Assessment of a Deep Learning Model Based on Electronic Health Record Data to Forecast Clinical Outcomes in Patients With Rheumatoid Arthritis

Artificial intelligence and machine learning in axial spondyloarthritis

PURPOSE OF REVIEW

To evaluate the current applications and prospects of artificial intelligence and machine learning in diagnosing and managing axial spondyloarthritis (axSpA), focusing on their role in medical imaging, predictive modelling, and patient monitoring.

RECENT FINDINGS

Artificial intelligence, particularly deep learning, is showing promise in diagnosing axSpA assisting with X-ray, computed tomography (CT) and MRI analyses, with some models matching or outperforming radiologists in detecting sacroiliitis and markers. Moreover, it is increasingly being used in predictive modelling of disease progression and personalized treatment, and could aid risk assessment, treatment response and clinical subtype identification. Variable study designs, sample sizes and the predominance of retrospective, single-centre studies still limit the generalizability of results.

SUMMARY

Artificial intelligence technologies have significant potential to advance the diagnosis and treatment of axSpA, providing more accurate, efficient and personalized healthcare solutions. However, their integration into clinical practice requires rigorous validation, ethical and legal considerations, and comprehensive training for healthcare professionals. Future advances in artificial intelligence could complement clinical expertise and improve patient care through improved diagnostic accuracy and tailored therapeutic strategies, but the challenge remains to ensure that these technologies are validated in prospective multicentre trials and ethically integrated into patient care.

Development of a Machine Learning Model to Predict the Use of Surgery in Patients With Rheumatoid Arthritis

OBJECTIVE

One in five patients with rheumatoid arthritis (RA) rely on surgery to restore joint function. However, variable response to disease-modifying antirheumatic drugs (DMARDs) complicates surgical planning, and it is difficult to predict which patients may ultimately require surgery. We used machine learning to develop predictive models for the likelihood of undergoing an operation related to RA and which type of operation patients who require surgery undergo.

METHODS

We used electronic health record data to train two extreme gradient boosting machine learning models. The first model predicted patients' probabilities of undergoing surgery ≥5 years after their initial clinic visit. The second model predicted whether patients who underwent surgery would undergo a major joint replacement versus a less intensive procedure. Predictors included demographics, comorbidities, and medication data. The primary outcome was model discrimination, measured by area under the receiver operating characteristic curve (AUC).

RESULTS

We identified 5,481 patients, of whom 278 (5.1%) underwent surgery. There was no significant difference in the frequency of DMARD or steroid prescriptions between patients who did and did not have surgery, though nonsteroidal anti-inflammatory drug prescriptions were more common among patients who did have surgery (P = 0.03). The model predicting use of surgery had an AUC of 0.90 ± 0.02. The model predicting type of surgery had an AUC of 0.58 ± 0.10.

CONCLUSIONS

Predictive models using clinical data have the potential to facilitate identification of patients who may undergo rheumatoid-related surgery, but not what type of procedure they will need. Integrating similar models into practice has the potential to improve surgical planning.

Exploring the impact of pathogenic microbiome in orthopedic diseases: machine learning and deep learning approaches

Osteoporosis, arthritis, and fractures are examples of orthopedic illnesses that not only significantly impair patients' quality of life but also complicate and raise the expense of therapy. It has been discovered in recent years that the pathophysiology of orthopedic disorders is significantly influenced by the microbiota. By employing machine learning and deep learning techniques to conduct a thorough analysis of the disease-causing microbiome, we can enhance our comprehension of the pathophysiology of many illnesses and expedite the creation of novel treatment approaches. Today's science is undergoing a revolution because to the introduction of machine learning and deep learning technologies, and the field of biomedical research is no exception. The genesis, course, and management of orthopedic disorders are significantly influenced by pathogenic microbes. Orthopedic infection diagnosis and treatment are made more difficult by the lengthy and imprecise nature of traditional microbial detection and characterization techniques. These cutting-edge analytical techniques are offering previously unheard-of insights into the intricate relationships between orthopedic health and pathogenic microbes, opening up previously unimaginable possibilities for illness diagnosis, treatment, and prevention. The goal of biomedical research has always been to improve diagnostic and treatment methods while also gaining a deeper knowledge of the processes behind the onset and development of disease. Although traditional biomedical research methodologies have demonstrated certain limits throughout time, they nevertheless rely heavily on experimental data and expertise. This is the area in which deep learning and machine learning approaches excel. The advancements in machine learning (ML) and deep learning (DL) methodologies have enabled us to examine vast quantities of data and unveil intricate connections between microorganisms and orthopedic disorders. The importance of ML and DL in detecting, categorizing, and forecasting harmful microorganisms in orthopedic infectious illnesses is reviewed in this work.

Advancing Rheumatology Care Through Machine Learning

Rheumatologic diseases are marked by their complexity, involving immune-, metabolic- and mechanically mediated processes which can affect different organ systems. Despite a growing arsenal of targeted medications, many rheumatology patients fail to achieve full remission. Assessing disease activity remains challenging, as patients prioritize different symptoms and disease phenotypes vary. This is also reflected in clinical trials where the efficacy of drugs is not necessarily measured in an optimal way with the traditional outcome assessment. The recent COVID-19 pandemic has catalyzed a digital transformation in healthcare, embracing telemonitoring and patient-reported data via apps and wearables. As a further driver of digital medicine, electronic medical record (EMR) providers are actively engaged in developing algorithms for clinical decision support, heralding a shift towards patient-centered, decentralized care. Machine learning algorithms have emerged as valuable tools for handling the increasing volume of patient data, promising to enhance treatment quality and patient well-being. Convolutional neural networks (CNN) are particularly promising for radiological image analysis, aiding in the detection of specific lesions such as erosions, sacroiliitis, or osteoarthritis, with several FDA-approved applications. Clinical predictions, including numerical disease activity forecasts and medication choices, offer the potential to optimize treatment strategies. Numeric predictions can be integrated into clinical workflows, allowing for shared decision making with patients. Clustering patients based on disease characteristics provides a personalized care approach. Digital biomarkers, such as patient-reported outcomes and wearables data, offer insights into disease progression and therapy response more flexibly and outside patient consultations. In association with patient-reported outcomes, disease-specific digital biomarkers via image recognition or single-camera motion capture enables more efficient remote patient monitoring. Digital biomarkers may also play a major role in clinical trials in the future as continuous, disease-specific outcome measurement facilitating decentralized studies. Prediction models can help with patient selection in clinical trials, such as by predicting high disease activity. Efforts are underway to integrate these advancements into clinical workflows using digital pathways and remote patient monitoring platforms. In summary, machine learning, digital biomarkers, and advanced imaging technologies hold immense promise for enhancing clinical decision support and clinical trials in rheumatology. Effective integration will require a multidisciplinary approach and continued validation through prospective studies.

Temporal self-attention for risk prediction from electronic health records using non-stationary kernel approximation

Effective modeling of patient representation from electronic health records (EHRs) is increasingly becoming a vital research topic. Yet, modeling the non-stationarity in EHR data has received less attention. Most existing studies follow a strong assumption of stationarity in patient representation from EHRs. However, in practice, a patient's visits are irregularly spaced over a relatively long period of time, and disease progression patterns exhibit non-stationarity. Furthermore, the time gaps between patient visits often encapsulate significant domain knowledge, potentially revealing undiscovered patterns that characterize specific medical conditions. To address these challenges, we introduce a new method which combines the self-attention mechanism with non-stationary kernel approximation to capture both contextual information and temporal relationships between patient visits in EHRs. To assess the effectiveness of our proposed approach, we use two real-world EHR datasets, comprising a total of 76,925 patients, for the task of predicting the next diagnosis code for a patient, given their EHR history. The first dataset is a general EHR cohort and consists of 11,451 patients with a total of 3,485 unique diagnosis codes. The second dataset is a disease-specific cohort that includes 65,474 pregnant patients and encompasses a total of 9,782 unique diagnosis codes. Our experimental evaluation involved nine prediction models, categorized into three distinct groups. Group 1 comprises the baselines: original self-attention with positional encoding model, RETAIN model, and LSTM model. Group 2 includes models employing self-attention with stationary kernel approximations, specifically incorporating three variations of Bochner's feature maps. Lastly, Group 3 consists of models utilizing self-attention with non-stationary kernel approximations, including quadratic, cubic, and bi-quadratic polynomials. The experimental results demonstrate that non-stationary kernels significantly outperformed baseline methods for NDCG@10 and Hit@10 metrics in both datasets. The performance boost was more substantial in dataset 1 for the NDCG@10 metric. On the other hand, stationary Kernels showed significant but smaller gains over baselines and were nearly as effective as Non-stationary Kernels for Hit@10 in dataset 2. These findings robustly validate the efficacy of employing non-stationary kernels for temporal modeling of EHR data, and emphasize the importance of modeling non-stationary temporal information in healthcare prediction tasks.

