The hidden information in patient-reported outcomes and clinician-assessed outcomes: multiple sclerosis as a proof of concept of a machine learning approach

A taxonomy of cognitive phenotypes in Multiple Sclerosis: a 1-year longitudinal study

As meaningful measure of cognitive impairment (CI), cognitive phenotypes provide an avenue for symptom management and individualized rehabilitation. Since CI is highly variable in severity and progression, monitoring cognitive phenotypes over time may be useful to identify trajectory of cognitive decline in Multiple Sclerosis (MS). Based on cognitive and mood information from patient-reported outcomes (PROs) and clinician-assessed outcomes (CAOs), four cognitive subgroups of people with MS (PwMS) were identified: phenotype 1 (44.5%) showed a preserved cognitive profile; phenotype 2 (22.8%) had a mild-cognitive impairment profile with attention difficulties; phenotype 3 (24.3%) included people with marked difficulties in visuo-executive, attention, language, memory and information processing speed; lastly, phenotype 4 (8.4%) grouped individuals with a multi-domain impairment profile (visuo-executive, attention, language, memory, orientation, information processing speed and mood disorders). Although some fluctuations occurred considering the rate of impairment, cognitive phenotypes did not substantially vary at follow up in terms of type and number of impairments, suggesting that 1 year is a relatively brief temporal window to observe considerable changes. Our results corroborate that investigating cognitive phenotypes and their stability over time would provide valuable information regarding CI and, in addition, increase clinical importance of PROs and CAOs and their uptake in decision-making and individualized treatment planning for PwMS.

An analytical review on the use of artificial intelligence and machine learning in diagnosis, prediction, and risk factor analysis of multiple sclerosis

Medical research offers potential for disease prediction, like Multiple Sclerosis (MS). This neurological disorder damages nerve cell sheaths, with treatments focusing on symptom relief. Manual MS detection is time-consuming and error prone. Though MS lesion detection has been studied, limited attention has been paid to clinical analysis and computational risk factor prediction. Artificial intelligence (AI) techniques and Machine Learning (ML) methods offer accurate and effective alternatives to mapping MS progression. However, there are challenges in accessing clinical data and interdisciplinary collaboration. By analyzing 103 papers, we recognize the trends, strengths and weaknesses of AI, ML, and statistical methods applied to MS diagnosis. AI/ML-based approaches are suggested to identify MS risk factors, select significant MS features, and improve the diagnostic accuracy, such as Rule-based Fuzzy Logic (RBFL), Adaptive Fuzzy Inference System (ANFIS), Artificial Neural Network methods (ANN), Support Vector Machine (SVM), and Bayesian Networks (BNs). Meanwhile, applications of the Expanded Disability Status Scale (EDSS) and Magnetic Resonance Imaging (MRI) can enhance MS diagnostic accuracy. By examining established risk factors like obesity, smoking, and education, some research tackled the issue of disease progression. The performance metrics varied across different aspects of MS studies: Diagnosis: Sensitivity ranged from 60 % to 98 %, specificity from 60 % to 98 %, and accuracy from 61 % to 97 %. Prediction: Sensitivity ranged from 76 % to 98 %, specificity from 65 % to 98 %, and accuracy from 62 % to 99 %. Segmentation: Accuracy ranged up to 96.7 %. Classification: Sensitivity ranged from 78 % to 97.34 %, specificity from 65 % to 99.32 %, and accuracy from 71 % to 97.94 %. Furthermore, the literature shows that combining techniques can improve efficiency, exploiting their strengths for better overall performance.

Mobile Health App (DIGICOG-MS) for Self-Assessment of Cognitive Impairment in People With Multiple Sclerosis: Instrument Validation and Usability Study

BACKGROUND

Mobile health (mHealth) apps have proven useful for people with multiple sclerosis (MS). Thus, easy-to-use digital solutions are now strongly required to assess and monitor cognitive impairment, one of the most disturbing symptoms in MS that is experienced by almost 43% to 70% of people with MS. Therefore, we developed DIGICOG-MS (Digital assessment of Cognitive Impairment in Multiple Sclerosis), a smartphone- and tablet-based mHealth app to self-assess cognitive impairment in MS.

OBJECTIVE

This study aimed to test the validity and usability of the novel mHealth app with a sample of people with MS.

