Multivariate pattern analysis utilizing structural or functional MRI-In individuals with musculoskeletal pain and healthy controls: A systematic review

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

Neuroimaging data from multiple batches (i.e. acquisition sites, scanner manufacturer, datasets, etc.) are increasingly necessary to gain new insights into the human brain. However, multi-batch data, as well as extracted radiomic features, exhibit pronounced technical artifacts across batches. These batch effects introduce confounding into the data and can obscure biological effects of interest, decreasing the generalizability and reproducibility of findings. This is especially true when multi-batch data is used alongside complex downstream analysis models, such as machine learning methods. Image harmonization methods seeking to remove these batch effects are important for mitigating these issues; however, significant multivariate batch effects remain in the data following harmonization by current state-of-the-art statistical and deep learning methods. We present DeepCombat, a deep learning harmonization method based on a conditional variational autoencoder architecture and the ComBat harmonization model. DeepCombat learns and removes subject-level batch effects by accounting for the multivariate relationships between features. Additionally, DeepComBat relaxes a number of strong assumptions commonly made by previous deep learning harmonization methods and is empirically robust across a wide range of hyperparameter choices. We apply this method to neuroimaging data from a large cognitive-aging cohort and find that DeepCombat outperforms existing methods, as assessed by a battery of machine learning methods, in removing scanner effects from cortical thickness measurements while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically-motivated deep learning harmonization methods.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

•

An overview of systematic reviews on the application of AI including 129 studies.

•

AI use is prominent in Universal Health Coverage, featuring image analysis in neoplasms.

•

Half of the reviews did not evaluate validation procedures nor reporting guidelines.

•

Risk of bias was only included un a third of the reviews.

•

There is not sufficient evidence to transfer AI to actual healthcare delivery.

Background

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people’s health. It is necessary to assess the current status on the application of AI towards the improvement of people’s health in the domains defined by WHO’s Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

Objective

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people’s health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

Methods

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO’s PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

Results

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

Conclusion

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Pain modalities in the body and brain: Current knowledge and future perspectives

Development and validation of pain biomarkers has become a major issue in pain research. Recent advances in multimodal data acquisition have allowed researchers to gather multivariate and multilevel whole-body measurements in patients with pain conditions, and data analysis techniques such as machine learning have led to novel findings in neural biomarkers for pain. Most studies have focused on the development of a biomarker to predict the severity of pain with high precision and high specificity, however, a similar approach to discriminate different modalities of pain is lacking. Identification of more accurate and specific pain biomarkers will require an in-depth understanding of the modality specificity of pain. In this review, we summarize early and recent findings on the modality specificity of pain in the brain, with a focus on distinct neural activity patterns between chronic clinical and acute experimental pain, direct, social, and vicarious pain, and somatic and visceral pain. We also suggest future directions to improve our current strategy of pain management using our knowledge of modality-specific aspects of pain.

The neurologic pain signature responds to nonsteroidal anti-inflammatory treatment vs placebo in knee osteoarthritis

Supplemental Digital Content is Available in the Text.

fMRI-based measures, validated for nociceptive pain, respond to acute osteoarthritis pain, are not sensitive to placebo, and are mild-to-moderately sensitive to naproxen.

Introduction:

Many drug trials for chronic pain fail because of high placebo response rates in primary endpoints. Neurophysiological measures can help identify pain-linked pathophysiology and treatment mechanisms. They can also help guide early stop/go decisions, particularly if they respond to verum treatment but not placebo. The neurologic pain signature (NPS), an fMRI-based measure that tracks evoked pain in 40 published samples and is insensitive to placebo in healthy adults, provides a potentially useful neurophysiological measure linked to nociceptive pain.

Objectives:

This study aims to validate the NPS in knee osteoarthritis (OA) patients and test the effects of naproxen on this signature.