Machine learning application in autoimmune diseases: State of art and future prospectives

Autoimmune diseases are a group of disorders resulting from an alteration of immune tolerance, characterized by the formation of autoantibodies and the consequent development of heterogeneous clinical manifestations. Diagnosing autoimmune diseases is often complicated, and the available prognostic tools are limited. Machine learning allows us to analyze large amounts of data and carry out complex calculations quickly and with minimal effort. In this work, we examine the literature focusing on the use of machine learning in the field of the main systemic (systemic lupus erythematosus and rheumatoid arthritis) and organ-specific autoimmune diseases (type 1 diabetes mellitus, autoimmune thyroid, gastrointestinal, and skin diseases). From our analysis, interesting applications of machine learning emerged for developing algorithms useful in the early diagnosis of disease or prognostic models (risk of complications, therapeutic response). Subsequent studies and the creation of increasingly rich databases to be supplied to the algorithms will eventually guide the clinician in the diagnosis, allowing intervention when the pathology is still in an early stage and immediately directing towards a correct therapeutic approach.

Artificial intelligence in rheumatoid arthritis: potential applications and future implications

The widespread adoption of digital health records, coupled with the rise of advanced diagnostic testing, has resulted in an explosion of patient data, comparable in scope to genomic datasets. This vast information repository offers significant potential for improving patient outcomes and decision-making, provided one can extract meaningful insights from it. This is where artificial intelligence (AI) tools like machine learning (ML) and deep learning come into play, helping us leverage these enormous datasets to predict outcomes and make informed decisions. AI models can be trained to analyze and interpret patient data, including physician notes, laboratory testing, and imaging, to aid in the management of patients with rheumatic diseases. As one of the most common autoimmune diseases, rheumatoid arthritis (RA) has attracted considerable attention, particularly concerning the evolution of diagnostic techniques and therapeutic interventions. Our aim is to underscore those areas where AI, according to recent research, demonstrates promising potential to enhance the management of patients with RA.

Physicians' Perspectives on AI in Clinical Decision Support Systems: Interview Study of the CURATE.AI Personalized Dose Optimization Platform

BACKGROUND

Physicians play a key role in integrating new clinical technology into care practices through user feedback and growth propositions to developers of the technology. As physicians are stakeholders involved through the technology iteration process, understanding their roles as users can provide nuanced insights into the workings of these technologies that are being explored. Therefore, understanding physicians' perceptions can be critical toward clinical validation, implementation, and downstream adoption. Given the increasing prevalence of clinical decision support systems (CDSSs), there remains a need to gain an in-depth understanding of physicians' perceptions and expectations toward their downstream implementation. This paper explores physicians' perceptions of integrating CURATE.AI, a novel artificial intelligence (AI)-based and clinical stage personalized dosing CDSSs, into clinical practice.

OBJECTIVE

This study aims to understand physicians' perspectives of integrating CURATE.AI for clinical work and to gather insights on considerations of the implementation of AI-based CDSS tools.

METHODS

A total of 12 participants completed semistructured interviews examining their knowledge, experience, attitudes, risks, and future course of the personalized combination therapy dosing platform, CURATE.AI. Interviews were audio recorded, transcribed verbatim, and coded manually. The data were thematically analyzed.

RESULTS

Overall, 3 broad themes and 9 subthemes were identified through thematic analysis. The themes covered considerations that physicians perceived as significant across various stages of new technology development, including trial, clinical implementation, and mass adoption.

CONCLUSIONS

The study laid out the various ways physicians interpreted an AI-based personalized dosing CDSS, CURATE.AI, for their clinical practice. The research pointed out that physicians' expectations during the different stages of technology exploration can be nuanced and layered with expectations of implementation that are relevant for technology developers and researchers.

Temporal Generalizability of Machine Learning Models for Predicting Postoperative Delirium Using Electronic Health Record Data: Model Development and Validation Study

BACKGROUND

Although machine learning models demonstrate significant potential in predicting postoperative delirium, the advantages of their implementation in real-world settings remain unclear and require a comparison with conventional models in practical applications.

OBJECTIVE

The objective of this study was to validate the temporal generalizability of decision tree ensemble and sparse linear regression models for predicting delirium after surgery compared with that of the traditional logistic regression model.

METHODS

The health record data of patients hospitalized at an advanced emergency and critical care medical center in Kumamoto, Japan, were collected electronically. We developed a decision tree ensemble model using extreme gradient boosting (XGBoost) and a sparse linear regression model using least absolute shrinkage and selection operator (LASSO) regression. To evaluate the predictive performance of the model, we used the area under the receiver operating characteristic curve (AUROC) and the Matthews correlation coefficient (MCC) to measure discrimination and the slope and intercept of the regression between predicted and observed probabilities to measure calibration. The Brier score was evaluated as an overall performance metric. We included 11,863 consecutive patients who underwent surgery with general anesthesia between December 2017 and February 2022. The patients were divided into a derivation cohort before the COVID-19 pandemic and a validation cohort during the COVID-19 pandemic. Postoperative delirium was diagnosed according to the confusion assessment method.

RESULTS

A total of 6497 patients (68.5, SD 14.4 years, women n=2627, 40.4%) were included in the derivation cohort, and 5366 patients (67.8, SD 14.6 years, women n=2105, 39.2%) were included in the validation cohort. Regarding discrimination, the XGBoost model (AUROC 0.87-0.90 and MCC 0.34-0.44) did not significantly outperform the LASSO model (AUROC 0.86-0.89 and MCC 0.34-0.41). The logistic regression model (AUROC 0.84-0.88, MCC 0.33-0.40, slope 1.01-1.19, intercept -0.16 to 0.06, and Brier score 0.06-0.07), with 8 predictors (age, intensive care unit, neurosurgery, emergency admission, anesthesia time, BMI, blood loss during surgery, and use of an ambulance) achieved good predictive performance.

CONCLUSIONS

The XGBoost model did not significantly outperform the LASSO model in predicting postoperative delirium. Furthermore, a parsimonious logistic model with a few important predictors achieved comparable performance to machine learning models in predicting postoperative delirium.

Computer model of IL-6-dependent rheumatoid arthritis in F759 mice

The interleukin-6 (IL-6) amplifier, which describes the simultaneous activation of signal transducer and activator of transcription 3 (STAT3) and NF-κb nuclear factor kappa B (NF-κB), in synovial fibroblasts causes the infiltration of immune cells into the joints of F759 mice. The result is a disease that resembles human rheumatoid arthritis. However, the kinetics and regulatory mechanisms of how augmented transcriptional activation by STAT3 and NF-κB leads to F759 arthritis is unknown. We here show that the STAT3-NF-κB complex is present in the cytoplasm and nucleus and accumulates around NF-κB binding sites of the IL-6 promoter region and established a computer model that shows IL-6 and IL-17 (interleukin 17) signaling promotes the formation of the STAT3-NF-κB complex followed by its binding on promoter regions of NF-κB target genes to accelerate inflammatory responses, including the production of IL-6, epiregulin, and C-C motif chemokine ligand 2 (CCL2), phenotypes consistent with in vitro experiments. The binding also promoted cell growth in the synovium and the recruitment of T helper 17 (Th17) cells and macrophages in the joints. Anti-IL-6 blocking antibody treatment inhibited inflammatory responses even at the late phase, but anti-IL-17 and anti-TNFα antibodies did not. However, anti-IL-17 antibody at the early phase showed inhibitory effects, suggesting that the IL-6 amplifier is dependent on IL-6 and IL-17 stimulation at the early phase, but only on IL-6 at the late phase. These findings demonstrate the molecular mechanism of F759 arthritis can be recapitulated in silico and identify a possible therapeutic strategy for IL-6 amplifier-dependent chronic inflammatory diseases.