METHODS

DIGICOG-MS includes 4 digital tests assumed to evaluate the most affected cognitive domains in MS (visuospatial memory [VSM], verbal memory [VM], semantic fluency [SF], and information processing speed [IPS]) and inspired by traditional paper-based tests that assess the same cognitive functions (10/36 Spatial Recall Test, Rey Auditory Verbal Learning Test, Word List Generation, Symbol Digit Modalities Test). Participants were asked to complete both digital and traditional assessments in 2 separate sessions. Convergent validity was analyzed using the Pearson correlation coefficient to determine the strength of the associations between digital and traditional tests. To test the app's reliability, the agreement between 2 repeated measurements was assessed using intraclass correlation coefficients (ICCs). Usability of DIGICOG-MS was evaluated using the System Usability Scale (SUS) and mHealth App Usability Questionnaire (MAUQ) administered at the conclusion of the digital session.

RESULTS

The final sample consisted of 92 people with MS (60 women) followed as outpatients at the Italian Multiple Sclerosis Society (AISM) Rehabilitation Service of Genoa (Italy). They had a mean age of 51.38 (SD 11.36) years, education duration of 13.07 (SD 2.74) years, disease duration of 12.91 (SD 9.51) years, and a disability level (Expanded Disability Status Scale) of 3.58 (SD 1.75). Relapsing-remitting MS was most common (68/92, 74%), followed by secondary progressive (15/92, 16%) and primary progressive (9/92, 10%) courses. Pearson correlation analyses indicated significantly strong correlations for VSM, VM, SF, and IPS (all P<.001), with r values ranging from 0.58 to 0.78 for all cognitive domains. Test-retest reliability of the mHealth app was excellent (ICCs>0.90) for VM and IPS and good for VSM and SF (ICCs>0.80). Moreover, the SUS score averaged 84.5 (SD 13.34), and the mean total MAUQ score was 104.02 (SD 17.69), suggesting that DIGICOG-MS was highly usable and well appreciated.

CONCLUSIONS

The DIGICOG-MS tests were strongly correlated with traditional paper-based evaluations. Furthermore, people with MS positively evaluated DIGICOG-MS, finding it highly usable. Since cognitive impairment poses major limitations for people with MS, these findings open new paths to deploy digital cognitive tests for MS and further support the use of a novel mHealth app for cognitive self-assessment by people with MS in clinical practice.

The global patient-reported outcomes for multiple sclerosis initiative: bridging the gap between clinical research and care - updates at the 2023 plenary event

Significant advancements have been achieved in delineating the progress of the Global PROMS (PROMS) Initiative. The PROMS Initiative, a collaborative endeavor by the European Charcot Foundation and the Multiple Sclerosis International Federation, strives to amplify the influence of patient input on MS care and establish a cohesive perspective on Patient-Reported Outcomes (PROs) for diverse stakeholders. This initiative has established an expansive, participatory governance framework launching four dedicated working groups that have made substantive contributions to research, clinical management, eHealth, and healthcare system reform. The initiative prioritizes the global integration of patient (For the purposes of the Global PROMS Initiative, the term "patient" refers to the people with the disease (aka People with Multiple Sclerosis - pwMS): any individual with lived experience of the disease. People affected by the disease/Multiple Sclerosis: any individual or group that is affected by the disease: E.g., family members, caregivers will be also engaged as the other stakeholders in the initiative). insights into the management of MS care. It merges subjective PROs with objective clinical metrics, thereby addressing the complex variability of disease presentation and progression. Following the completion of its second phase, the initiative aims to help increasing the uptake of eHealth tools and passive PROs within research and clinical settings, affirming its unwavering dedication to the progressive refinement of MS care. Looking forward, the initiative is poised to continue enhancing global surveys, rethinking to the relevant statistical approaches in clinical trials, and cultivating a unified stance among 'industry', regulatory bodies and health policy making regarding the application of PROs in MS healthcare strategies.

The administration of the paper and electronic versions of the Manual Ability Measure-36 (MAM-36) and Fatigue Severity Scale (FSS) is equivalent in people with multiple sclerosis

BACKGROUND

The mobile device diffusion has increasingly highlighted the opportunity to collect patient-reported outcomes (PROs) through electronic patient-reported outcomes measurements (ePROMs) during the clinical routine. Despite the ePROMs promises and advantages, the equivalence when a PRO measure is moved from the original paper-and-pencil to the electronic version is still little investigated. This study aims at evaluating equivalence between PROMs and ePROMs self-administration in people with multiple sclerosis (PwMS); in addition, preference of self-administration type was evaluated.

