurate ROP screening.

Sequential Patterns of Multimorbidity in a Nationally Representative Cohort Study of Aging

Multimorbidity – the presence of two or more chronic health conditions – is common among older adults. Despite this, relatively little is known about the epidemiology of specific sequences of disease onset that occurs in mid-life and older adults over time. This may be attributed to the sheer number of possible permutations, which is difficult to handle with traditional methods. This is a retrospective cohort study using the Health & Retirement Study (HRS), a nationally-representative panel survey of aging. The study population included all adults age 50 and older that had no reported chronic disease at baseline (n=5567). We use a data mining algorithm, Sequential Pattern Discovery using Equivalence classes (SPADE), to identify all possible sequences of eight self-reported age-related chronic diseases: hypertension, arthritis, diabetes, cancer, stroke, heart disease, chronic lung disease, and psychiatric disorders. There were 67 unique sequences of disease identified that occurred in at least 1% of the study population. The most common two event sequence was Arthritis=>Hypertension (15.5% of all subjects), and the second most common was Hypertension=>Arthritis (9.6%). The most common three-way sequence was Arthritis=>Hypertension=>Heart Disease (1.8%). Arthritis=>Stroke occurred in 1.5% of subjects and was associated with the highest mortality rate (71.3% of subjects died). Sequential pattern mining allows for the discovery of longitudinal patterns of disease that frequently occur in older adults and advancements in our understanding of the epidemiology of multimorbidity. Future applications may include predicting a given patient's disease trajectory based on their life course and disease history.

Plasma biomarkers of inflammation reflect disease state in autosomal dominant forms of familial frontotemporal dementia

AbstractBackgroundImmune dysregulation may influence disease pathogenesis in familial frontotemporal dementia (fFTD), but the utility of peripheral biomarkers of inflammation remains unclear in this cohort. We sought to investigate candidate plasma biomarkers of immune function within a large cohort of fFTD kindreds from the ARTFL and LEFFTDS Consortia.MethodsWe examined plasma samples from 148 non‐carrier healthy controls and 256 asymptomatic and symptomatic individuals carrying autosomal dominant fFTD‐associated mutations (n=73 MAPT, n=120 C9ORF72, and n=63 GRN). ELISA was used to measure three plasma biomarkers of inflammation (YKL‐40, TNF‐α,IL‐6). We used Mann–Whitney U tests to compare concentrations amongst controls and subgroups of fFTD differing in disease severity, defined by the Clinical Dementia Rating Scale plus National Alzheimer’s Disease Coordinating Center Frontotemporal Lobar Degeneration Behavior and Language Domains (CDR® plus NACC FTLD) global score (asymptomatic=0, early symptomatic=0.5, late symptomatic ≥1). We also used linear mixed models to assess the utility of baseline inflammatory biomarkers in predicting the subsequent annual rate of decline in functional clinical severity (CDR® plus NACC FTLD sum of boxes) and psychomotor speed (Trails A).ResultsPlasma YKL‐40 concentrations were elevated in late symptomatic fFTD (59.3ng/ml [50.1]) relative to controls (32.9ng/ml [24.0]) (p=0.0003) and asymptomatic mutation carriers (30.9ng/ml [25.4], p=0.0001). Plasma TNF‐α concentrations were relatively low in asymptomatic mutation carriers (1.96pg/ml [0.56]) compared to early symptomatic fFTD (2.35pg/ml [0.83], p= 0.009). Amongst mutation carriers (including 140 with follow up clinical data), higher baseline plasma IL‐6 and YKL‐40 concentrations were associated with greater increase in functional clinical severity and declines in psychomotor speed, respectively.ConclusionPlasma biomarkers of inflammation increase with disease severity in fFTD and predict worse clinical trajectories. While the role of inflammation remains unclear in familial FTD, plasma markers of inflammation appear to reflect the processes influencing disease trajectory in patients carrying mutations associated with familial frontotemporal dementia.