Performance of advanced machine learning algorithms overlogistic regression in predicting hospital readmissions: A meta-analysis

Objectives

Machine learning algorithms are being increasingly used for predicting hospital readmissions. This meta-analysis evaluated the performance of logistic regression (LR) and machine learning (ML) models for the prediction of 30-day hospital readmission among patients in the US.

Methods

Electronic databases (i.e., Medline, PubMed, and Embase) were searched from January 2015 to December 2019. Only studies in the English language were included. Two reviewers performed studies screening, quality appraisal, and data collection. The quality of the studies was assessed using the Quality in Prognosis Studies (QUIPS) tool. Model performance was evaluated using the Area Under the Curve (AUC). A random-effects meta-analysis was performed using STATA 16.

Results

Nine studies were included based on the selection criteria. The most common ML techniques were tree-based methods such as boosting and random forest. Most of the studies had a low risk of bias (8/9). The AUC was greater with ML to predict 30-day all-cause hospital readmission compared with LR [Mean Difference (MD): 0.03; 95% Confidence Interval (CI) 0.01-0.05]. Subgroup analyses found that deep-learning methods had a better performance compared with LR (MD 0.06; 95% CI, 0.04-0.09), followed by neural networks (MD: 0.03; 95% CI, 0.03-0.03), while the AUCs of the tree-based (MD: 0.02; 95% CI -0.00-0.04) and kernel-based (MD: 0.02; 95% CI 0.02 (-0.13-0.16) methods were no different compared to LR. More than half of the studies evaluated heart failure-related rehospitalization (N = 5). For the readmission prediction among heart failure patients, ML performed better compared with LR, with a mean difference in AUC of 0.04 (95% CI, 0.01-0.07). The leave-one-out sensitivity analysis confirmed the robustness of the findings.

Conclusion

Multiple ML methods were used to predict 30-day all-cause hospital readmission. Performance varied across the ML methods, with deep-learning methods showing the best performance over the LR.

Assessment of Prediction Tasks and Time Window Selection in Temporal Modeling of Electronic Health Record Data: a Systematic Review

Temporal electronic health record (EHR) data are often preferred for clinical prediction tasks because they offer more complete representations of a patient's pathophysiology than static data. A challenge when working with temporal EHR data is problem formulation, which includes defining the time windows of interest and the prediction task. Our objective was to conduct a systematic review that assessed the definition and reporting of concepts relevant to temporal clinical prediction tasks. We searched PubMed® and IEEE Xplore® databases for studies from January 1, 2010 applying machine learning models to EHR data for patient outcome prediction. Publications applying time-series methods were selected for further review. We identified 92 studies and summarized them by clinical context and definition and reporting of the prediction problem. For the time windows of interest, 12 studies did not discuss window lengths, 57 used a single set of window lengths, and 23 evaluated the relationship between window length and model performance. We also found that 72 studies had appropriate reporting of the prediction task. However, evaluation of prediction problem formulation for temporal EHR data was complicated by heterogeneity in assessing and reporting of these concepts. Even among studies modeling similar clinical outcomes, there were variations in terminology used to describe the prediction problem, rationale for window lengths, and determination of the outcome of interest. As temporal modeling using EHR data expands, minimal reporting standards should include time-series specific concerns to promote rigor and reproducibility in future studies and facilitate model implementation in clinical settings.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00143-4.

lab: an R package for generating analysis-ready data from laboratory records

Background

Electronic health records (EHRs) play a crucial role in healthcare decision-making by giving physicians insights into disease progression and suitable treatment options. Within EHRs, laboratory test results are frequently utilized for predicting disease progression. However, processing laboratory test results often poses challenges due to variations in units and formats. In addition, leveraging the temporal information in EHRs can improve outcomes, prognoses, and diagnosis predication. Nevertheless, the irregular frequency of the data in these records necessitates data preprocessing, which can add complexity to time-series analyses.

Methods

To address these challenges, we developed an open-source R package that facilitates the extraction of temporal information from laboratory records. The proposed lab package generates analysis-ready time series data by segmenting the data into time-series windows and imputing missing values. Moreover, users can map local laboratory codes to the Logical Observation Identifier Names and Codes (LOINC), an international standard. This mapping allows users to incorporate additional information, such as reference ranges and related diseases. Moreover, the reference ranges provided by LOINC enable us to categorize results into normal or abnormal. Finally, the analysis-ready time series data can be further summarized using descriptive statistics and utilized to develop models using machine learning technologies.

Results

Using the lab package, we analyzed data from MIMIC-III, focusing on newborns with patent ductus arteriosus (PDA). We extracted time-series laboratory records and compared the differences in test results between patients with and without 30-day in-hospital mortality. We then identified significant variations in several laboratory test results 7 days after PDA diagnosis. Leveraging the time series-analysis-ready data, we trained a prediction model with the long short-term memory algorithm, achieving an area under the receiver operating characteristic curve of 0.83 for predicting 30-day in-hospital mortality in model training. These findings demonstrate the lab package's effectiveness in analyzing disease progression.

Conclusions

The proposed lab package simplifies and expedites the workflow involved in laboratory records extraction. This tool is particularly valuable in assisting clinical data analysts in overcoming the obstacles associated with heterogeneous and sparse laboratory records.

Understanding the role and adoption of artificial intelligence techniques in rheumatology research: An in-depth review of the literature

The major and upward trend in the number of published research related to rheumatic and musculoskeletal diseases, in which artificial intelligence plays a key role, has exhibited the interest of rheumatology researchers in using these techniques to answer their research questions. In this review, we analyse the original research articles that combine both worlds in a five- year period (2017-2021). In contrast to other published papers on the same topic, we first studied the review and recommendation articles that were published during that period, including up to October 2022, as well as the publication trends. Secondly, we review the published research articles and classify them into one of the following categories: disease identification and prediction, disease classification, patient stratification and disease subtype identification, disease progression and activity, treatment response, and predictors of outcomes. Thirdly, we provide a table with illustrative studies in which artificial intelligence techniques have played a central role in more than twenty rheumatic and musculoskeletal diseases. Finally, the findings of the research articles, in terms of disease and/or data science techniques employed, are highlighted in a discussion. Therefore, the present review aims to characterise how researchers are applying data science techniques in the rheumatology medical field. The most immediate conclusions that can be drawn from this work are: multiple and novel data science techniques have been used in a wide range of rheumatic and musculoskeletal diseases including rare diseases; the sample size and the data type used are heterogeneous, and new technical approaches are expected to arrive in the short-middle term.

Bottom-up and top-down paradigms of artificial intelligence research approaches to healthcare data science using growing real-world big data

OBJECTIVES

As the real-world electronic health record (EHR) data continue to grow exponentially, novel methodologies involving artificial intelligence (AI) are becoming increasingly applied to enable efficient data-driven learning and, ultimately, to advance healthcare. Our objective is to provide readers with an understanding of evolving computational methods and help in deciding on methods to pursue.

TARGET AUDIENCE

The sheer diversity of existing methods presents a challenge for health scientists who are beginning to apply computational methods to their research. Therefore, this tutorial is aimed at scientists working with EHR data who are early entrants into the field of applying AI methodologies.

SCOPE

This manuscript describes the diverse and growing AI research approaches in healthcare data science and categorizes them into 2 distinct paradigms, the bottom-up and top-down paradigms to provide health scientists venturing into artificial intelligent research with an understanding of the evolving computational methods and help in deciding on methods to pursue through the lens of real-world healthcare data.