METHODS

The Manual Ability Measure-36 (MAM-36) and Fatigue Severity Scale (FSS) were selected for the equivalence test. The app ABOUTCOME was developed through a user-centered design approach to administer the questionnaires on tablet. Both paper-and-pencil and electronic versions were randomly self-administered. Intrarater reliability between both versions was evaluated through the intraclass correlation coefficient (ICC, excellent for values ≥ 0.75).

RESULTS

Fifty PwMS (35 females) participated to the study (mean age: 54.7±11.0 years, disease course: 27 relapsing-remitting and 23 progressive; mean EDSS: 4.7±1.9; mean disease duration: 13.3±9.5 years). No statistically significant differences were found for the means total scores of MAM-36 (p = 0.61) and FSS (p = 0.78). The ICC value for MAM-36 and FSS was excellent (0.98 and 0.94, respectively). Most of participants preferred the tablet version (84%).

CONCLUSION

The results of the study provide evidence about the equivalence between the paper-and-pencil and electronic versions of PROs administration. In addition, PwMS prefer electronic methods rather than paper because the information can be provided more efficiently and accurately. The results could be easily extended to other MS PROs.

Monitoring and Predicting Health Status in Neurological Patients: The ALAMEDA Data Collection Protocol

(1) Objective: We explore the predictive power of a novel stream of patient data, combining wearable devices and patient reported outcomes (PROs), using an AI-first approach to classify the health status of Parkinson's disease (PD), multiple sclerosis (MS) and stroke patients (collectively named PMSS). (2) Background: Recent studies acknowledge the burden of neurological disorders on patients and on the healthcare systems managing them. To address this, effort is invested in the digital transformation of health provisioning for PMSS patients. (3) Methods: We introduce the data collection journey within the ALAMEDA project, which continuously collects PRO data for a year through mobile applications and supplements them with data from minimally intrusive wearable devices (accelerometer bracelet, IMU sensor belt, ground force measuring insoles, and sleep mattress) worn for 1-2 weeks at each milestone. We present the data collection schedule and its feasibility, the mapping of medical predictor variables to wearable device capabilities and mobile application functionality. (4) Results: A novel combination of wearable devices and smartphone applications required for the desired analysis of motor, sleep, emotional and quality-of-life outcomes is introduced. AI-first analysis methods are presented that aim to uncover the prediction capability of diverse longitudinal and cross-sectional setups (in terms of standard medical test targets). Mobile application development and usage schedule facilitates the retention of patient engagement and compliance with the study protocol.

Prognostic models for predicting clinical disease progression, worsening and activity in people with multiple sclerosis

BACKGROUND

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system that affects millions of people worldwide. The disease course varies greatly across individuals and many disease-modifying treatments with different safety and efficacy profiles have been developed recently. Prognostic models evaluated and shown to be valid in different settings have the potential to support people with MS and their physicians during the decision-making process for treatment or disease/life management, allow stratified and more precise interpretation of interventional trials, and provide insights into disease mechanisms. Many researchers have turned to prognostic models to help predict clinical outcomes in people with MS; however, to our knowledge, no widely accepted prognostic model for MS is being used in clinical practice yet.

OBJECTIVES

To identify and summarise multivariable prognostic models, and their validation studies for quantifying the risk of clinical disease progression, worsening, and activity in adults with MS.

SEARCH METHODS

We searched MEDLINE, Embase, and the Cochrane Database of Systematic Reviews from January 1996 until July 2021. We also screened the reference lists of included studies and relevant reviews, and references citing the included studies.

SELECTION CRITERIA

We included all statistically developed multivariable prognostic models aiming to predict clinical disease progression, worsening, and activity, as measured by disability, relapse, conversion to definite MS, conversion to progressive MS, or a composite of these in adult individuals with MS. We also included any studies evaluating the performance of (i.e. validating) these models. There were no restrictions based on language, data source, timing of prognostication, or timing of outcome.

DATA COLLECTION AND ANALYSIS

Pairs of review authors independently screened titles/abstracts and full texts, extracted data using a piloted form based on the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), assessed risk of bias using the Prediction Model Risk Of Bias Assessment Tool (PROBAST), and assessed reporting deficiencies based on the checklist items in Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). The characteristics of the included models and their validations are described narratively. We planned to meta-analyse the discrimination and calibration of models with at least three external validations outside the model development study but no model met this criterion. We summarised between-study heterogeneity narratively but again could not perform the planned meta-regression.