A system-level analysis of patient disease trajectories based on clinical, phenotypic and molecular similarities.

Incorporating the temporal dimension into multimorbidity studies has shown to be crucial for achieving a better understanding of the disease associations. Furthermore, due to the multifactorial nature of human disease, exploring disease associations from different perspectives can provide a holistic view to support the study of their aetiology. In this work, a temporal systems-medicine approach is proposed for identifying time-dependent multimorbidity patterns from patient disease trajectories, by integrating data from electronic health records with genetic and phenotypic information. Specifically, the disease trajectories are clustered using an unsupervised algorithm based on dynamic time warping and three disease similarity metrics: clinical, genetic and phenotypic. An evaluation method is also presented for quantitatively assessing, in the different disease spaces, both the cluster homogeneity and the respective similarities between the associated diseases within individual trajectories. The latter can facilitate exploring the origin(s) in the identified disease patterns. The proposed integrative methodology can be applied to any longitudinal cohort and disease of interest. In this article, prostate cancer is selected as a use case of medical interest to demonstrate, for the first time, the identification of temporal disease multimorbidities in different disease spaces. https://gitlab.com/agiannoula/diseasetrajectories. Supplementary data are available at Bioinformatics online.

Identification and prediction of novel classes of long-term disease trajectories for patients with juvenile dermatomyositis using growth mixture models.

ObjectivesUncertainty around clinical heterogeneity and outcomes for patients with JDM represents a major burden of disease and a challenge for clinical management. We sought to identify novel classes of patients having similar temporal patterns in disease activity and relate them to baseline clinical features.MethodsData were obtained for n = 519 patients, including baseline demographic and clinical features, baseline and follow-up records of physician’s global assessment of disease (PGA), and skin disease activity (modified DAS). Growth mixture models (GMMs) were fitted to identify classes of patients with similar trajectories of these variables. Baseline predictors of class membership were identified using Lasso regression.ResultsGMM analysis of PGA identified two classes of patients. Patients in class 1 (89%) tended to improve, while patients in class 2 (11%) had more persistent disease. Lasso regression identified abnormal respiration, lipodystrophy and time since diagnosis as baseline predictors of class 2 membership, with estimated odds ratios, controlling for the other two variables, of 1.91 for presence of abnormal respiration, 1.92 for lipodystrophy and 1.32 for time since diagnosis. GMM analysis of modified DAS identified three classes of patients. Patients in classes 1 (16%) and 2 (12%) had higher levels of modified DAS at diagnosis that improved or remained high, respectively. Patients in class 3 (72%) began with lower DAS levels that improved more quickly. Higher proportions of patients in PGA class 2 were in DAS class 2 (19%, compared with 16 and 10%).ConclusionGMM analysis identified novel JDM phenotypes based on longitudinal PGA and modified DAS.

Transitions In Hemometabolic Related Cardiogenic Shock

Introduction We sought to determine the disease trajectory of patients with chronic heart failure complicated with cardiogenic shock and the impact of surrogates related to clinical severity and impaired hemometabolic status. Methods Patients with acute-on-chronic heart failure as cause of cardiogenic shock (n=712) were identified from the CSWG Registry and were evaluated by treatment, metabolic indicators of renal and liver dysfunction and hemodynamics with respect to outcome. Treatment parameters analyzed across the duration of in-patient hospitalization included the use of more than 1 AMCS device, the use of more than 1 vasopressor/inotrope, and the use of mechanical ventilation. Metabolic indicators were measured prior to any AMCS usage and included elevated INR, serum creatinine, and total bilirubin. Elevated right atrial pressure (RAP), wedge pressure and cardiac index at baseline was used to evaluate hemodynamic status. Recovery (discharge w/o replacement), replacement (bridge to VAD or OHT) and in-hospital mortality were the primary outcomes of interest. Results Out of 712 HF CS patients, 255 (35.81%) recovered, 277 (38.90%) bridged to either a VAD or OHT, and 180 (25.28%) did not survive their hospitalization. The variation in hemometabolic status and clinical severity across outcomes is summarized in the figure below. Conclusions Specific surrogates of worsening clinical (mechanical ventilation/increased inotropes/vasoactives), hemodynamic (increased RAP) and metabolic (increased SCr and Total Bilirubin) status in HF-CS were associated with impaired survival. Our findings support the value of studying dedicated system-based strategies for early clinical and hemometabolic situational awareness in HF-CS.