A survey of artificial intelligence in rheumatoid arthritis

The article offers a survey of currently notable artificial intelligence methods (released between 2019-2023), with a particular emphasis on the latest advancements in detecting rheumatoid arthritis (RA) at an early stage, providing early treatment, and managing the disease. We discussed challenges in these areas followed by specific artificial intelligence (AI) techniques and summarized advances, relevant strengths, and obstacles. Overall, the application of AI in the fields of RA has the potential to enable healthcare professionals to detect RA at an earlier stage, thereby facilitating timely intervention and better disease management. However, more research is required to confirm the precision and dependability of AI in RA, and several problems such as technological and ethical concerns related to these approaches must be resolved before their widespread adoption.

Developing and Validating Models to Predict Progression to Proliferative Diabetic Retinopathy

Purpose

To develop models for progression of nonproliferative diabetic retinopathy (NPDR) to proliferative diabetic retinopathy (PDR) and determine if incorporating updated information improves model performance.

Design

Retrospective cohort study.

Participants

Electronic health record (EHR) data from a tertiary academic center, University of California San Francisco (UCSF), and a safety-net hospital, Zuckerberg San Francisco General (ZSFG) Hospital were used to identify patients with a diagnosis of NPDR, age ≥ 18 years, a diagnosis of type 1 or 2 diabetes mellitus, ≥ 6 months of ophthalmology follow-up, and no prior diagnosis of PDR before the index date (date of first NPDR diagnosis in the EHR).

Methods

Four survival models were developed: Cox proportional hazards, Cox with backward selection, Cox with LASSO regression and Random Survival Forest. For each model, three variable sets were compared to determine the impact of including updated clinical information: Static₀ (data up to the index date), Static_6m (data updated 6 months after the index date), and Dynamic (data in Static₀ plus data change during the 6-month period). The UCSF data were split into 80% training and 20% testing (internal validation). The ZSFG data were used for external validation. Model performance was evaluated by the Harrell's concordance index (C-Index).

Main Outcome Measures

Time to PDR.

Results

The UCSF cohort included 1130 patients and 92 (8.1%) patients progressed to PDR. The ZSFG cohort included 687 patients and 30 (4.4%) patients progressed to PDR. All models performed similarly (C-indices ∼ 0.70) in internal validation. The random survival forest with Static_6m set performed best in external validation (C-index 0.76). Insurance and age were selected or ranked as highly important by all models. Other key predictors were NPDR severity, diabetic neuropathy, number of strokes, mean Hemoglobin A1c, and number of hospital admissions.

Conclusions

Our models for progression of NPDR to PDR achieved acceptable predictive performance and validated well in an external setting. Updating the baseline variables with new clinical information did not consistently improve the predictive performance.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Artificial Intelligence and laboratory data in rheumatic diseases

Artificial intelligence (AI)-based medical technologies are rapidly evolving into actionable solutions for clinical practice. Machine learning (ML) algorithms can process increasing amounts of laboratory data such as gene expression immunophenotyping data and biomarkers. In recent years, the analysis of ML has become particularly useful for the study of complex chronic diseases, such as rheumatic diseases, heterogenous conditions with multiple triggers. Numerous studies have used ML to classify patients and improve diagnosis, to stratify the risk and determine disease subtypes, as well as to discover biomarkers and gene signatures. This review aims to provide examples of ML models for specific rheumatic diseases using laboratory data and some insights into relevant strengths and limitations. A better understanding and future application of these analytical strategies could facilitate the development of precision medicine for rheumatic patients.

Specific recommendations to improve the design and conduct of clinical trials

There are many reasons why the majority of clinical trials fail or have limited applicability to patient care. These include restrictive entry criteria, short duration studies, unrecognized adverse drug effects, and reporting of therapy assignment preferential to actual use. Frequently, experimental animal models are used sparingly and do not accurately simulate human disease. We suggest two approaches to improve the conduct, increase the success, and applicability of clinical trials. Studies can apply dosing of the investigational therapeutics and outcomes, determined from animal models that more closely simulate human disease. More extensive identification of known and potential risk factors and confounding issues, gleaned from recently organized "big data," should be utilized to create models for trials. The risk factors in each model are then accounted for and managed during each study.

A Multidatabase ExTRaction PipEline (METRE) for Facile Cross Validation in Critical Care Research

Transforming raw EHR data into machine learning model-ready inputs requires considerable effort. One widely used EHR database is Medical Information Mart for Intensive Care (MIMIC). Prior work on MIMIC-III cannot query the updated and improved MIMIC-IV version. Besides, the need to use multicenter datasets further highlights the challenge of EHR data extraction. Therefore, we developed an extraction pipeline that works on both MIMIC-IV and eICU Collaborative Research Database and allows for model cross validation using these 2 databases. Under the default choices, the pipeline extracted 38,766 and 126,448 ICU records for MIMIC-IV and eICU, respectively. Using the extracted time-dependent variables, we compared the Area Under the Curve (AUC) performance with ​​prior works on clinically relevant tasks such as in-hospital mortality prediction. METRE achieved comparable performance with AUC 0.723-0.888 across all tasks with MIMIC-IV. Additionally, when we evaluated the model directly on MIMIC-IV data using a model trained on eICU, we observed that the AUC change can be as small as +0.019 or -0.015. Our open-source pipeline transforms MIMIC-IV and eICU into structured data frames and allows researchers to perform model training and testing using data collected from different institutions, which is of critical importance for model deployment under clinical contexts.

Artificial intelligence and high-dimensional technologies in the theragnosis of systemic lupus erythematosus

Systemic lupus erythematosus is a complex, systemic autoimmune disease characterised by immune dysregulation. Pathogenesis is multifactorial, contributing to clinical heterogeneity and posing challenges for diagnosis and treatment. Although strides in treatment options have been made in the past 15 years, with the US Food and Drug Administration approval of belimumab in 2011, there are still many patients who have inadequate responses to therapy. A better understanding of underlying disease mechanisms with a holistic and multiparametric approach is required to improve clinical assessment and treatment. This Review discusses the evolution of genomics, epigenomics, transcriptomics, and proteomics in the study of systemic lupus erythematosus and ways to amalgamate these silos of data with a systems-based approach while also discussing ways to strengthen the overall process. These mechanistic insights will facilitate the discovery of functionally relevant biomarkers to guide rational therapeutic selection to improve patient outcomes.

From real-world electronic health record data to real-world results using artificial intelligence

With the worldwide digitalisation of medical records, electronic health records (EHRs) have become an increasingly important source of real-world data (RWD). RWD can complement traditional study designs because it captures almost the complete variety of patients, leading to more generalisable results. For rheumatology, these data are particularly interesting as our diseases are uncommon and often take years to develop. In this review, we discuss the following concepts related to the use of EHR for research and considerations for translation into clinical care: EHR data contain a broad collection of healthcare data covering the multitude of real-life patients and the healthcare processes related to their care. Machine learning (ML) is a powerful method that allows us to leverage a large amount of heterogeneous clinical data for clinical algorithms, but requires extensive training, testing, and validation. Patterns discovered in EHR data using ML are applicable to real life settings, however, are also prone to capturing the local EHR structure and limiting generalisability outside the EHR(s) from which they were developed. Population studies on EHR necessitates knowledge on the factors influencing the data available in the EHR to circumvent biases, for example, access to medical care, insurance status. In summary, EHR data represent a rapidly growing and key resource for real-world studies. However, transforming RWD EHR data for research and for real-world evidence using ML requires knowledge of the EHR system and their differences from existing observational data to ensure that studies incorporate rigorous methods that acknowledge or address factors such as access to care, noise in the data, missingness and indication bias.

Development of a Natural Language Processing System for Extracting Rheumatoid Arthritis Outcomes From Clinical Notes Using the National Rheumatology Informatics System for Effectiveness Registry

OBJECTIVE

To accelerate the use of outcome measures in rheumatology, we developed and evaluated a natural language processing (NLP) pipeline for extracting these measures from free-text outpatient rheumatology notes within the American College of Rheumatology's Rheumatology Informatics System for Effectiveness (RISE) registry.