MAIN RESULTS

We included 57 studies, from which we identified 75 model developments, 15 external validations corresponding to only 12 (16%) of the models, and six author-reported validations. Only two models were externally validated multiple times. None of the identified external validations were performed by researchers independent of those that developed the model. The outcome was related to disease progression in 39 (41%), relapses in 8 (8%), conversion to definite MS in 17 (18%), and conversion to progressive MS in 27 (28%) of the 96 models or validations. The disease and treatment-related characteristics of included participants, and definitions of considered predictors and outcome, were highly heterogeneous amongst the studies. Based on the publication year, we observed an increase in the percent of participants on treatment, diversification of the diagnostic criteria used, an increase in consideration of biomarkers or treatment as predictors, and increased use of machine learning methods over time. Usability and reproducibility All identified models contained at least one predictor requiring the skills of a medical specialist for measurement or assessment. Most of the models (44; 59%) contained predictors that require specialist equipment likely to be absent from primary care or standard hospital settings. Over half (52%) of the developed models were not accompanied by model coefficients, tools, or instructions, which hinders their application, independent validation or reproduction. The data used in model developments were made publicly available or reported to be available on request only in a few studies (two and six, respectively). Risk of bias We rated all but one of the model developments or validations as having high overall risk of bias. The main reason for this was the statistical methods used for the development or evaluation of prognostic models; we rated all but two of the included model developments or validations as having high risk of bias in the analysis domain. None of the model developments that were externally validated or these models' external validations had low risk of bias. There were concerns related to applicability of the models to our research question in over one-third (38%) of the models or their validations. Reporting deficiencies Reporting was poor overall and there was no observable increase in the quality of reporting over time. The items that were unclearly reported or not reported at all for most of the included models or validations were related to sample size justification, blinding of outcome assessors, details of the full model or how to obtain predictions from it, amount of missing data, and treatments received by the participants. Reporting of preferred model performance measures of discrimination and calibration was suboptimal.

AUTHORS' CONCLUSIONS

The current evidence is not sufficient for recommending the use of any of the published prognostic prediction models for people with MS in clinical routine today due to lack of independent external validations. The MS prognostic research community should adhere to the current reporting and methodological guidelines and conduct many more state-of-the-art external validation studies for the existing or newly developed models.

Post-total joint arthroplasty opioid prescribing practices vary widely and are not associated with opioid refill: an observational cohort study

INTRODUCTION

Optimized health system approaches to improving guideline-congruent care require evaluation of multilevel factors associated with prescribing practices and outcomes after total knee and hip arthroplasty.

MATERIALS AND METHODS

Electronic health data from patients who underwent a total knee or hip arthroplasty between January 2016-January 2020 in the Military Health System Data were retrospectively analyzed. A generalized linear mixed-effects model (GLMM) examined the relationship between fixed covariates, random effects, and the primary outcome (30-day opioid prescription refill).

RESULTS

In the sample (N = 9151, 65% knee, 35% hip), the median discharge morphine equivalent dose was 660 mg [450, 892] and varied across hospitals and several factors (e.g., joint, race and ethnicity, mental and chronic pain conditions, etc.). Probability of an opioid refill was higher in patients who underwent total knee arthroplasty, were white, had a chronic pain or mental health condition, had a lower age, and received a presurgical opioid prescription (all p < 0.01). Sex assigned in the medical record, hospital duration, discharge non-opioid prescription receipt, discharge morphine equivalent dose, and receipt of an opioid-only discharge prescription were not significantly associated with opioid refill.

CONCLUSION

In the present study, several patient-, care-, and hospital-level factors were associated with an increased probability of an opioid prescription refill within 30 days after arthroplasty. Future work is needed to identify optimal approaches to reduce unwarranted and inequitable healthcare variation within a patient-centered framework.

Machine learning for exploring neurophysiological functionality in multiple sclerosis based on trigeminal and hand blink reflexes

Brainstem dysfunctions are very common in Multiple Sclerosis (MS) and are a critical predictive factor for future disability. Brainstem functionality can be explored with blink reflexes, subcortical responses consisting in a blink following a peripheral stimulation. Some reflexes are already employed in clinical practice, such as Trigeminal Blink Reflex (TBR). Here we propose for the first time in MS the exploration of Hand Blink Reflex (HBR), which size is modulated by the proximity of the stimulated hand to the face, reflecting the extension of the peripersonal space. The aim of this work is to test whether Machine Learning (ML) techniques could be used in combination with neurophysiological measurements such as TBR and HBR to improve their clinical information and potentially favour the early detection of brainstem dysfunctionality. HBR and TBR were recorded from a group of People with MS (PwMS) with Relapsing-Remitting form and from a healthy control group. Two AdaBoost classifiers were trained with TBR and HBR features each, for a binary classification task between PwMS and Controls. Both classifiers were able to identify PwMS with an accuracy comparable and even higher than clinicians. Our results indicate that ML techniques could represent a tool for clinicians for investigating brainstem functionality in MS. Also, HBR could be promising when applied in clinical practice, providing additional information about the integrity of brainstem circuits potentially favouring early diagnosis.

