Identifying phenotypes in persons with temporomandibular disorders, using latent class analyses: Temporomandibular disorders and phenotypes.

BACKGROUND: The heterogeneity of persons with temporomandibular disorders (TMD) and the lack of effective treatments have called for a biopsychosocial model and the development of a more personalised treatment approach. Emphasis on phenotypes might be a beneficial approach. OBJECTIVE: Identifying phenotypes among persons with TMD using potential prognostic factors, including personal characteristics and responses to clinical tests. Additionally, examining the distribution of TMD diagnoses within the identified phenotypes. METHODS: A cross-sectional study including 208 persons (85% females) seeking physiotherapy for problems in the temporomandibular area. All participants were examined clinically and answered questionnaires electronically. The phenotypes were identified using latent class analysis based on seven potential prognostic factors selected within pain, function and psychological domains. Table analysis was used to explore the distribution of TMD diagnoses within the identified phenotypes. RESULTS: Most participants fit into one of three identified phenotypes. Phenotype 1 (32%) was characterised by functional disability, low psychosocial scores and low risk for developing chronicity and future work disability; Phenotype 2 (29%) by parafunctional habits, low psychosocial score and seeking treatment to reduce pain; and Phenotype 3 (39%) by high levels of mental distress, fear avoidance and a large risk of future work disability. Intra-articular disorders dominated Phenotype 1, myalgia and TMD-related headache Phenotype 2, while Phenotype 3 included all the different TMD diagnoses. CONCLUSION: The knowledge about the three identified phenotypes might be useful for clinicians treating persons with TMD and for the development of preventive strategies and more personalised treatment.

The clinical course of neck pain: Are trajectory patterns stable over a 1-year period?

BACKGROUND: Recent studies with data-driven approaches have established common pain trajectories. It is uncertain whether these trajectory patterns are consistent over time, and if a shorter measurement period will provide accurate trajectories. METHODS: We included 1,124 patients with non-specific neck pain in chiropractic practice. We classified patients into pre-defined trajectory patterns in each of four quarters of the follow-up year (persistent, episodic, and recovery) based on measures of pain intensity and frequency from weekly SMS. We explored the shifts between patterns and compared patients with stable and shifting patterns on baseline characteristics and clinical findings. RESULTS: 785 (70%) patients were in the same pattern in 1st and 4th quarters. Patients with episodic pattern in the 1st quarter shifted to other patterns more frequently than patients in the other patterns. A stable persistent pattern was associated with reduced function and higher scores on psychosocial factors. There was a decreased frequency of patients classified as persistent pattern (75% to 63%) and an increase of patients in recovery pattern (4% to 15%) throughout the four quarters. The frequency of patients classified as episodic remained relatively stable (21% to 24%). CONCLUSIONS: We found an overall stability of the persistent pattern, and that episodic patterns have more potential for shifts. Shifts mostly occurred between patterns closest in pain variation. The deviation in pattern distribution compared with previous studies suggests that the duration of measurement periods has an impact on the results of the classification. SIGNIFICANCE: Having persistent pain and having very minor pain is relatively stable over one year, while episodic pain has more potential for shifts. The duration of measurement periods appears to have an impact on the results of the classification. The given criteria resulted in a reduced frequency of episodic pattern due to shorter measurement periods. Our findings contribute to improved understanding and predicting NP using a combination of patient characteristics and trajectory patterns.

The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires.

Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel deep learning method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.