Mixture of longitudinal factor analyzers and their application to the assessment of chronic pain.

Multivariate longitudinal data are used in a variety of research areas not only because they allow to analyze time trajectories of multiple indicators, but also to determine how these trajectories are influenced by other covariates. In this article, we propose a mixture of longitudinal factor analyzers. This model could be used to extract latent factors representing multiple longitudinal noisy indicators in heterogeneous longitudinal data and to study the impact of one or several covariates on these latent factors. One of the advantages of this model is that it allows for measurement non-invariance, which arises in practice when the factor structure varies between groups of individuals due to cultural or physiological differences. This is achieved by estimating different factor models for different latent classes. The proposed model could also be used to extract latent classes with different latent factor trajectories over time. Other advantages of the model include its ability to take into account heteroscedasticity of errors in the factor analysis model by estimating different error variances for different latent classes. We first define the mixture of longitudinal factor analyzers and its parameters. Then, we propose an EM algorithm to estimate these parameters. We propose a Bayesian information criterion to identify both the number of components in the mixture and the number of latent factors. We then discuss the comparability of the latent factors obtained between subjects in different latent groups. Finally, we apply the model to simulated and real data of patients with chronic postoperative pain.

Potential estimation model in French alpine skiing - Individual evolution curve and progression typology.

Estimating the potential of alpine skiers is an unresolved question, especially because of the complexity of sports performance. We developed a potential estimation model based solely on the evolution of performance as a function of age. A bayesian mixed model allowed to estimate the potential curve and the age at peak performance for the population (24.81 ± 0.2) and for each individual as the uncertainty around this curve. With Gaussian mixtures, we identified among all the estimates four types of curves, clustered according to the performance level and the progression per age. Relying on the uncertainty calculated on the progression curve the model created also allow to estimate a score and an uncertainty associated with each cluster for all individuals. The results allows to: i) describe and explain the relationship between age and performance in alpine skiing from a species point of view (at 0.87%) and ii) to provide to sport staffs the estimation of the potential of each individual and her/his typology of progression to better detect sports potential. The entire methodology is based on age and performance data, but the progression identified may depend on parameters specific to alpine skiing.

A Novel Multi-Dimensional Clinical Response Index Dedicated to Improving Global Assessment of Pain in Patients with Persistent Spinal Pain Syndrome after Spinal Surgery, Based on a Real-Life Prospective Multicentric Study (PREDIBACK) and Machine Learning Techniques.

The multidimensionality of chronic pain forces us to look beyond isolated assessment such as pain intensity, which does not consider multiple key parameters, particularly in post-operative Persistent Spinal Pain Syndrome (PSPS-T2) patients. Our ambition was to produce a novel Multi-dimensional Clinical Response Index (MCRI), including not only pain intensity but also functional capacity, anxiety-depression, quality of life and quantitative pain mapping, the objective being to achieve instantaneous assessment using machine learning techniques. Two hundred PSPS-T2 patients were enrolled in the real-life observational prospective PREDIBACK study with 12-month follow-up and received various treatments. From a multitude of questionnaires/scores, specific items were combined, as exploratory factor analyses helped to create a single composite MCRI; using pairwise correlations between measurements, it appeared to more accurately represent all pain dimensions than any previous classical score. It represented the best compromise among all existing indexes, showing the highest sensitivity/specificity related to Patient Global Impression of Change (PGIC). Novel composite indexes could help to refine pain assessment by informing the physician's perception of patient condition on the basis of objective and holistic metrics, and also by providing new insights regarding therapy efficacy/patient outcome assessments, before ultimately being adapted to other pathologies.

Finite Mixture Models Based on Pain Intensity, Functional Disability and Psychological Distress Composite Assessment Allow Identification of Two Distinct Classes of Persistent Spinal Pain Syndrome after Surgery Patients Related to Their Quality of Life.

Persistent Spinal Pain Syndrome Type 2 (PSPS-T2), (Failed Back Surgery Syndrome), dramatically impacts on patient quality of life, as evidenced by Health-Related Quality of Life (HRQoL) assessment tools. However, the importance of functioning, pain perception and psychological status in HRQoL can substantially vary between subjects. Our goal was to extract patient profiles based on HRQoL dimensions in a sample of PSPS-T2 patients and to identify factors associated with these profiles. Two classes were clearly identified using a mixture of mixed effect models from a clinical data set of 200 patients enrolled in "PREDIBACK", a multicenter observational prospective study including PSPS-T2 patients with one-year follow-up. We observed that HRQoL was more impacted by functional disability for first class patients (n = 136), and by pain perception for second class patients (n = 62). Males that perceive their work as physical were more impacted by disability than pain intensity. Lower education level, lack of adaptive coping strategies and higher pain intensity were significantly associated with HRQoL being more impacted by pain perception. The identification of such classes allows for a better understanding of HRQoL dimensions and opens the gate towards optimized health-related quality of life evaluation and personalized pain management.

Machine Learning Algorithms Provide Greater Prediction of Response to SCS Than Lead Screening Trial: A Predictive AI-Based Multicenter Study.

Persistent pain after spinal surgery can be successfully addressed by spinal cord stimulation (SCS). International guidelines strongly recommend that a lead trial be performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears that patient outco mes, with or without lead trial, are similar. In contrast, during trialing, infection rate drops drastically within time and can compromise the therapy. Using composite pain assessment experience and previous research, we hypothesized that machine learning models could be robust screening tools and reliable predictors of long-term SCS efficacy. We developed several algorithms including logistic regression, regularized logistic regression (RLR), naive Bayes classifier, artificial neural networks, random forest and gradient-boosted trees to test this hypothesis and to perform internal and external validations, the objective being to confront model predictions with lead trial results using a 1-year composite outcome from 103 patients. While almost all models have demonstrated superiority on lead trialing, the RLR model appears to represent the best compromise between complexity and interpretability in the prediction of SCS efficacy. These results underscore the need to use AI-based predictive medicine, as a synergistic mathematical approach, aimed at helping implanters to optimize their clinical choices on daily practice.