METHODS

We included all patients in RISE (2015-2018). The NLP pipeline extracted scores corresponding to 8 measures of rheumatoid arthritis (RA) disease activity (DA) and functional status (FS) documented in outpatient rheumatology notes. Score extraction performance was evaluated by chart review, and we assessed agreement with scores documented in structured data. We conducted an external validation of our NLP pipeline using data from rheumatology notes from an academic medical center that is not included in the RISE registry.

RESULTS

We processed over 34 million notes from 854,628 patients, 158 practices, and 24 electronic health record (EHR) systems from RISE. Manual chart review revealed a sensitivity, positive predictive value (PPV), and F1 score of 95%, 87%, and 91%, respectively. Substantial agreement was observed between scores extracted from RISE notes and scores derived from structured data (κ = 0.43-0.68 among DA and 0.86-0.98 among FS measures). In the external validation, we found a sensitivity, PPV, and F1 score of 92%, 69%, and 79%, respectively.

CONCLUSION

We developed an NLP pipeline to extract RA outcome measures from a national registry of notes from multiple EHR systems and found it to have good internal and external validity. This pipeline can facilitate measurement of clinical- and patient-reported outcomes for use in research and quality measurement.

Use of artificial neural networks in the prognosis of musculoskeletal diseases-a scoping review

To determine the current evidence on artificial neural network (ANN) in prognostic studies of musculoskeletal diseases (MSD) and to assess the accuracy of ANN in predicting the prognosis of patients with MSD. The scoping review was reported under the Preferred Items for Systematic Reviews and the Meta-Analyses extension for Scope Reviews (PRISMA-ScR). Cochrane Library, Embase, Pubmed, and Web of science core collection were searched from inception to January 2023. Studies were eligible if they used ANN to make predictions about MSD prognosis. Variables, model prediction accuracy, and disease type used in the ANN model were extracted and charted, then presented as a table along with narrative synthesis. Eighteen Studies were included in this scoping review, with 16 different types of musculoskeletal diseases. The accuracy of the ANN model predictions ranged from 0.542 to 0.947. ANN models were more accurate compared to traditional logistic regression models. This scoping review suggests that ANN can predict the prognosis of musculoskeletal diseases, which has the potential to be applied to different types of MSD.

Predicting decompression surgery by applying multimodal deep learning to patients' structured and unstructured health data

BACKGROUND

Low back pain (LBP) is a common condition made up of a variety of anatomic and clinical subtypes. Lumbar disc herniation (LDH) and lumbar spinal stenosis (LSS) are two subtypes highly associated with LBP. Patients with LDH/LSS are often started with non-surgical treatments and if those are not effective then go on to have decompression surgery. However, recommendation of surgery is complicated as the outcome may depend on the patient's health characteristics. We developed a deep learning (DL) model to predict decompression surgery for patients with LDH/LSS.

MATERIALS AND METHOD

We used datasets of 8387 and 8620 patients from a prospective study that collected data from four healthcare systems to predict early (within 2 months) and late surgery (within 12 months after a 2 month gap), respectively. We developed a DL model to use patients' demographics, diagnosis and procedure codes, drug names, and diagnostic imaging reports to predict surgery. For each prediction task, we evaluated the model's performance using classical and generalizability evaluation. For classical evaluation, we split the data into training (80%) and testing (20%). For generalizability evaluation, we split the data based on the healthcare system. We used the area under the curve (AUC) to assess performance for each evaluation. We compared results to a benchmark model (i.e. LASSO logistic regression).

RESULTS

For classical performance, the DL model outperformed the benchmark model for early surgery with an AUC of 0.725 compared to 0.597. For late surgery, the DL model outperformed the benchmark model with an AUC of 0.655 compared to 0.635. For generalizability performance, the DL model outperformed the benchmark model for early surgery. For late surgery, the benchmark model outperformed the DL model.

CONCLUSIONS

For early surgery, the DL model was preferred for classical and generalizability evaluation. However, for late surgery, the benchmark and DL model had comparable performance. Depending on the prediction task, the balance of performance may shift between DL and a conventional ML method. As a result, thorough assessment is needed to quantify the value of DL, a relatively computationally expensive, time-consuming and less interpretable method.

Machine learning-based mortality prediction models using national liver transplantation registries are feasible but have limited utility across countries

Many countries curate national registries of liver transplant (LT) data. These registries are often used to generate predictive models; however, potential performance and transferability of these models remain unclear. We used data from 3 national registries and developed machine learning algorithm (MLA)-based models to predict 90-day post-LT mortality within and across countries. Predictive performance and external validity of each model were assessed. Prospectively collected data of adult patients (aged ≥18 years) who underwent primary LTs between January 2008 and December 2018 from the Canadian Organ Replacement Registry (Canada), National Health Service Blood and Transplantation (United Kingdom), and United Network for Organ Sharing (United States) were used to develop MLA models to predict 90-day post-LT mortality. Models were developed using each registry individually (based on variables inherent to the individual databases) and using all 3 registries combined (variables in common between the registries [harmonized]). The model performance was evaluated using area under the receiver operating characteristic (AUROC) curve. The number of patients included was as follows: Canada, n = 1214; the United Kingdom, n = 5287; and the United States, n = 59,558. The best performing MLA-based model was ridge regression across both individual registries and harmonized data sets. Model performance diminished from individualized to the harmonized registries, especially in Canada (individualized ridge: AUROC, 0.74; range, 0.73-0.74; harmonized: AUROC, 0.68; range, 0.50-0.73) and US (individualized ridge: AUROC, 0.71; range, 0.70-0.71; harmonized: AUROC, 0.66; range, 0.66-0.66) data sets. External model performance across countries was poor overall. MLA-based models yield a fair discriminatory potential when used within individual databases. However, the external validity of these models is poor when applied across countries. Standardization of registry-based variables could facilitate the added value of MLA-based models in informing decision making in future LTs.

Causal deep learning reveals the comparative effectiveness of antihyperglycemic treatments in poorly controlled diabetes

Type-2 diabetes is associated with severe health outcomes, the effects of which are responsible for approximately 1/4^th of the total healthcare spending in the United States (US). Current treatment guidelines endorse a massive number of potential anti-hyperglycemic treatment options in various combinations. Strategies for optimizing treatment selection are lacking. Real-world data from a nationwide population of over one million high-risk diabetic patients (HbA1c ≥ 9%) in the US is analyzed to evaluate the comparative effectiveness for HbA1c reduction in this population of more than 80 different treatment strategies ranging from monotherapy up to combinations of five concomitant classes of drugs across each of 10 clinical cohorts defined by age, insulin dependence, and a number of other chronic conditions. A causal deep learning approach developed on such data allows for more personalized evaluation of treatment selection. An average confounder-adjusted reduction in HbA1c of 0.69% [-0.75, -0.65] is observed between patients receiving high vs low ranked treatments across cohorts for which the difference was significant. This method can be extended to explore treatment optimization for other chronic conditions.

Narrative Review of Machine Learning in Rheumatic and Musculoskeletal Diseases for Clinicians and Researchers: Biases, Goals, and Future Directions

There has been rapid growth in the use of artificial intelligence (AI) analytics in medicine in recent years, including in rheumatic and musculoskeletal diseases (RMDs). Such methods represent a challenge to clinicians, patients, and researchers, given the "black box" nature of most algorithms, the unfamiliarity of the terms, and the lack of awareness of potential issues around these analyses. Therefore, this review aims to introduce this subject area in a way that is relevant and meaningful to clinicians and researchers. We hope to provide some insights into relevant strengths and limitations, reporting guidelines, as well as recent examples of such analyses in key areas, with a focus on lessons learned and future directions in diagnosis, phenotyping, prognosis, and precision medicine in RMDs.

