Comorbidity clusters in patients with rheumatoid arthritis identify a patient phenotype with a favourable prognosis.

OBJECTIVES: We aimed to cluster patients with rheumatoid arthritis (RA) based on comorbidities and then examine the association between these clusters and RA disease activity and mortality. METHODS: In this population-based study, residents of an eight-county region with prevalent RA on 1 January 2015 were identified. Patients were followed for vital status until death, last contact or 31 December 2021. Diagnostic codes for 5 years before the prevalence date were used to define 55 comorbidities. Latent class analysis was used to cluster patients based on comorbidity patterns. Standardised mortality ratios were used to assess mortality. RESULTS: A total of 1643 patients with prevalent RA (72% female; 94% white; median age 64 years, median RA duration 7 years) were studied. Four clusters were identified. Cluster 1 (n=686) included patients with few comorbidities, and cluster 4 (n=134) included older patients with 10 or more comorbidities. Cluster 2 (n=200) included patients with five or more comorbidities and high prevalences of depression and obesity, while cluster 3 (n=623) included the remainder. RA disease activity and survival differed across the clusters, with cluster 1 demonstrating more remission and mortality comparable to the general population. CONCLUSIONS: More than 40% of patients with prevalent RA did not experience worse mortality than their peers without RA. The cluster with the worst prognosis (<10% of patients with prevalent RA) was older, had more comorbidities and had less disease-modifying antirheumatic drug and biological use compared with the other clusters. Comorbidity patterns may hold the key to moving beyond a one-size-fits-all perspective of RA prognosis.

Biomarkers of cellular senescence in idiopathic pulmonary fibrosis.

BACKGROUND: Cellular senescence is a cell fate in response to diverse forms of age-related damage and stress that has been implicated in the pathogenesis of idiopathic pulmonary fibrosis (IPF). The associations between circulating levels of candidate senescence biomarkers and disease outcomes have not been specifically studied in IPF. In this study we assessed the circulating levels of candidate senescence biomarkers in individuals affected by IPF and controls and evaluated their ability to predict disease outcomes. METHODS: We measured the plasma concentrations of 32 proteins associated with senescence in Lung Tissue Research Consortium participants and studied their relationship with the diagnosis of IPF, parameters of pulmonary and physical function, health-related quality of life, mortality, and lung tissue expression of P16, a prototypical marker of cellular senescence. A machine learning approach was used to evaluate the ability of combinatorial biomarker signatures to predict disease outcomes. RESULTS: The circulating levels of several senescence biomarkers were significantly elevated in persons affected by IPF compared to controls. A subset of biomarkers accurately classified participants as having or not having the disease and was significantly correlated with measures of pulmonary function, health-related quality of life and, to an extent, physical function. An exploratory analysis revealed senescence biomarkers were also associated with mortality in IPF participants. Finally, the plasma concentrations of several biomarkers were associated with their expression levels in lung tissue as well as the expression of P16. CONCLUSIONS: Our results suggest that circulating levels of candidate senescence biomarkers are informative of disease status, pulmonary and physical function, and health-related quality of life. Additional studies are needed to validate the combinatorial biomarkers signatures that emerged using a machine learning approach.

Predicting cholangiocarcinoma in primary sclerosing cholangitis: using artificial intelligence, clinical and laboratory data.