Consideration of sense of coherence in a structured communication approach with stage IV lung cancer patients and their informal caregivers: a qualitative interview study

ObjectiveSalutogenetic aspects are valuable for consideration in patient-centred care of advanced oncological diseases with a limited life expectancy. The Milestone Communication Approach (MCA), involving physician-nurse tandems, addresses specific challenges and needs over the disease trajectory of patients with stage IV lung cancer and their informal caregivers. This study aims to explore patients’ and informal caregivers’ salutogenetic experiences with the MCA concept.MethodsThis qualitative study used face-to-face semi-structured interviews with patients and informal caregivers. All generated data were audio-recorded, pseudonymised and transcribed verbatim. Data were structured using Qualitative Content Analysis. The material was coded deductively into themes related to the components of sense of coherence (Aaron Antonovsky) and emerging sub-themes. All data was managed and organised in MAXQDA.ResultsIn 25 interviews, sense of coherence was referred to with all three components: “Comprehensibility” was supported by information conveyed suitably for the patients; “meaningfulness” was addressed as accepting the situation; and “manageability” led to advance care planning the patients were comfortable with. Patients and informal caregivers experienced the interprofessional tandem as an added value for patient care.ConclusionsParticipants appreciate the MCA in its support for coping with a life-limiting disease. Considering salutogenetic aspects facilitates prognostic awareness and advance care planning. Nevertheless, individual needs of patients and informal caregivers require an individualised application of the MCA.

Improving guideline-mandated care of patients with implantable cardiac defibrillators.

Implantable cardiac defibrillators reduce the risk of sudden cardiac death in selected patients. The value of an implantable cardiac defibrillator declines as the patient's disease progresses. Guidelines suggest that the appropriateness of maintaining implantable cardiac defibrillator therapy be regularly reviewed as part of monitoring of the patient's disease trajectory. It is recommended that implantable cardiac defibrillators are deactivated as patients approach the end of life. Patients with a better understanding of their current state of health and the role that the implantable cardiac defibrillator plays within it are more likely to make informed decisions about the timing of deactivation. A quality improvement project was undertaken on appropriate deactivation of implantable cardiac defibrillators within a large tertiary cardiac centre. This was driven by audit data showing inadequate patient communication and documentation around deactivation. Drivers for change included the introduction of electronic data records, clinical review of comorbid patients approaching elective battery change and an ongoing forum for patient and carer education. Measured outcomes included the number of deactivations performed, evidence of patient discussion and consent, and timing of deactivation of the implantable cardiac defibrillator. There were increased numbers of timely device deactivations undertaken following the interventions with improved documented evidence of patient discussion and consent. The educational forum was received favourably. Focused multidisciplinary interventions can impact favourably on appropriate implantable cardiac defibrillator deactivation and improve patient engagement.