Analysis of Characteristic Factors of Nursing Safety Incidents in ENT Surgery by Deep Learning-Based Medical Data Association Rules Method

It is of great significance to explore the characteristic factors of postoperative nursing safety events in patients with otolaryngology surgery and to understand the characteristics of postoperative nursing safety events in otolaryngology surgery patients. This paper carried out preoperative safety protection for 385 inpatients, and the results showed that there were 52 cases of postoperative safety nursing events. This experiment found that the coinfected lesions (P = 0.001, HR = 14.283, 95.0% C1: 9.365~21.038), the treatment period (P = 0.001, HR = 13.716, 95.0% CI: 7.147~20.275), during hospital treatment (P = 0.002, HR = 15.208, 95.0% CI: 8.918-24.237), antibiotic use (P = 0.001, HR = 14.054, 95.0% CI: 8.163-21.739), and hypertension (P = 0.001, HR = 13.976, 95.0% CI: 7.926-22.385) are the important factors affecting postoperative care; using the association rule method to control and analyze the main risk factors of postoperative infection and bleeding in ENT patients can significantly improve the prognosis.

Exploration of machine learning methods to predict systemic lupus erythematosus hospitalizations

OBJECTIVES

Systemic lupus erythematosus (SLE) is a heterogeneous disease characterized by disease flares which can require hospitalization. Our objective was to apply machine learning methods to predict hospitalizations for SLE from electronic health record (EHR) data.

METHODS

We identified patients with SLE in a longitudinal EHR-based cohort with ≥2 outpatient rheumatology visits between 2012 and 2019. We applied multiple machine learning methods to predict hospitalizations with a primary diagnosis code for SLE, including decision tree, random forest, naive Bayes, logistic regression, and an ensemble method. Candidate predictors were derived from structured EHR features, including demographics, laboratory tests, medications, ICD-9/10 codes for SLE manifestations, and healthcare utilization. We used two approaches to assess these variables over longitudinal follow-up, including the incorporation of lagged features to capture changes over time of clinical data. The performance of each model was evaluated by overall accuracy, the F statistic, and the area under the receiver operator curve (AUC).

RESULTS

We identified 1996 patients with SLE. 4.6% were hospitalized for SLE in their most recent year of follow-up. Random forest models had highest performance in predicting SLE hospitalizations, with AUC 0.751 and AUC 0.772 for two approaches (averaging and progressive), respectively. The leading predictors of SLE hospitalizations included dsDNA positivity, C3 level, blood cell counts, and inflammatory markers as well as age and albumin.

CONCLUSION

We have demonstrated that machine learning methods can predict SLE hospitalizations. We identified key predictors of these events including known markers of SLE disease activity; further validation in external cohorts is warranted.

A Case Study of Multiple Maintenance Efficacy in Gynaecological Surgery Assessed by Deep Learning

Deep learning is a new learning concept and a highly effective way of learning, which is still being explored in the field of nursing education. This paper analyses the effectiveness of interventions in perioperative gynaecological care using humanised care in the operating theatre and the impact of this model of care on patients’ psychological well-being and sleep quality. A deep learning-based vision robot was designed to provide higher quality of care for our human care and simplify our approach to gynaecological surgery. The anxiety and depression scores of the two groups were significantly improved after and before care, and the scores of the observation group were lower than those of the control group, with a statistically significant difference ( $P<0.05$ ). The humanised care for gynaecological surgery patients in the perioperative period is more conducive to the improvement of their negative emotions and at the same time can improve the sleep quality of patients, so it can be further promoted.

Artificial intelligence and spine imaging: limitations, regulatory issues and future direction

BACKGROUND

As big data and artificial intelligence (AI) in spine care, and medicine as a whole, continue to be at the forefront of research, careful consideration to the quality and techniques utilized is necessary. Predictive modeling, data science, and deep analytics have taken center stage. Within that space, AI and machine learning (ML) approaches toward the use of spine imaging have gathered considerable attention in the past decade. Although several benefits of such applications exist, limitations are also present and need to be considered.

PURPOSE

The following narrative review presents the current status of AI, in particular, ML, with special regard to imaging studies, in the field of spinal research.

METHODS

A multi-database assessment of the literature was conducted up to September 1, 2021, that addressed AI as it related to imaging of the spine. Articles written in English were selected and critically assessed.

RESULTS

Overall, the review discussed the limitations, data quality and applications of ML models in the context of spine imaging. In particular, we addressed the data quality and ML algorithms in spine imaging research by describing preliminary results from a widely accessible imaging algorithm that is currently available for spine specialists to reference for information on severity of spine disease and degeneration which ultimately may alter clinical decision-making. In addition, awareness of the current, under-recognized regulation surrounding the execution of ML for spine imaging was raised.

CONCLUSIONS

Recommendations were provided for conducting high-quality, standardized AI applications for spine imaging.

Machine learning predicts response to TNF inhibitors in rheumatoid arthritis: results on the ESPOIR and ABIRISK cohorts

Objectives

Around 30% of patients with rheumatoid arthritis (RA) do not respond to tumour necrosis factor inhibitors (TNFi). We aimed to predict patient response to TNFi using machine learning on simple clinical and biological data.

Methods

We used data from the RA ESPOIR cohort to train our models. The endpoints were the EULAR response and the change in Disease Activity Score (DAS28). We compared the performances of multiple models (linear regression, random forest, XGBoost and CatBoost) on the training set and cross-validated them using the area under the receiver operating characteristic curve (AUROC) or the mean squared error. The best model was then evaluated on a replication cohort (ABIRISK).

Results

We included 161 patients from ESPOIR and 118 patients from ABIRISK. The key selected features were DAS28, lymphocytes, ALT (aspartate aminotransferase), neutrophils, age, weight, and smoking status. When predicting EULAR response, CatBoost achieved the best performances of the four tested models. It reached an AUROC of 0.72 (0.68–0.73) on the train set (ESPOIR). Better results were obtained on the train set when etanercept and monoclonal antibodies were analysed separately. On the test set (ABIRISK), these models respectively achieved on AUROC of 0.70 (0.57–0.82) and 0.71 (0.55–0.86). Two decision thresholds were tested. The first prioritised a high confidence in identifying responders and yielded a confidence up to 90% for predicting response. The second prioritised a high confidence in identifying inadequate responders and yielded a confidence up to 70% for predicting non-response. The change in DAS28 was predicted with an average error of 1.1 DAS28 points.

Conclusion

The machine learning models developed allowed predicting patient response to TNFi exclusively using data available in clinical routine.

Artificial Intelligence in Rheumatoid Arthritis: Current Status and Future Perspectives: A State-of-the-Art Review

Investigation of the potential applications of artificial intelligence (AI), including machine learning (ML) and deep learning (DL) techniques, is an exponentially growing field in medicine and healthcare. These methods can be critical in providing high-quality care to patients with chronic rheumatological diseases lacking an optimal treatment, like rheumatoid arthritis (RA), which is the second most prevalent autoimmune disease. Herein, following reviewing the basic concepts of AI, we summarize the advances in its applications in RA clinical practice and research. We provide directions for future investigations in this field after reviewing the current knowledge gaps and technical and ethical challenges in applying AI. Automated models have been largely used to improve RA diagnosis since the early 2000s, and they have used a wide variety of techniques, e.g., support vector machine, random forest, and artificial neural networks. AI algorithms can facilitate screening and identification of susceptible groups, diagnosis using omics, imaging, clinical, and sensor data, patient detection within electronic health record (EHR), i.e., phenotyping, treatment response assessment, monitoring disease course, determining prognosis, novel drug discovery, and enhancing basic science research. They can also aid in risk assessment for incidence of comorbidities, e.g., cardiovascular diseases, in patients with RA. However, the proposed models may vary significantly in their performance and reliability. Despite the promising results achieved by AI models in enhancing early diagnosis and management of patients with RA, they are not fully ready to be incorporated into clinical practice. Future investigations are required to ensure development of reliable and generalizable algorithms while they carefully look for any potential source of bias or misconduct. We showed that a growing body of evidence supports the potential role of AI in revolutionizing screening, diagnosis, and management of patients with RA. However, multiple obstacles hinder clinical applications of AI models. Incorporating the machine and/or deep learning algorithms into real-world settings would be a key step in the progress of AI in medicine.