BACKGROUND: Primary sclerosing cholangitis (PSC) patients have a risk of developing cholangiocarcinoma (CCA). Establishing predictive models for CCA in PSC is important. METHODS: In a large cohort of 1,459 PSC patients seen at Mayo Clinic (1993-2020), we quantified the impact of clinical/laboratory variables on CCA development using univariate and multivariate Cox models and predicted CCA using statistical and artificial intelligence (AI) approaches. We explored plasma bile acid (BA) levels' predictive power of CCA (subset of 300 patients, BA cohort). RESULTS: Eight significant risk factors (false discovery rate: 20%) were identified with univariate analysis; prolonged inflammatory bowel disease (IBD) was the most important one. IBD duration, PSC duration, and total bilirubin remained significant (p < 0.05) with multivariate analysis. Clinical/laboratory variables predicted CCA with cross-validated C-indexes of 0.68-0.71 at different time points of disease, significantly better compared to commonly used PSC risk scores. Lower chenodeoxycholic acid, higher conjugated fraction of lithocholic acid and hyodeoxycholic acid, and higher ratio of cholic acid to chenodeoxycholic acid were predictive of CCA. BAs predicted CCA with a cross-validated C-index of 0.66 (std: 0.11, BA cohort), similar to clinical/laboratory variables (C-index = 0.64, std: 0.11, BA cohort). Combining BAs with clinical/laboratory variables leads to the best average C-index of 0.67 (std: 0.13, BA cohort). CONCLUSIONS: In a large PSC cohort, we identified clinical and laboratory risk factors for CCA development and demonstrated the first AI based predictive models that performed significantly better than commonly used PSC risk scores. More predictive data modalities are needed for clinical adoption of these models.

Smoking, early menopause and multiple sclerosis disease course.

Smoking is associated with an increased risk of multiple sclerosis (MS), and smoking and early menopause are related to poor outcomes in MS. Smoking is also associated with early menopause. To explore this intricate relationship between smoking status, age at menopause and disease course in MS, 137 women with MS and 396 age-matched controls were included in this case-control study. Age at menopause (median 49.0 vs. 50.0 years; p = 0.79) and smoking status (40.3% vs. 47.6%; p = 0.15) were similar among MS and control women. Relapsing MS onset was earlier in ever-smoker women with early menopause compared to the rest of the women (median 30.4 vs. 37.0 years; p = 0.02) and also compared to ever-smoker women with normal age at menopause (median 30.4 vs. 41.0 years; p = 0.008) and never-smoker women with early menopause (median 30.4 vs. 41.5 years; p = 0.004). Progressive MS onset was also earlier in ever-smoker women with early menopause compared to ever-smoker women with normal age at menopause (median 41.1 vs. 49.4 years; p = 0.05) and never-smoker women with early menopause (median 41.1 vs. 50.1 years; p = 0.12). Our results suggest that smoking and menopause associate with MS disease course, including the onset of relapsing and progressive MS in women.

Pregnancy-associated plasma protein-A (PAPP-A) is a key component of an interactive cellular mechanism promoting pulmonary fibrosis.

Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease with few effective treatment options. We found a highly significant correlation between pregnancy-associated plasma protein (PAPP)-A expression in IPF lung tissue and disease severity as measured by various pulmonary and physical function tests. PAPP-A is a metalloproteinase that enhances local insulin-like growth factor (IGF) activity. We used primary cultures of normal adult human lung fibroblasts (NHLF) to test the hypothesis that PAPP-A plays an important role in the development of pulmonary fibrosis. Treatment of NHLF with pro-fibrotic transforming growth factor (TGF)-ß stimulated marked increases in IGF-I mRNA expression (>20-fold) and measurable IGF-I levels in 72-h conditioned medium (CM). TGF-ß treatment also increased PAPP-A levels in CM fourfold (p = 0.004) and proteolytic activity ~2-fold. There was an indirect effect of TGF-ß to stimulate signaling through the PI3K/Akt pathway, which was significantly inhibited by both IGF-I-inactivating and PAPP-A inhibitory antibodies. Induction of senescence in NHLF increased PAPP-A levels in CM 10-fold (p = 0.006) with attendant increased proteolytic activity. Thus, PAPP-A is a novel component of the senescent lung fibroblast secretome. In addition, NHLF secreted extracellular vehicles (EVs) with surface-bound active PAPP-A that were increased fivefold with senescence. Regulation of PAPP-A and IGF signaling by TGF-ß and cell senescence suggests an interactive cellular mechanism underlying the resistance to apoptosis and the progression of fibrosis in IPF. Furthermore, PAPP-A-associated EVs may be a means of pro-fibrotic, pro-senescent communication with other cells in the lung and, thus, a potential therapeutic target for IPF.

Bile Acid Profiles in Primary Sclerosing Cholangitis and Their Ability to Predict Hepatic Decompensation.