Talking to children about illness and death of a loved one during the COVID-19 pandemic

Talking to children about illness and death of a loved one during the COVID-19 pandemic

Clinical and Hemometabolic Status Impact Transitions in Acute on Chronic Heart Failure Shock: Insights from the CSWG Registry

Cardiogenic shock remains a complex global health entity associated with high mortality despite increased utilization and availability of acute mechanical circulatory support (AMCS) as a bridge to replacement, recovery and/or palliation. We sought to determine the disease trajectory of patients with chronic heart failure complicated with cardiogenic shock and the impact of surrogates related to clinical severity and impaired hemometabolic status. 712 cardiogenic shock patients with acute-on-chronic heart failure as cause of shock were identified from the CSWG Registry and were evaluated by treatment, metabolic indicators of renal and liver dysfunction and hemodynamics with respect to outcome. Treatment parameters analyzed across the duration of in-patient hospitalization included the use of more than 1 AMCS device, the use of more than 1 vasopressor/inotrope, and the use of mechanical ventilation. Metabolic indicators were measured prior to any AMCS usage and included elevated INR, serum creatinine, and total bilirubin. Elevated right atrial pressure (RAP), wedge pressure and cardiac index at baseline was used to evaluate hemodynamic status. Recovery (discharge w/o replacement), replacement (bridge to VAD or OHT) and in-hospital mortality were the primary outcomes of interest. Out of 712 HF CS patients, 255 (35.81%) recovered, 277 (38.90%) bridged to either a VAD or OHT, and 180 (25.28%) did not survive their hospitalization. The variation in hemometabolic status and clinical severity across outcomes is summarized in the figure below. Specific surrogates of worsening clinical (mechanical ventilation/increased inotropes/vasoactives), hemodynamic (increased RAP) and metabolic (increased SCr and Total Bilirubin) status in HF-CS were associated with impaired survival. Our findings support the value of studying dedicated system-based strategies for early clinical and hemometabolic situational awareness in HF-CS.

Characteristics and trajectory of patients with pediatric acute respiratory distress syndrome

This study delineates the disease trajectory of patients with pediatric acute respiratory distress syndrome (PARDS) defined by the Pediatric Acute Lung Injury Consensus Conference (PALICC) definition, and evaluates the impact of comorbidities on outcomes. This prospective study over November 2017-October 2019 was conducted in a single-center multidisciplinary pediatric intensive care unit (PICU) and included patients <21years of age with PARDS. Clinical history of those requiring mechanical ventilation for <3 days was interrogated and cases in which the diagnosis of PARDS were unlikely, identified. The impact of chronic comorbidities on clinical outcomes, in particular, pulmonary disease and immunosuppression, were analyzed. Eighty-five of 1272 PICU admissions (6.7%) met the criteria for PARDS and were included. Median age and oxygenation indexes were 2.8 (0.6, 8.3) years and 10.6 (7.6, 15.4), respectively. Overall mortality was 12 out of 85 (14.1%). Despite fulfilling criteria in 6/85 (7.1%), hypoxemia contributed by bronchospasm, mucus plugging, fluid overload, and atelectasis was quickly reversible and PARDS was unlikely in these patients. Comorbidities (57/85 [67.1%]) were not associated with worsened outcomes. However, pre-existing pulmonary disease and immunosuppression were associated with severe PARDS (12/20 [60.0%] vs 19/65 [29.2%]; P = .017), extracorporeal membrane oxygenation use (5/20 [25.0%] vs 3/65 [4.6%]; P = .016) and reduced ventilator free days (VFD) (15 [0, 19] vs 21 [6, 23]; P = .039), compared with those without them. A small percentage of children fulfilling the PALICC definition had quickly reversible hypoxemia with likely alternate pathophysiology to PARDS. Patients with pulmonary comorbidities and immunosuppression had a more severe course of PARDS compared with others.