Classification of multiple sclerosis clinical profiles using machine learning and grey matter connectome

Purpose: The main goal of this study is to investigate the discrimination power of Grey Matter (GM) thickness connectome data between Multiple Sclerosis (MS) clinical profiles using statistical and Machine Learning (ML) methods. Materials and Methods: A dataset composed of 90 MS patients acquired at the MS clinic of Lyon Neurological Hospital was used for the analysis. Four MS profiles were considered, corresponding to Clinical Isolated Syndrome (CIS), Relapsing-Remitting MS (RRMS), Secondary Progressive MS (SPMS), and Primary Progressive MS (PPMS). Each patient was classified in one of these profiles by our neurologist and underwent longitudinal MRI examinations including T1-weighted image acquisition at each examination, from which the GM tissue was segmented and the cortical GM thickness measured. Following the GM parcellation using two different atlases (FSAverage and Glasser 2016), the morphological connectome was built and six global metrics (Betweenness Centrality (BC), Assortativity (r), Transitivity (T), Efficiency (E g ), Modularity (Q) and Density (D)) were extracted. Based on their connectivity metrics, MS profiles were first statistically compared and second, classified using four different learning machines (Logistic Regression, Random Forest, Support Vector Machine and AdaBoost), combined in a higher level ensemble model by majority voting. Finally, the impact of the GM spatial resolution on the MS clinical profiles classification was analyzed. Results: Using binary comparisons between the four MS clinical profiles, statistical differences and classification performances higher than 0.7 were observed. Good performances were obtained when comparing the two early clinical forms, RRMS and PPMS (F1 score of 0.86), and the two neurodegenerative profiles, PPMS and SPMS (F1 score of 0.72). When comparing the two atlases, slightly better performances were obtained with the Glasser 2016 atlas, especially between RRMS with PPMS (F1 score of 0.83), compared to the FSAverage atlas (F1 score of 0.69). Also, the thresholding value for graph binarization was investigated suggesting more informative graph properties in the percentile range between 0.6 and 0.8. Conclusion: An automated pipeline was proposed for the classification of MS clinical profiles using six global graph metrics extracted from the GM morphological connectome of MS patients. This work demonstrated that GM morphological connectivity data could provide good classification performances by combining four simple ML models, without the cost of long and complex MR techniques, such as MR diffusion, and/or deep learning architectures.

Machine learning techniques for prediction of multiple sclerosis progression

Patients afflicted by multiple sclerosis experience a relapsing-remitting course in about 85% of the cases. Furthermore, after a 10/15-year period their situation tends to worse, resulting in what is considered the second phase of multiple sclerosis. While treatments are now available to reduce the symptoms and slow down the progression of the disease, the administration of drugs must be adapted to the course of the disease, and predicting relapsing periods and the worsening of the symptoms can greatly improve the outcome of the treatment. For this reason, indicators such as the patient-reported outcome measures (PROMs) have been largely used to support early diagnosis and prediction of future relapsing periods in patients affected by multiple sclerosis. However, such indicators are insufficient, as the prediction they provide is often not accurate enough. In this paper, machine learning techniques have been applied to data obtained from clinical trial, in order to improve the prediction capabilities and provide doctors with an additional instrument to evaluate the clinical situation of patients. After the application of correlation indicators and the use of principal component analysis for the reduction of the dimensionality of the feature space, classification algorithms have been applied and compared, in order to identify the best suiting one for our purposes. After the application of re-balance algorithms, the accuracy of the machine learning-based prediction system reaches 79%, demonstrating the capability of the framework to correctly predict future progression of disability.