BACKGROUND AND AIMS: Altered bile acid (BA) homeostasis is an intrinsic facet of cholestatic liver diseases, but clinical usefulness of plasma BA assessment in primary sclerosing cholangitis (PSC) remains understudied. We performed BA profiling in a large retrospective cohort of patients with PSC and matched healthy controls, hypothesizing that plasma BA profiles vary among patients and have clinical utility. APPROACH AND RESULTS: Plasma BA profiling was performed in the Clinical Biochemical Genetics Laboratory at Mayo Clinic using a mass spectrometry based assay. Cox proportional hazard (univariate) and gradient boosting machines (multivariable) models were used to evaluate whether BA variables predict 5-year risk of hepatic decompensation (HD; defined as ascites, variceal hemorrhage, or encephalopathy). There were 400 patients with PSC and 302 controls in the derivation cohort (Mayo Clinic) and 108 patients with PSC in the validation cohort (Norwegian PSC Research Center). Patients with PSC had increased BA levels, conjugated fraction, and primary-to-secondary BA ratios relative to controls. Ursodeoxycholic acid (UDCA) increased total plasma BA level while lowering cholic acid and chenodeoxycholic acid concentrations. Patients without inflammatory bowel disease (IBD) had primary-to-secondary BA ratios between those of controls and patients with ulcerative colitis. HD risk was associated with increased concentration and conjugated fraction of many BA, whereas higher G:T conjugation ratios were protective. The machine-learning model, PSC-BA profile score (concordance statistic [C-statistic], 0.95), predicted HD better than individual measures, including alkaline phosphatase, and performed well in validation (C-statistic, 0.86). CONCLUSIONS: Patients with PSC demonstrated alterations of plasma BA consistent with known mechanisms of cholestasis, UDCA treatment, and IBD. Notably, BA profiles predicted future HD, establishing the clinical potential of BA profiling, which may be suited for use in clinical trials.

Distal radius fractures and risk of incident neurocognitive disorders in older adults: a retrospective cohort study.

INTRODUCTION: Distal radius fractures (DRF) are associated with increased risk of subsequent fractures and physical decline in older adults. This study aims to evaluate the risk cognitive decline following DRF and potential for timely screening and intervention. METHODS: A cohort of 1046 individuals 50-75 years of age with DRF were identified between 1995 and 2015 (81.5% female; mean age 62.5 [± 7.1] years). A control group (N = 1044) without history of DRF was matched by age, sex, and fracture date (i.e., index). The incidence of neurocognitive disorders (NCD) in relation to DRF/index was determined. Group comparisons were adjusted by age and comorbidity measured by the Elixhauser index. RESULTS: The DRF group had a greater incidence of NCD compared to the control group (11.3% vs. 8.2%) with a 56% greater relative risk (HR = 1.56, 95% Cl: 1.18, 2.07; p = 0.002) after adjusting for age and comorbidity. For every 10-year age increase, the DRF group was over three times more likely to develop a NCD (HR = 3.23, 95% Cl: 2.57, 4.04; p < 0.001). CONCLUSION: DRF in adults ages 50 to 75 are associated with increased risk of developing neurocognitive disorders. DRF may represent a sentinel opportunity for cognitive screening and early intervention. Distal radius fractures (DRF) have been associated with greater risk of future fractures and physical decline. This study reports that DRF are also associated with greater risk of developing neurocognitive disorders in older adults. Timely intervention may improve early recognition and long-term outcomes for older adults at risk of cognitive decline.

An international genome-wide meta-analysis of primary biliary cholangitis: Novel risk loci and candidate drugs.