Methods:

In 2 studies (50 patients, 64.6 years, 75% females), we (1) test the NPS and other control signatures related to negative emotion in knee OA pain patients; (2) test the effect of placebo treatments; and (3) test the effect of naproxen, a routinely prescribed nonsteroidal anti-inflammatory drug in OA.

Results:

The NPS was activated during knee pain in OA (d = 1.51, P < 0.001) and did not respond to placebo (d = 0.12, P = 0.23). A single dose of naproxen reduced NPS responses (vs placebo, NPS d = 0.34, P = 0.03 and pronociceptive NPS component d = 0.38, P = 0.02). Naproxen effects were specific for the NPS and did not appear in other control signatures.

Conclusion:

This study provides preliminary evidence that fMRI-based measures, validated for nociceptive pain, respond to acute OA pain, do not appear sensitive to placebo, and are mild-to-moderately sensitive to naproxen.

Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study

Artificial intelligence (AI) centred diagnostic systems are increasingly recognised as robust solutions in healthcare delivery pathways. In turn, there has been a concurrent rise in secondary research studies regarding these technologies in order to influence key clinical and policymaking decisions. It is therefore essential that these studies accurately appraise methodological quality and risk of bias within shortlisted trials and reports. In order to assess whether this critical step is performed, we undertook a meta-research study evaluating adherence to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool within AI diagnostic accuracy systematic reviews. A literature search was conducted on all studies published from 2000 to December 2020. Of 50 included reviews, 36 performed the quality assessment, of which 27 utilised the QUADAS-2 tool. Bias was reported across all four domains of QUADAS-2. Two hundred forty-three of 423 studies (57.5%) across all systematic reviews utilising QUADAS-2 reported a high or unclear risk of bias in the patient selection domain, 110 (26%) reported a high or unclear risk of bias in the index test domain, 121 (28.6%) in the reference standard domain and 157 (37.1%) in the flow and timing domain. This study demonstrates the incomplete uptake of quality assessment tools in reviews of AI-based diagnostic accuracy studies and highlights inconsistent reporting across all domains of quality assessment. Poor standards of reporting act as barriers to clinical implementation. The creation of an AI-specific extension for quality assessment tools of diagnostic accuracy AI studies may facilitate the safe translation of AI tools into clinical practice.

Mitigating site effects in covariance for machine learning in neuroimaging data

To acquire larger samples for answering complex questions in neuroscience, researchers have increasingly turned to multi‐site neuroimaging studies. However, these studies are hindered by differences in images acquired across multiple sites. These effects have been shown to bias comparison between sites, mask biologically meaningful associations, and even introduce spurious associations. To address this, the field has focused on harmonizing data by removing site‐related effects in the mean and variance of measurements. Contemporaneously with the increase in popularity of multi‐center imaging, the use of machine learning (ML) in neuroimaging has also become commonplace. These approaches have been shown to provide improved sensitivity, specificity, and power due to their modeling the joint relationship across measurements in the brain. In this work, we demonstrate that methods for removing site effects in mean and variance may not be sufficient for ML. This stems from the fact that such methods fail to address how correlations between measurements can vary across sites. Data from the Alzheimer's Disease Neuroimaging Initiative is used to show that considerable differences in covariance exist across sites and that popular harmonization techniques do not address this issue. We then propose a novel harmonization method called Correcting Covariance Batch Effects (CovBat) that removes site effects in mean, variance, and covariance. We apply CovBat and show that within‐site correlation matrices are successfully harmonized. Furthermore, we find that ML methods are unable to distinguish scanner manufacturer after our proposed harmonization is applied, and that the CovBat‐harmonized data retain accurate prediction of disease group.