The role of machine learning in developing non-magnetic resonance imaging based biomarkers for multiple sclerosis: a systematic review

BACKGROUND

Multiple sclerosis (MS) is a neurological condition whose symptoms, severity, and progression over time vary enormously among individuals. Ideally, each person living with MS should be provided with an accurate prognosis at the time of diagnosis, precision in initial and subsequent treatment decisions, and improved timeliness in detecting the need to reassess treatment regimens. To manage these three components, discovering an accurate, objective measure of overall disease severity is essential. Machine learning (ML) algorithms can contribute to finding such a clinically useful biomarker of MS through their ability to search and analyze datasets about potential biomarkers at scale. Our aim was to conduct a systematic review to determine how, and in what way, ML has been applied to the study of MS biomarkers on data from sources other than magnetic resonance imaging.

METHODS

Systematic searches through eight databases were conducted for literature published in 2014-2020 on MS and specified ML algorithms.

RESULTS

Of the 1, 052 returned papers, 66 met the inclusion criteria. All included papers addressed developing classifiers for MS identification or measuring its progression, typically, using hold-out evaluation on subsets of fewer than 200 participants with MS. These classifiers focused on biomarkers of MS, ranging from those derived from omics and phenotypical data (34.5% clinical, 33.3% biological, 23.0% physiological, and 9.2% drug response). Algorithmic choices were dependent on both the amount of data available for supervised ML (91.5%; 49.2% classification and 42.3% regression) and the requirement to be able to justify the resulting decision-making principles in healthcare settings. Therefore, algorithms based on decision trees and support vector machines were commonly used, and the maximum average performance of 89.9% AUC was found in random forests comparing with other ML algorithms.

CONCLUSIONS

ML is applicable to determining how candidate biomarkers perform in the assessment of disease severity. However, applying ML research to develop decision aids to help clinicians optimize treatment strategies and analyze treatment responses in individual patients calls for creating appropriate data resources and shared experimental protocols. They should target proceeding from segregated classification of signals or natural language to both holistic analyses across data modalities and clinically-meaningful differentiation of disease.

Towards Multimodal Machine Learning Prediction of Individual Cognitive Evolution in Multiple Sclerosis

Multiple sclerosis (MS) manifests heterogeneously among persons suffering from it, making its disease course highly challenging to predict. At present, prognosis mostly relies on biomarkers that are unable to predict disease course on an individual level. Machine learning is a promising technique, both in terms of its ability to combine multimodal data and through the capability of making personalized predictions. However, most investigations on machine learning for prognosis in MS were geared towards predicting physical deterioration, while cognitive deterioration, although prevalent and burdensome, remained largely overlooked. This review aims to boost the field of machine learning for cognitive prognosis in MS by means of an introduction to machine learning and its pitfalls, an overview of important elements for study design, and an overview of the current literature on cognitive prognosis in MS using machine learning. Furthermore, the review discusses new trends in the field of machine learning that might be adopted for future studies in the field.

Personalized prediction of rehabilitation outcomes in multiple sclerosis: a proof-of-concept using clinical data, digital health metrics, and machine learning

Predicting upper limb neurorehabilitation outcomes in persons with multiple sclerosis (pwMS) is essential to optimize therapy allocation. Previous research identified population-level predictors through linear models and clinical data. This work explores the feasibility of predicting individual neurorehabilitation outcomes using machine learning, clinical data, and digital health metrics. Machine learning models were trained on clinical data and digital health metrics recorded pre-intervention in 11 pwMS. The dependent variables indicated whether pwMS considerably improved across the intervention, as defined by the Action Research Arm Test (ARAT), Box and Block Test (BBT), or Nine Hole Peg Test (NHPT). Improvements in ARAT or BBT could be accurately predicted (88% and 83% accuracy) using only patient master data. Improvements in NHPT could be predicted with moderate accuracy (73%) and required knowledge about sensorimotor impairments. Assessing these with digital health metrics over clinical scales increased accuracy by 10%. Non-linear models improved accuracy for the BBT (+ 9%), but not for the ARAT (-1%) and NHPT (-2%). This work demonstrates the feasibility of predicting upper limb neurorehabilitation outcomes in pwMS, which justifies the development of more representative prediction models in the future. Digital health metrics improved the prediction of changes in hand control, thereby underlining their advanced sensitivity.

Graphical Abstract

Predominant cognitive phenotypes in multiple sclerosis: Insights from patient-centered outcomes

BACKGROUND

Since combining information from different domains could be useful to increase prediction accuracy over and above what can be achieved at the level of single category of markers, this study aimed to identify distinct and predominant subtypes, i.e., cognitive phenotypes, in people with multiple sclerosis (PwMS) considering both cognitive impairment and mood disorders.