BACKGROUNDS & AIMS: Primary biliary cholangitis (PBC) is a chronic liver disease in which autoimmune destruction of the small intrahepatic bile ducts eventually leads to cirrhosis. Many patients have inadequate response to licensed medications, motivating the search for novel therapies. Previous genome-wide association studies (GWAS) and meta-analyses (GWMA) of PBC have identified numerous risk loci for this condition, providing insight into its aetiology. We undertook the largest GWMA of PBC to date, aiming to identify additional risk loci and prioritise candidate genes for in silico drug efficacy screening. METHODS: We combined new and existing genotype data for 10,516 cases and 20,772 controls from 5 European and 2 East Asian cohorts. RESULTS: We identified 56 genome-wide significant loci (20 novel) including 46 in European, 13 in Asian, and 41 in combined cohorts; and a 57th genome-wide significant locus (also novel) in conditional analysis of the European cohorts. Candidate genes at newly identified loci include FCRL3, INAVA, PRDM1, IRF7, CCR6, CD226, and IL12RB1, which each play key roles in immunity. Pathway analysis reiterated the likely importance of pattern recognition receptor and TNF signalling, JAK-STAT signalling, and differentiation of T helper (TH)1 and TH17 cells in the pathogenesis of this disease. Drug efficacy screening identified several medications predicted to be therapeutic in PBC, some of which are well-established in the treatment of other autoimmune disorders. CONCLUSIONS: This study has identified additional risk loci for PBC, provided a hierarchy of agents that could be trialled in this condition, and emphasised the value of genetic and genomic approaches to drug discovery in complex disorders. LAY SUMMARY: Primary biliary cholangitis (PBC) is a chronic liver disease that eventually leads to cirrhosis. In this study, we analysed genetic information from 10,516 people with PBC and 20,772 healthy individuals recruited in Canada, China, Italy, Japan, the UK, or the USA. We identified several genetic regions associated with PBC. Each of these regions contains several genes. For each region, we used diverse sources of evidence to help us choose the gene most likely to be involved in causing PBC. We used these 'candidate genes' to help us identify medications that are currently used for treatment of other conditions, which might also be useful for treatment of PBC.

Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning.

Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95% confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95% CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95% CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95% CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95% CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95% CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.

Environmental risk factors are associated with autoimmune hepatitis.

BACKGROUND: Failure of immunologic homeostasis and resultant hepatocyte destruction in autoimmune hepatitis (AIH) is likely the result of environmental triggers within a permissive genetic architecture. AIMS: We aimed to identify risk factors associated with AIH in a well-phenotyped AIH cohort. METHODS: We prospectively collected environmental questionnaires from 358 AIH cases and 563 healthy controls. Response frequencies were compared using logistic regression, adjusting for age at recruitment, sex and education. RESULTS: AIH cases were more likely to ever have a urinary tract infection (UTI) (53.6% vs 33.9%, P < .001) and recurrent UTI (more than 1 per year) (23.5% vs 15.9%, P = .002) compared to controls. Female cases more frequently had ever used oral contraceptives (83.0% vs 73.7%, P = .006), fewer pregnancies (median = 1 vs 3, P < .001) and less often used hormone replacement therapy compared to controls (28.5% vs 60.1%, P < .001). Current smoking was more prevalent in cases (18.9% vs 7.4%, P = .022), yet no difference according to historical smoking behaviours was observed. Finally, cases were less likely to have history of mumps (32.4% vs 53.1%, P = .011) and rheumatic fever (1.1% vs 4.4%, P = .028), but reported higher vaccination frequency to chicken pox (38% vs 28.1%), measles (66.5% vs 39.3%), mumps (58.7% vs 34.6%), rubella (55.3% vs 32.7%), pertussis (59.8% vs 40.1%) and pneumococcus (47.2% VS 39.4%) (P < .002). CONCLUSIONS: Environmental factors are important in AIH pathogenesis. Replication of these findings and prospective examination may provide new insight into AIH onset and outcomes.

The PSC scientific community resource: an asset for multi-omics interrogation of primary sclerosing cholangitis.

