Myofascial pain (MP) is a leading cause of chronic low back pain, yet its tissue-level drivers remain poorly defined and lack reliable image biomarkers. Existing studies focus predominantly on muscle while neglecting fascia, fat, and other soft tissues that play integral biomechanical roles. We developed an anatomically grounded explainable artificial intelligence (AI) framework, LAYER (Layer-wise Analysis for Yielding Explainable Relevance Tissue), that analyses six tissue layers in three-dimensional (3D) ultrasound and quantifies their contribution to MP prediction. By utilizing the largest multi-model 3D ultrasound cohort consisting of over 4,000 scans, LAYER reveals that non-muscle tissues contribute substantially to pain prediction. In B-mode imaging, the deep fascial membrane (DFM) showed the highest saliency (0.420), while in combined B-mode and shear-wave images, the collective saliency of non-muscle layers (0.316) nearly matches that of muscle (0.317), challenging the conventional muscle-centric paradigm in MP research and potentially affecting the therapy methods. LAYER establishes a quantitative, interpretable framework for linking layer-specific anatomy to pain physiology, uncovering new tissue targets and providing a generalizable approach for explainable analysis of soft-tissue imaging.

Clinical data informs the personalization of health care with a potential for more effective disease management. In practice, this is achieved by subgrouping, whereby clusters with similar patient characteristics are identified and then receive customized treatment plans with the goal of targeting subgroup-specific disease dynamics. In this paper, we propose a novel mixture hidden Markov model for subgrouping patient trajectories from chronic diseases. Our model is probabilistic and carefully designed to capture different trajectory phases of chronic diseases (i.e., "severe", "moderate", and "mild") through tailored latent states. We demonstrate our subgrouping framework based on a longitudinal study across 847 patients with non-specific low back pain. Here, our subgrouping framework identifies 8 subgroups. Further, we show that our subgrouping framework outperforms common baselines in terms of cluster validity indices. Finally, we discuss the applicability of the model to other chronic and long-lasting diseases.

Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions? Findings: In this prognostic study of 6.8 million patients, our denoising sequence-to-sequence prediction model of multiple outcomes outperformed state-of-the-art models scuh pretrained BERT on a broad range of patient outcomes, including intentional self-harm and pancreatic cancer. Meaning: Deep bidirectional and autoregressive representation improves patient outcome prediction.

Globally, Low back pain (LBP) is one of the top three contributors to years lived with disability. Self-management with an active lifestyle and regular exercises is the cornerstone for preventing and managing LBP. Digital interventions are introduced in the recent past to reinforce self-management where they rely on self-reporting to keep track of the exercises performed. This data directly influence the recommendations made by the digital intervention thus accurate and reliable reporting is fundamental to the success of the intervention. In addition, performing exercises with precision is important where current systems are unable to provide the guidance required. The main challenge to implementing an end-to-end solution is the lack of public sensor-rich datasets to implement Machine Learning algorithms to perform Exercise Recognition (ExR) and qualitative analysis. Accordingly we introduce the ExR benchmark dataset “MEx”, which we share publicly to encourage future research. The dataset include 7 exercise classes, recorded with 30 users using 4 sensors. In this paper we benchmark state-of-the-art classification algorithms with deep and shallow architectures on each sensor and achieve performances 90.2%, 63.4%, 87.2% and 74.1% respectively for the pressure mat, the depth camera, the thigh accelerometer and the wrist accelerometer. We recognise the scope of each sensor in capturing exercise movements with confusion matrices and highlight the most suitable sensors for deployment considering performance vs. obtrusiveness.