METHODS

A latent class analysis (LCA) was applied on data from 872 PwMS who were tested with Montreal Cognitive Assessment (MoCA), Symbol Digit Modalities Test (SDMT) and Hospital Anxiety and Depression Scale (HADS). Furthermore, the distribution of demographic (i.e., age, gender, years of education) and clinical characteristics (i.e., disease duration, disease course, disability level) was examined amongst the identified phenotypes.

RESULTS

Based on model fit and parsimony criteria, LCA identified four cognitive phenotypes: 1) only memory difficulties (n = 247; 28.3%); 2) minor memory and language deficits with mood disorders (n = 185; 21.2%); 3) moderate memory, language and attention impairments (n = 164; 18.8%); 4) severe memory, language, attention, information processing and executive functions difficulties (n = 276; 31.7%).

CONCLUSIONS

Since less is known about the progressive deterioration of cognition in PwMS, a taxonomy of distinct subtypes that consider information from different clustered domains (i.e., cognition and mood) represents both a challenge and opportunity for an advanced understanding of cognitive impairments and development of tailored cognitive treatments in MS.

Patient Reported Outcomes in Chronic Inflammatory Diseases: Current State, Limitations and Perspectives

Chronic inflammatory diseases (CID) are emerging disorders which do not only affect specific organs with respective clinical symptoms but can also affect various aspects of life, such as emotional distress, anxiety, fatigue and quality of life. These facets of chronic disease are often not recognized in the therapy of CID patients. Furthermore, the symptoms and patient-reported outcomes often do not correlate well with the actual inflammatory burden. The discrepancy between patient-reported symptoms and objectively assessed disease activity can indeed be instructive for the treating physician to draw an integrative picture of an individual's disease course. This poses a challenge for the design of novel, more comprehensive disease assessments. In this mini-review, we report on the currently available patient-reported outcomes, the unmet needs in the field of chronic inflammatory diseases and the challenges of addressing these.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

The course of multiple sclerosis begins with a relapsing-remitting phase, which evolves into a secondarily progressive form over an extremely variable period, depending on many factors, each with a subtle influence. To date, no prognostic factors or risk score have been validated to predict disease course in single individuals. This is increasingly frustrating, since several treatments can prevent relapses and slow progression, even for a long time, although the possible adverse effects are relevant, in particular for the more effective drugs. An early prediction of disease course would allow differentiation of the treatment based on the expected aggressiveness of the disease, reserving high-impact therapies for patients at greater risk. To increase prognostic capacity, approaches based on machine learning (ML) algorithms are being attempted, given the failure of other approaches. Here we review recent studies that have used clinical data, alone or with other types of data, to derive prognostic models. Several algorithms that have been used and compared are described. Although no study has proposed a clinically usable model, knowledge is building up and in the future strong tools are likely to emerge.

MAM-36 and ABILHAND as outcome measures of multiple sclerosis hand disability: an observational study

BACKGROUND

Impaired upper limb functionality and dexterity are common in people with multiple sclerosis (PwMS) and lead to increased dependency and reduced quality of life.

AIM

The aim of this study was to compare the ability of the Manual Abilites Measure 36 (MAM-36) and the ABILHAND questionnaire to recognize an involvement of the upper limbs in PwMS, and to compare their results with those of other patient reported outcomes (PRO) evaluating disability, functional independence, symptoms of anxiety and depression, fatigue and quality of life.

DESIGN

The study design was observational.

SETTING

The setting of the study was outpatient.

POPULATION

The study population included fifty-one PwMS (mean age of 56.31 years, age range of 33-82 years, 72.5% of patients were females).

METHODS

For each patient were collected MAM-36, ABILHAND questionnaire, expanded disability status scale (EDSS), Functional Independence measure (FIM), Hospital Anxiety and Depression Scale (HADS), Modified Fatigue Impact Scale (MFIS) and Life Satisfaction Index (LSI).

RESULTS

A strong correlation between MAM-36 and the ABILHAND questionnaire (Spearman r: 0.79; P<0.0001) were found. We obtained a significant correlation between MAM-36 and EDSS (Spearman r: -0.5; P=0.0002), FIM (Spearman r: 0.55; P<0.0001); we did not observe a correlation with MFIS (Spearman r: -0.33; P=0.02); moreover we found a similar trend between ABILHAND and EDSS (Spearman r: -0.47; P=0.0005), FIM (Spearman r: 0.61; P<0.0001), MFIS (Spearman r: -0.41; P=0.002).

CONCLUSIONS

In PwMS the assessment of upper limbs is fundamental since it closely related to the level of disability of the person. Both MAM-36 and ABILHAND Questionnaire are equally able to detect upper limb dysfunctions in PwMS.