CRT-600.54 Hemometabolic Status Impacts Transitions in Chronic Heart Failure-related Shock: Insights From the CSWG Registry

Cardiogenic shock remains a complex global health entity associated with high mortality despite increased utilization and availability of acute mechanical circulatory support (AMCS) as a bridge to replacement, recovery and/or palliation. We sought to determine the disease trajectory of patients with

Improving continuity by bringing the cancer patient, general practitioner and oncologist together in a shared video-based consultation \u2013 protocol for a randomised controlled trial

BackgroundStrengthening the coordination, continuity and intersectoral cooperation for cancer patients’ during cancer treatment is being underlined by international guidelines and research. General practitioners have assumed a growing role in the cancer patient disease trajectory because of their roles as coordinators and the consistent health provider. However, general practitioners are challenged in providing support for cancer patients both during treatment and in the survivorship phase. General practitioners reported barriers are lack of timely and relevant communication from the oncologist and limited knowledge to guidelines, as well as lack of trust from patients.Therefore, the current study will examine whether a shared video-based consultation between the cancer patient, general practitioner and oncologist can ease general’ challenges and thereby enhance the patient-centeredness for the cancer patients and their perception of intersectoral cooperation and continuity.MethodsThe study is designed as a pragmatic randomised controlled trial for patients starting chemotherapy at the Department of Oncology, Lillebaelt Hospital, Denmark who are listed with a general practitioner in the Region of Southern Denmark. We intend to include 278 adults diagnosed with colorectal, breast, lung, gynecologic or prostate cancer.The intervention group will receive the “Partnership intervention” which consists of one or more video-consultations between the cancer patient, general practitioner and oncologist. The consultations are estimated to last between 10 and 20 min. The specific aims of the consultation are, summary of the patient trajectory, sharing of knowledge regarding comorbidity, psychosocial resources and needs, physical well-being, medicine, anxiety and depression symptoms, spouses, workability and late complication and side-effects to the cancer treatment.DiscussionVideo-based consultation that brings the cancer patient, the general practitioner and the oncologist together in the early phase of treatment may facilitate a sense of partnership that is powerful enough to improve the patient’s perception of intersectoral cooperation, continuity of cancer care and health-related quality of life.Trial registrationClincialTrials.gov Identifier: NCT02716168. Date of registration: 03.03.2016.

Evaluation of the psychological burden during the early disease trajectory in patients with intracranial tumors by the ultra-brief Patient Health Questionnaire for Depression and Anxiety (PHQ-4).

Depressive symptoms of patients with intracranial tumors need to be assessed adequately. The Patient Health Questionnaire for Depression and Anxiety (PHQ-4) is an ultra-short screening tool consisting of four items, a cutoff of six indicates depressive symptoms. The aim was to assess patients' psychological burden by the PHQ-4 compared with the results of well-established screening instruments. Patients were screened three times after primary diagnosis postoperatively (t1), after 3 (t2) and 6 (t3) months using the PHQ-4, the Hornheide Screening Instrument (HSI), the NCCN Distress Thermometer (DT), and the European Organization for Research and Treatment of Cancer Quality of Life Core Questionnaire with its brain module (EORTC QLQ-C30 + BN20). Demographic, tumor-related data, and Karnofsky Performance Scale (KPS) were analyzed. A cutoff value for PHQ-4 indicating a need for support or increased distress was determined by applying receiver operating characteristic (ROC). The proportion of patients reaching a total score ≥ 6 was n = 32 out of 139 (23%) at t1; at t2, n = 12 out of 117 (10%) scored ≥ 6. At t3, n = 8 out of 96 (8%) scored ≥ 6. At t1, PHQ-4 scores did not differ significantly between gender, age groups, and tumor laterality. A cutoff value of 2.5 was identified to moderately discriminate between patients in or not in distress (sensitivity 76.8%) and between patients wishing further, specific support or not (sensitivity 82.5%). The PHQ4 can be applied in this patient cohort to detect those with relevant psychological comorbidities. The cutoff value should be re-evaluated in a larger cohort as we observed that a cutoff of 6, as recommended previously, may be too high in order to detect affected patients adequately.

Complex challenges for patients with protracted incurable cancer: an ethnographic study in a comprehensive cancer centre in the Netherlands

ObjectiveAdvances in oncology increasingly result in protracted disease trajectories for patients with incurable cancer. In this disease phase, patients are aware of the incurable nature of cancer although they are...