BACKGROUND: Primary sclerosing cholangitis (PSC) is a rare, chronic cholestatic liver disease that often progresses to end-stage liver disease and/or the development of hepatobiliary neoplasia. Lack of prognostic tools and treatment options for PSC is driven in part by our poor understanding of its pathogenesis, which is thought to be complex, the interaction of genetic variants, environmental influences and biological response throughout the course of disease. The PSC Scientific Community Resource (PSC-SCR) seeks to overcome previous shortcomings by facilitating novel research in PSC with the ultimate goals of individualizing patient care and improving patient outcomes. METHODS: PSC patients who receive their health care at Mayo Clinic or a collaborating site are identified by chart review and invited in person or by mail to participate. Non-Mayo patients are offered enrollment if they provide sufficient access to their medical records to evaluate inclusion/exclusion criteria. Controls without liver disease are identified with assistance of the Mayo Clinic Biobank. Participant consent is obtained at the beginning of the recruitment process by mail-in, electronic or face-to-face protocols. Clinical data is extracted from the medical record by qualified physicians and entered in a custom designed database. Participants fill out a custom-designed, comprehensive questionnaire, which collects scientifically relevant demographic and clinical information. Biospecimens are collected using mail-in kits thar are returned via overnight carrier service and processed by the biospecimen accessioning and processing facility at Mayo Clinic, which coordinates sample transfers and provides required sample preparation services. The resource is currently being utilized to perform omics-scale projects investigating the exposome, metabolome, methylome, immunome and microbiome in PSC. Datasets and residual biospecimens will be shared with researchers proposing scientifically sound PSC-focused research with approval of the appropriate review boards. DISCUSSION: Patient-based studies leveraging the latest technologies for targeted and wide-scale interrogation of multiple omics layers offer promise to accelerate PSC research through discovery of unappreciated aspects of disease pathogenesis. However, the rarity of PSC severely limits such studies. Here we describe our effort to overcome this limitation, the PSC-SCR, a repository of patient biospecimens coupled with clinical and omics data for use by the broader PSC research community.

Adjusted Survival Curves Improve Understanding of Multivariable Cox Model Results.

Kaplan-Meier survival curves are the most common methods for unadjusted group comparison of outcomes in orthopedic research. However, they may be misleading due to an imbalance of confounders between patient groups. The Cox model is frequently used to adjust for confounders, but graphical display of adjusted survival curves is not commonly utilized. We describe the circumstances when adjusted survival curves are useful in orthopedic research, describe and use 2 different methods to obtain adjusted curves, and illustrate how they can improve understanding of the multivariable Cox model results. We further provide practical strategies for identifying the need for and performing adjusted survival curves. Please visit the followinghttps://youtu.be/ys0hy2CiMCAfor a video that explains the highlights of the paper in practical terms.

Living With Survival Analysis in Orthopedics.

Time to event data occur commonly in orthopedics research and require special methods that are often called "survival analysis." These data are complex because both a follow-up time and an event indicator are needed to correctly describe the occurrence of the outcome of interest. Common pitfalls in analyzing time to event data include using methods designed for binary outcomes, failing to check proportional hazards, ignoring competing risks, and introducing immortal time bias by using future information. This article describes the concepts involved in time to event analyses as well as how to avoid common statistical pitfalls. Please visit the followinghttps://youtu.be/QNETrx8B6IUandhttps://youtu.be/8SBoTr9Jy1Qfor videos that explain the highlights of the paper in practical terms.

Unsupervised machine learning for the discovery of latent disease clusters and patient subgroups using electronic health records.

Machine learning has become ubiquitous and a key technology on mining electronic health records (EHRs) for facilitating clinical research and practice. Unsupervised machine learning, as opposed to supervised learning, has shown promise in identifying novel patterns and relations from EHRs without using human created labels. In this paper, we investigate the application of unsupervised machine learning models in discovering latent disease clusters and patient subgroups based on EHRs. We utilized Latent Dirichlet Allocation (LDA), a generative probabilistic model, and proposed a novel model named Poisson Dirichlet Model (PDM), which extends the LDA approach using a Poisson distribution to model patients' disease diagnoses and to alleviate age and sex factors by considering both observed and expected observations. In the empirical experiments, we evaluated LDA and PDM on three patient cohorts, namely Osteoporosis, Delirium/Dementia, and Chronic Obstructive Pulmonary Disease (COPD)/Bronchiectasis Cohorts, with their EHR data retrieved from the Rochester Epidemiology Project (REP) medical records linkage system, for the discovery of latent disease clusters and patient subgroups. We compared the effectiveness of LDA and PDM in identifying disease clusters through the visualization of disease representations. We tested the performance of LDA and PDM in differentiating patient subgroups through survival analysis, as well as statistical analysis of demographics and Elixhauser Comorbidity Index (ECI) scores in those subgroups. The experimental results show that the proposed PDM could effectively identify distinguished disease clusters based on the latent patterns hidden in the EHR data by alleviating the impact of age and sex, and that LDA could stratify patients into differentiable subgroups with larger p-values than PDM. However, those subgroups identified by LDA are highly associated with patients' age and sex. The subgroups discovered by PDM might imply the underlying patterns of diseases of greater interest in epidemiology research due to the alleviation of age and sex. Both unsupervised machine learning approaches could be leveraged to discover patient subgroups using EHRs but with different foci.

