Machine Learning Based Linking of Patient Reported Outcome Measures to WHO International Classification of Functioning, Disability, and Health Activity/Participation Categories.

BACKGROUND: In the primary and secondary medical health sector, patient reported outcome measures (PROMs) are widely used to assess a patient's disease-related functional health state. However, the World Health Organization (WHO), in its recently adopted resolution on "strengthening rehabilitation in all health systems", encourages that all health sectors, not only the rehabilitation sector, classify a patient's functioning and health state according to the International Classification of Functioning, Disability and Health (ICF). AIM: This research sought to optimize machine learning (ML) methods that fully and automatically link information collected from PROMs in persons with unspecific chronic low back pain (cLBP) to limitations in activities and restrictions in participation that are listed in the WHO core set categories for LBP. The study also aimed to identify the minimal set of PROMs necessary for linking without compromising performance. METHODS: A total of 806 patients with cLBP completed a comprehensive set of validated PROMs and were interviewed by clinical psychologists who assessed patients' performance in activity limitations and restrictions in participation according to the ICF brief core set for low back pain (LBP). The information collected was then utilized to further develop random forest (RF) methods that classified the presence or absence of a problem within each of the activity participation ICF categories of the ICF core set for LBP. Further analyses identified those PROM items relevant to the linking process and validated the respective linking performance that utilized a minimal subset of items. RESULTS: Compared to a recently developed ML linking method, receiver operating characteristic curve (ROC-AUC) values for the novel RF methods showed overall improved performance, with AUC values ranging from 0.73 for the ICF category d850 to 0.81 for the ICF category d540. Variable importance measurements revealed that minimal subsets of either 24 or 15 important PROM variables (out of 80 items included in full set of PROMs) would show similar linking performance. CONCLUSIONS: Findings suggest that our optimized ML based methods more accurately predict the presence or absence of limitations and restrictions listed in ICF core categories for cLBP. In addition, this accurate performance would not suffer if the list of PROM items was reduced to a minimum of 15 out of 80 items assessed.

The Back Muscle Surface Electromyography-Based Fatigue Index: A Digital Biomarker of Human Neuromuscular Aging?

As part of our quest for digital biomarkers of neuromuscular aging, and encouraged by recent findings in healthy volunteers, this study investigated if the instantaneous median frequency (IMDF) derived from back muscle surface electromyographic (SEMG) data monitored during cyclic back extensions could reliably differentiate between younger and older individuals with cLBP. A total of 243 persons with cLBP participated in three experimental sessions: at baseline, one to two days after the first session, and then again approximately six weeks later. During each session, the study participants performed a series of three isometric maximal voluntary contractions (MVC) of back extensors using a dynamometer. These were followed by an isometric back extension at 80% MVC, and-after a break-25 slow cyclic back extensions at 50% MVC. SEMG data were recorded bilaterally at L5 (multifidus), L2 (longissimus dorsi), and L1 (iliocostalis lumborum). Linear mixed-effects models found the IMDF-SEMG time-course changes more rapidly in younger than in older individuals, and more prominently in male participants. The absolute and relative reliabilities of the SEMG time-frequency representations were well compared between older and younger participants. The results indicated an overall good relative reliability, but variable absolute reliability levels. IMDF-SEMG estimates derived from cyclic back extensions proved to be successful in reliably detecting differences in back muscle function in younger vs. older persons with cLBP. These findings encourage further research, with a focus on assessing whether an IMDF-SEMG-based index could be utilized as a tool to achieve the preclinical detection of back muscle aging, and possibly predict the development of back muscle sarcopenia.

Design and quantitative structure-activity relationship of 3-amidinobenzyl-1H-indole-2-carboxamides as potent, nonchiral, and selective inhibitors of blood coagulation factor Xa.

A series of 138 nonchiral 3-amidinobenzyl-1H-indole-2-carboxamides and analogues as inhibitors of the blood coagulation enzyme factor Xa (fXa) were designed, synthesized, and investigated by X-ray structure analysis and 3D quantitative structure-activity relationship (QSAR) studies (CoMFA, CoMSIA) in order to identify important protein-ligand interactions responsible for biological affinity and selectivity. Several compounds from this series are highly potent and selective inhibitors of this important enzyme linking extrinsic and intrinsic coagulation pathways. To rationalize biological affinity and to provide guidelines for further design, all compounds were docked into the factor Xa binding site. Those docking studies were based on X-ray structures of factor Xa in complex with literature-known inhibitors. It was possible to validate those binding modes by four X-ray crystal structures of representative ligands in factor Xa, while one ligand was additionally crystallized in trypsin to rationalize requirements for selective factor Xa inhibition. The 3D-QSAR models based on a superposition rule derived from these docking studies were validated using conventional and cross-validated r(2) values using the leave-one-out method and repeated analyses using two randomly chosen cross-validation groups plus randomization of biological activities. This led to consistent and highly predictive 3D-QSAR models with good correlation coefficients for both CoMFA and CoMSIA, which were found to correspond to experimentally determined factor Xa binding site topology in terms of steric, electrostatic, and hydrophobic complementarity. Subsets selected as smaller training sets using 2D fingerprints and maximum dissimilarity methods resulted in 3D-QSAR models with remarkable correlation coefficients and a high predictive power. The final quantitative SAR information agrees with all experimental data for the binding topology and thus provides reasonable activity predictions for novel factor Xa inhibitors.