Big data analyses and individual health profiling in the arena of rheumatic and musculoskeletal diseases (RMDs)

Health care processes are under constant development and will need to embrace advances in technology and health science aiming to provide optimal care. Considering the perspective of increasing treatment options for people with rheumatic and musculoskeletal diseases, but in many cases not reaching all treatment targets that matter to patients, care systems bare potential to improve on a holistic level. This review provides an overview of systems and technologies under evaluation over the past years that show potential to impact diagnosis and treatment of rheumatic diseases in about 10 years from now. We summarize initiatives and studies from the field of electronic health records, biobanking, remote monitoring, and artificial intelligence. The combination and implementation of these opportunities in daily clinical care will be key for a new era in care of our patients. This aims to inform rheumatologists and healthcare providers concerned with chronic inflammatory musculoskeletal conditions about current important and promising developments in science that might substantially impact the management processes of rheumatic diseases in the 2030s.

Clinical predictors of response to methotrexate in patients with rheumatoid arthritis: a machine learning approach using clinical trial data

BACKGROUND

Methotrexate is the preferred initial disease-modifying antirheumatic drug (DMARD) for rheumatoid arthritis (RA). However, clinically useful tools for individualized prediction of response to methotrexate treatment in patients with RA are lacking. We aimed to identify clinical predictors of response to methotrexate in patients with rheumatoid arthritis (RA) using machine learning methods.

METHODS

Randomized clinical trials (RCT) of patients with RA who were DMARD-naïve and randomized to placebo plus methotrexate were identified and accessed through the Clinical Study Data Request Consortium and Vivli Center for Global Clinical Research Data. Studies with available Disease Activity Score with 28-joint count and erythrocyte sedimentation rate (DAS28-ESR) at baseline and 12 and 24 weeks were included. Latent class modeling of methotrexate response was performed. The least absolute shrinkage and selection operator (LASSO) and random forests methods were used to identify predictors of response.

RESULTS

A total of 775 patients from 4 RCTs were included (mean age 50 years, 80% female). Two distinct classes of patients were identified based on DAS28-ESR change over 24 weeks: "good responders" and "poor responders." Baseline DAS28-ESR, anti-citrullinated protein antibody (ACPA), and Health Assessment Questionnaire (HAQ) score were the top predictors of good response using LASSO (area under the curve [AUC] 0.79) and random forests (AUC 0.68) in the external validation set. DAS28-ESR ≤ 7.4, ACPA positive, and HAQ ≤ 2 provided the highest likelihood of response. Among patients with 12-week DAS28-ESR > 3.2, ≥ 1 point improvement in DAS28-ESR baseline-to-12-week was predictive of achieving DAS28-ESR ≤ 3.2 at 24 weeks.

CONCLUSIONS

We have developed and externally validated a prediction model for response to methotrexate within 24 weeks in DMARD-naïve patients with RA, providing variably weighted clinical features and defined cutoffs for clinical decision-making.

Improved diagnosis of rheumatoid arthritis using an artificial neural network

Rheumatoid arthritis (RA) is chronic systemic disease that can cause joint damage, disability and destructive polyarthritis. Current diagnosis of RA is based on a combination of clinical and laboratory features. However, RA diagnosis can be difficult at its disease onset on account of overlapping symptoms with other arthritis, so early recognition and diagnosis of RA permit the better management of patients. In order to improve the medical diagnosis of RA and evaluate the effects of different clinical features on RA diagnosis, we applied an artificial neural network (ANN) as the training algorithm, and used fivefold cross-validation to evaluate its performance. From each sample, we obtained data on 6 features: age, sex, rheumatoid factor, anti-citrullinated peptide antibody (CCP), 14-3-3η, and anti-carbamylated protein (CarP) antibodies. After training, this ANN model assigned each sample a probability for being either an RA patient or a non-RA patient. On the validation dataset, the F1 for all samples by this ANN model was 0.916, which was higher than the 0.906 we previously reported using an optimal threshold algorithm. Therefore, this ANN algorithm not only improved the accuracy of RA diagnosis, but also revealed that anti-CCP had the greatest effect while age and anti-CarP had a weaker on RA diagnosis.

An Interoperable Electronic Health Record System for Clinical Cardiology

Currently in hospitals, there are several separate information systems that manage, very often autonomously, the patient’s personal, clinical and diagnostic data. An electronic health record system has been specifically developed for a cardiology ward and it has been designed “ab initio” to be fully integrated into the hospital information system and to exchange data with the regional health information infrastructure. All documents have been given as Health Level 7 (HL7) clinical document architecture and messages are sent as HL7-Version 2 (V2) and/or HL7 Fast Healthcare Interoperability Resources (FHIR). Specific decision support sections for specific aspects have also been included. The system has been used for more than three years with a good level of satisfaction by the users. In the future, the system can be the basis for secondary use for clinical studies, further decision support systems and clinical trials.

Deep Learning-Based Computer-Aided Diagnosis of Rheumatoid Arthritis with Hand X-ray Images Conforming to Modified Total Sharp/van der Heijde Score

Introduction: Rheumatoid arthritis (RA) is a systemic autoimmune disease; early diagnosis and treatment are crucial for its management. Currently, the modified total Sharp score (mTSS) is widely used as a scoring system for RA. The standard screening process for assessing mTSS is tedious and time-consuming. Therefore, developing an efficient mTSS automatic localization and classification system is of urgent need for RA diagnosis. Current research mostly focuses on the classification of finger joints. Due to the insufficient detection ability of the carpal part, these methods cannot cover all the diagnostic needs of mTSS. Method: We propose not only an automatic label system leveraging the You Only Look Once (YOLO) model to detect the regions of joints of the two hands in hand X-ray images for preprocessing of joint space narrowing in mTSS, but also a joint classification model depending on the severity of the mTSS-based disease. In the image processing of the data, the window level is used to simulate the processing method of the clinician, the training data of the different carpal and finger bones of human vision are separated and integrated, and the resolution is increased or decreased to observe the changes in the accuracy of the model. Results: Integrated data proved to be beneficial. The mean average precision of the proposed model in joint detection of joint space narrowing reached 0.92, and the precision, recall, and F1 score all reached 0.94 to 0.95. For the joint classification, the average accuracy was 0.88, and the accuracy of severe, mild, and healthy reached 0.91, 0.79, and 0.9, respectively. Conclusions: The proposed model is feasible and efficient. It could be helpful for subsequent research on computer-aided diagnosis in RA. We suggest that applying the one-hand X-ray imaging protocol can improve the accuracy of mTSS classification model in determining mild disease if it is used in clinical practice.

Responding to and Driving Change in Rheumatology: Report from the 12th International Immunology Summit 2021

The coronavirus disease 2019 (COVID-19) pandemic has accelerated changes to rheumatology daily clinical practice. The main goal of the 12th International Immunology Summit, held 25-26 June, 2021 (virtual meeting), was to provide direction for these active changes rather than undergoing change reactively in order to improve patient outcomes. This review describes and explores the concept of change in rheumatology clinical practice based on presentations from the Immunology Summit. Many of the changes to rheumatology practice brought about by the COVID-19 pandemic may be considered as having a positive impact on disease management and may help with the long-term development of more patient-focused treatment. Rheumatologists can contribute key knowledge regarding the use of immunosuppressive agents in the context of the pandemic, and according to the European League Against Rheumatism, they should be involved in any multidisciplinary COVID-19 guideline committees. New technologies, including telemedicine and artificial intelligence, represent an opportunity for physicians to individualise patient treatment and improve disease management. Despite major advances in the treatment of rheumatic diseases, the efficacy of available disease-modifying anti-rheumatic drugs (DMARDs) remains suboptimal and data regarding serological biomarkers are limited. Synovial tissue biomarkers, such as CD68+ macrophages, have shown promise in elucidating pathogenesis and targeting treatment to the individual patient. In spondyloarthritis (SpA) or psoriatic arthritis (PsA), information regarding the effectiveness of the available agents with different mechanisms of action may be integrated to manage patients using a treat-to-target approach. Early diagnosis of SpA and PsA is important for optimisation of treatment response and long-term outcomes. Improving our understanding of disease pathogenesis and practice methods may help reduce diagnostic delays, thereby optimising disease outcomes in patients with rheumatic diseases.

