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.