CLINICAL REHABILITATION IMPACT

Both MAM-36 and ABILHAND can be used for upper limbs evaluation, within a multidimensional approach that seems to be the best way to evaluate PwMS.

The patients' perspective on the perceived difficulties of dual-tasking: development and validation of the Dual-task Impact on Daily-living Activities Questionnaire (DIDA-Q)

BACKGROUND

Everyday-life activities often require performing dual tasks (DT), with consequent possible occurrence of motor-cognitive or motor-motor interference. This could reduce quality of life, in particular in people with neurological diseases. However, there is lack of validated tools to assess the patients' perspective on DT difficulties in this population. Therefore, we developed the Dual-task Impact on Daily-living Activities-Questionnaire (DIDA-Q) and tested its psychometric properties in people with multiple sclerosis (PwMS).

METHODS

Items were generated based on existing scales, DT paradigms used in previous studies and the opinion of a multi-stakeholder group, including both experts and PwMS. Twenty DT constituted the preliminary version of the DIDA-Q which was administered to 230 PwMS. The psychometric properties of the scale were evaluated including internal consistency, validity and reliability.

RESULTS

Nineteen items survived after exploratory factor analysis, showing a three-factor solution which identifies the components mostly contributing to DT perceived difficulty (i.e., balance and mobility, cognition and upper-limb ability). The DIDA-Q appropriately fits the graded response model, with first evaluations supporting internal consistency (Cronbach's alpha=0.95), validity (70% of the hypotheses for convergent and discriminant constructs confirmed) and reliability (intraclass correlation coefficients=0.95) of this tool.

CONCLUSION

The DIDA-Q could be used in research and clinical settings to discriminate individuals with low vs. high cognitive-motor or motor-motor interference, and to develop and evaluate the efficacy of personalized DT rehabilitative treatments in PwMS.

Measuring outcomes that matter most to people with multiple sclerosis: the role of patient-reported outcomes

PURPOSE OF REVIEW

Patient-reported outcome (PRO) represents a unique opportunity to measure the impact of health research, and care on outcomes that matter most to people with multiple sclerosis (PwMS).

RECENT FINDINGS

How to incorporate PROs in MS clinical trials and, practice remains a matter of debate. The variety of measures available for use in MS has some benefits, but the lack of a set of standard measures has significant disadvantages. To help meeting the challenge, different PROs standard sets have been developed (PROMIS) for use across a broad range of chronic health conditions, and SymptoMScreen, specifically for MS. However, many of them were not co-created with PwMS and lacking understanding about what matters to patients. The newly proposed MS care unit model together with emerging initiatives such as iConquerMS and PROMOPROMS, are shaping new meaningful PROs. However, the uptake of PROMs in all settings can be effective only by a commonly held strategic agenda shared by all relevant stakeholders.

SUMMARY

The newly born PRO Initiative for MS (PROMS) aims to develop a strategic agenda shared by all relevant stakeholders to help meeting the challenge of developing PRO measures that correspond to the needs of all stakeholders.

Innovations in research and clinical care using patient-generated health data

Patient-generated health data (PGHD), or health-related data gathered from patients to help address a health concern, are used increasingly in oncology to make regulatory decisions and evaluate quality of care. PGHD include self-reported health and treatment histories, patient-reported outcomes (PROs), and biometric sensor data. Advances in wireless technology, smartphones, and the Internet of Things have facilitated new ways to collect PGHD during clinic visits and in daily life. The goal of the current review was to provide an overview of the current clinical, regulatory, technological, and analytic landscape as it relates to PGHD in oncology research and care. The review begins with a rationale for PGHD as described by the US Food and Drug Administration, the Institute of Medicine, and other regulatory and scientific organizations. The evidence base for clinic-based and remote symptom monitoring using PGHD is described, with an emphasis on PROs. An overview is presented of current approaches to digital phenotyping or device-based, real-time assessment of biometric, behavioral, self-report, and performance data. Analytic opportunities regarding PGHD are envisioned in the context of big data and artificial intelligence in medicine. Finally, challenges and solutions for the integration of PGHD into clinical care are presented. The challenges include electronic medical record integration of PROs and biometric data, analysis of large and complex biometric data sets, and potential clinic workflow redesign. In addition, there is currently more limited evidence for the use of biometric data relative to PROs. Despite these challenges, the potential benefits of PGHD make them increasingly likely to be integrated into oncology research and clinical care.