"Everything that is not curative is now palliative": A nurse perspective.

127 Background: Advances in oncology increasingly result in protracted disease trajectories for patients with incurable cancer. This phase can be described as advanced / metastatic cancer and in which anti-cancer treatment should control symptoms, slow disease progression, and/or prolong life. It poses new challenges for patients and their doctors; it is unknown how and which disease labels are used by nurses. Methods: Qualitative ethnographic study, based on in-depth interviews with 13 oncology nurses at the day-care unit in a Dutch comprehensive cancer hospital. Results: A substantial number of nurses reported not to know whether patients were treated with a curative or palliative intent, and to follow a patient-centred approach. Other nurses clearly demarcated palliative patients, and some distinguished "real palliative patients" from patients with long-standing incurable cancer. When nurses were explicitly asked about medical terminology, many nurses were not very positive about the term "palliative". They considered this to be an old term, e.g. "Now everything that is not curative is palliative". Moreover, the term "palliative" could have an ambiguous/threatening meaning, especially for patients. Whereas nurses often associated the term "palliative" with alleviating symptoms, for patients this term was frequently associated with the approaching death. Most nurses therefore preferred not to use the term "palliative" in front of the patient; but only amongst nurses themselves. Since nurses had not previously been provoked to think about other terms, they were unsure whether "chronic" was the right term. Some indicated that cancer was rather different compared to other chronic diseases, others felt unsure when to use the term "chronic" at all. Conclusions: According to nurses, the use of specific medical terms such as "chronic" to describe the situation of patients in protracted disease trajectories is unclear. Although they acknowledge differences across the palliative care continuum, they refrain from using the word "palliative" in front of the patient. Nurses’ awareness of the disease stage (curative/palliative/ "chronic") might be important to optimise to patients’ specific needs in every disease phase.

Embracing the setting sun: provision of palliative care via a collaborative model between hospital and community for patients with intellectual disabilities

Palliative care (PC) evolved from taking care of terminal cancer patients to modern concept of early integration into disease trajectories of patients with life limiting cancer and non-cancer diseases (1).

Coping with long-lasting incurable cancer: An ethnographic study in a comprehensive cancer centre.

e22214Background: Advances in oncology increasingly result in protracted disease trajectories for patients with incurable cancer. In this protracted disease phase, patients are aware of the incurab...

From Childhood to Adulthood: Disease Activity Trajectories in Childhood-Onset Systemic Lupus Erythematosus.

No previous study has studied the longitudinal disease course of childhood-onset systemic lupus erythematosus (cSLE). Our objectives are to assess distinguishable differences in disease activity trajectories in cSLE patients, determine baseline factors predictive of disease trajectory membership, and assess if the different disease activity trajectories are associated with different damage trajectories. This is a retrospective, longitudinal inception cohort of cSLE patients. Patients were followed from diagnosis as children, until they were adults. SLE disease activity was modeled as a latent characteristic, jointly using the Systemic Lupus Erythematosus Disease Activity Index 2000 and prednisone in a Bayesian growth mixture model. Baseline factors were tested for membership prediction of the latent classes of disease trajectories. Differences in damage trajectories by disease activity classes were tested using a mixed model. A total of 473 patients (82% females), with median age at diagnosis of 14.1 years, were studied. We studied 11,992 visits (2,666 patient-years). We identified 5 classes of disease activity trajectories. Baseline major organ involvement, number of American College of Rheumatology criteria, and age at diagnosis predicted memberships into different classes. A higher proportion of Asians was in class 2 compared to class 5. Class 1 was associated with the most accrual of damage, while class 5 was associated with no significant damage accrual, even after 10 years. There are 5 distinct latent classes of disease trajectory in patients with cSLE. Membership within disease trajectories is predicted by baseline clinical and demographic factors. Membership in different disease activity trajectory classes is associated with different damage trajectories.