Machine Learning in Chronic Pain Research: A Scoping Review

Given the high prevalence and associated cost of chronic pain, it has a significant impact on individuals and society. Improvements in the treatment and management of chronic pain may increase patients’ quality of life and reduce societal costs. In this paper, we evaluate state-of-the-art machine learning approaches in chronic pain research. A literature search was conducted using the PubMed, IEEE Xplore, and the Association of Computing Machinery (ACM) Digital Library databases. Relevant studies were identified by screening titles and abstracts for keywords related to chronic pain and machine learning, followed by analysing full texts. Two hundred and eighty-seven publications were identified in the literature search. In total, fifty-three papers on chronic pain research and machine learning were reviewed. The review showed that while many studies have emphasised machine learning-based classification for the diagnosis of chronic pain, far less attention has been paid to the treatment and management of chronic pain. More research is needed on machine learning approaches to the treatment, rehabilitation, and self-management of chronic pain. As with other chronic conditions, patient involvement and self-management are crucial. In order to achieve this, patients with chronic pain need digital tools that can help them make decisions about their own treatment and care.

Neuroimaging-based biomarkers for pain: state of the field and current directions

Chronic pain is an endemic problem involving both peripheral and brain pathophysiology. Although biomarkers have revolutionized many areas of medicine, biomarkers for pain have remained controversial and relatively underdeveloped. With the realization that biomarkers can reveal pain-causing mechanisms of disease in brain circuits and in the periphery, this situation is poised to change. In particular, brain pathophysiology may be diagnosable with human brain imaging, particularly when imaging is combined with machine learning techniques designed to identify predictive measures embedded in complex data sets. In this review, we explicate the need for brain-based biomarkers for pain, some of their potential uses, and some of the most popular machine learning approaches that have been brought to bear. Then, we evaluate the current state of pain biomarkers developed with several commonly used methods, including structural magnetic resonance imaging, functional magnetic resonance imaging and electroencephalography. The field is in the early stages of biomarker development, but these complementary methodologies have already produced some encouraging predictive models that must be tested more extensively across laboratories and clinical populations.

Delineating conditions and subtypes in chronic pain using neuroimaging

Differentiating subtypes of chronic pain still remains a challenge—both from a subjective and objective point of view. Personalized medicine is the current goal of modern medical care and is limited by the subjective nature of patient self-reporting of symptoms and behavioral evaluation. Physiology-focused techniques such as genome and epigenetic analyses inform the delineation of pain groups; however, except under rare circumstances, they have diluted effects that again, share a common reliance on behavioral evaluation. The application of structural neuroimaging towards distinguishing pain subtypes is a growing field and may inform pain-group classification through the analysis of brain regions showing hypertrophic and atrophic changes in the presence of pain. Analytical techniques such as machine-learning classifiers have the capacity to process large volumes of data and delineate diagnostically relevant information from neuroimaging analysis. The issue of defining a “brain type” is an emerging field aimed at interpreting observed brain changes and delineating their clinical identity/significance. In this review, 2 chronic pain conditions (migraine and irritable bowel syndrome) with similar clinical phenotypes are compared in terms of their structural neuroimaging findings. Independent investigations are compared with findings from application of machine-learning algorithms. Findings are discussed in terms of differentiating patient subgroups using neuroimaging data in patients with chronic pain and how they may be applied towards defining a personalized pain signature that helps segregate patient subgroups (eg, migraine with and without aura, with or without nausea; irritable bowel syndrome vs other functional gastrointestinal disorders).

Mechanisms Underlying Bone and Joint Pain

PURPOSE OF REVIEW

The goal of this review is to provide a broad overview of the current understanding of mechanisms underlying bone and joint pain.

RECENT FINDINGS

Bone or joint pathology is generally accompanied by local release of pro-inflammatory cytokines, growth factors, and neurotransmitters that activate and sensitize sensory nerves resulting in an amplified pain signal. Modulation of the pain signal within the spinal cord and brain that result in net increased facilitation is proposed to contribute to the development of chronic pain. Great strides have been made in our understanding of mechanisms underlying bone and joint pain that will guide development of improved therapeutic options for these patients. Continued research is required for improved understanding of mechanistic differences driving different components of bone and/or joint pain such as movement related pain compared to persistent background pain. Advances will guide development of more individualized and comprehensive therapeutic options.