Using real-world data to dynamically predict flares during tapering of biological DMARDs in rheumatoid arthritis: development, validation, and potential impact of prediction-aided decisions

Background

Biological disease-modifying antirheumatic drugs (bDMARDs) are effective in the treatment of rheumatoid arthritis. However, as bDMARDs may also lead to adverse events and are expensive, tapering them is of great clinical interest. Tapering according to disease activity-guided dose optimization (DGDO) does not seem to affect long term remission rates, but flares are frequent during this process. Our objective was to develop a model for the prediction of flares during bDMARD tapering using data from routine care and to evaluate its potential clinical impact.

Methods

We used a joint latent class model to repeatedly predict the probability of a flare occurring within the next 3 months. The model was developed using longitudinal data on disease activity (DAS28) and other routine care data from two clinics. Predictive accuracy was assessed in cross-validation and external validation was performed with data from the DRESS (Dose REduction Strategy of Subcutaneous tumor necrosis factor inhibitors) trial. Additionally, we simulated the reduction in number of flares and bDMARD dose when implementing the model as a decision aid during bDMARD tapering in the DRESS trial.

Results

Data from 279 bDMARD courses were used for model development. The final model included two latent DAS28-trajectories, bDMARD type and dose, disease duration, and seropositivity. The area under the curve of the final model was 0.76 (0.69–0.83) in cross-validation and 0.68 (0.62–0.73) in external validation. In simulation of prediction-aided decisions, the mean number of flares over 18 months decreased from 1.21 (0.99–1.43) to 0.75 (0.54–0.96). The reduction in he bDMARD dose was mostly maintained, increasing from 54 to 64% of full dose.

Conclusions

We developed a dynamic flare prediction model, exclusively based on data typically available in routine care. Our results show that using this model to aid decisions during bDMARD tapering may significantly reduce the number of flares while maintaining most of the bDMARD dose reduction.

Trial registration

The clinical impact of the prediction model is currently under investigation in the PATIO randomized controlled trial (Dutch Trial Register number NL9798).

Supplementary Information

The online version contains supplementary material available at 10.1186/s13075-022-02751-8.

A novel kernel based approach to arbitrary length symbolic data with application to type 2 diabetes risk

Predictive modeling of clinical data is fraught with challenges arising from the manner in which events are recorded. Patients typically fall ill at irregular intervals and experience dissimilar intervention trajectories. This results in irregularly sampled and uneven length data which poses a problem for standard multivariate tools. The alternative of feature extraction into equal-length vectors via methods like Bag-of-Words (BoW) potentially discards useful information. We propose an approach based on a kernel framework in which data is maintained in its native form: discrete sequences of symbols. Kernel functions derived from the edit distance between pairs of sequences may then be utilized in conjunction with support vector machines to classify the data. Our method is evaluated in the context of the prediction task of determining patients likely to develop type 2 diabetes following an earlier episode of elevated blood pressure of 130/80 mmHg. Kernels combined via multi kernel learning achieved an F1-score of 0.96, outperforming classification with SVM 0.63, logistic regression 0.63, Long Short Term Memory 0.61 and Multi-Layer Perceptron 0.54 applied to a BoW representation of the data. We achieved an F1-score of 0.97 on MKL on external dataset. The proposed approach is consequently able to overcome limitations associated with feature-based classification in the context of clinical data.

Use of machine learning in osteoarthritis research: a systematic literature review

Objective

The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA).

Methods

A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected.

Results

From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles.

Conclusion

This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.

Deep Learning-Based Classification of Inflammatory Arthritis by Identification of Joint Shape Patterns—How Neural Networks Can Tell Us Where to “Deep Dive” Clinically

Objective:

We investigated whether a neural network based on the shape of joints can differentiate between rheumatoid arthritis (RA), psoriatic arthritis (PsA), and healthy controls (HC), which class patients with undifferentiated arthritis (UA) are assigned to, and whether this neural network is able to identify disease-specific regions in joints.

Methods

We trained a novel neural network on 3D articular bone shapes of hand joints of RA and PsA patients as well as HC. Bone shapes were created from high-resolution peripheral-computed-tomography (HR-pQCT) data of the second metacarpal bone head. Heat maps of critical spots were generated using GradCAM. After training, we fed shape patterns of UA into the neural network to classify them into RA, PsA, or HC.

Results

Hand bone shapes from 932 HR-pQCT scans of 617 patients were available. The network could differentiate the classes with an area-under-receiver-operator-curve of 82% for HC, 75% for RA, and 68% for PsA. Heat maps identified anatomical regions such as bare area or ligament attachments prone to erosions and bony spurs. When feeding UA data into the neural network, 86% were classified as “RA,” 11% as “PsA,” and 3% as “HC” based on the joint shape.

Conclusion

We investigated neural networks to differentiate the shape of joints of RA, PsA, and HC and extracted disease-specific characteristics as heat maps on 3D joint shapes that can be utilized in clinical routine examination using ultrasound. Finally, unspecific diseases such as UA could be grouped using the trained network based on joint shape.

Building a Precision Medicine Delivery Platform for Clinics: The University of California, San Francisco, BRIDGE Experience

Despite an ever-expanding number of analytics with the potential to impact clinical care, the field currently lacks point-of-care technological tools that allow clinicians to efficiently select disease-relevant data about their patients, algorithmically derive clinical indices (eg, risk scores), and view these data in straightforward graphical formats to inform real-time clinical decisions. Thus far, solutions to this problem have relied on either bottom-up approaches that are limited to a single clinic or generic top-down approaches that do not address clinical users’ specific setting-relevant or disease-relevant needs. As a road map for developing similar platforms, we describe our experience with building a custom but institution-wide platform that enables economies of time, cost, and expertise. The BRIDGE platform was designed to be modular and scalable and was customized to data types relevant to given clinical contexts within a major university medical center. The development process occurred by using a series of human-centered design phases with extensive, consistent stakeholder input. This institution-wide approach yielded a unified, carefully regulated, cross-specialty clinical research platform that can be launched during a patient’s electronic health record encounter. The platform pulls clinical data from the electronic health record (Epic; Epic Systems) as well as other clinical and research sources in real time; analyzes the combined data to derive clinical indices; and displays them in simple, clinician-designed visual formats specific to each disorder and clinic. By integrating an application into the clinical workflow and allowing clinicians to access data sources that would otherwise be cumbersome to assemble, view, and manipulate, institution-wide platforms represent an alternative approach to achieving the vision of true personalized medicine.

A broad look into the future of rheumatoid arthritis

Despite all improvements in rheumatoid arthritis, we are still not able to prevent or cure the disease. Diagnostic delays due to lack of access to a specialist and costly therapies are still a major obstacle for many patients. Even in first-world countries, the treat-to-target principle and the goal of disease remission are often missed. Thus, rheumatoid arthritis (RA) is still the reason for disability and reduced quality of life for many patients. So, is it time to move the goalpost even further? Where are we heading next? And will we finally be able to cure the disease? These questions are addressed in our review article.

An artificial intelligence framework integrating longitudinal electronic health records with real-world data enables continuous pan-cancer prognostication

Despite widespread adoption of electronic health records (EHRs), most hospitals are not ready to implement data science research in the clinical pipelines. Here, we develop MEDomics, a continuously learning infrastructure through which multimodal health data are systematically organized and data quality is assessed with the goal of applying artificial intelligence for individual prognosis. Using this framework, currently composed of thousands of individuals with cancer and millions of data points over a decade of data recording, we demonstrate prognostic utility of this framework in oncology. As proof of concept, we report an analysis using this infrastructure, which identified the Framingham risk score to be robustly associated with mortality among individuals with early-stage and advanced-stage cancer, a potentially actionable finding from a real-world cohort of individuals with cancer. Finally, we show how natural language processing (NLP) of medical notes could be used to continuously update estimates of prognosis as a given individual's disease course unfolds.