Posterior single-stepping thresholds are prospectively related to falls in older women.

BACKGROUND: Falls are a leading cause of injury in older women. Stepping thresholds quantify balance-reaction capabilities. It is unclear how such evaluations predict falls in comparison to, or as a complement to, other objective measures of gait, standing postural control, strength, and balance confidence. AIMS: The objective of this study was to determine if stepping thresholds are prospectively related to falls in older women. METHODS: For this prospective cohort study, 125 ambulatory, community-dwelling women, age ≥ 65 years were recruited. Using a treadmill to deliver perturbations to standing participants, we determined anteroposterior single- and multiple-stepping thresholds. Here, thresholds represent the minimum perturbation magnitudes that consistently evoke one step or multiple steps. In addition, gait kinematics, obstacle-crossing kinematics, standing sway measures, unipedal stance time, the functional reach, lower extremity isometric strength, grip strength, balance confidence, and fall history were evaluated. Falls were prospectively recorded for one year. RESULTS: Seventy-four participants (59%) fell at least once. Posterior single-stepping thresholds were the only outcome that predicted future fall status (OR = 1.50, 95% CI 1.01-2.28; AUC = .62). A multivariate approach added postural sway with eyes closed as a second predictive variable, although predictive abilities were not meaningfully improved. DISCUSSION: These results align with the previous evidence that reactive balance is a prospective indicator of fall risk. Unlike previous studies, strength scaled to body size did not contribute to fall prediction. CONCLUSION: Posterior single-stepping thresholds held a significant relationship with future fall status. This relationship was independent of, and superior to that of, other measures of standing balance, gait, strength, and balance confidence.

Age is a critical determinant in recovery from multiple sclerosis relapses.

OBJECTIVE: To evaluate the impact of age on recovery from multiple sclerosis relapses. BACKGROUND: Increasing disability in multiple sclerosis is a consequence of progressive disease and incomplete relapse recovery. METHODS: The first and last-ever relapse data (357 relapses in 193 patients) from the Olmsted County population-based multiple sclerosis cohort were systematically reviewed for age, fulminance, location (optic nerve, brainstem/cerebellar, spinal cord), peak deficit, and maximum recovery. Three different relapse-outcome measures were studied both as paired analyses and as an overall group effect: change from peak deficit to maximum recovery in raw functional system score related to the relapse (ΔFSS), a previously published FSS-based relapse-impact model, and change from peak deficit to maximum recovery in Extended Disability Status Scale (ΔEDSS) score. RESULTS: Older age was linearly associated with worse recovery in the ΔFSS outcome (p = 0.002), ΔEDSS outcome (p < 0.001), and the FSS-based relapse-impact model (p < 0.001). A multivariate analysis of ΔFSS outcome linked poor recovery to older age (p = 0.015), relapse location (transverse myelitis or brainstem/cerebellar syndrome; p < 0.001), and relapse fulminance (p = 0.004). CONCLUSION: Multiple sclerosis-relapse recovery declines in a linear fashion with increased age, which should be considered when making treatment decisions.

Comparison of Lactase Variant MCM6 -13910 C>T Testing and Self-report of Dairy Sensitivity in Patients With Irritable Bowel Syndrome.

GOALS: To evaluate agreement of MCM6-13910 with self-report of dairy sensitivity (DS) and lactose hydrogen methane breath test (LHMBT) results in subjects with irritable bowel syndrome (IBS). BACKGROUND: IBS is a functional gastrointestinal disorder with symptoms including abdominal pain, variable bowel habits, and bloating. Adult patients with lactose malabsorption may present with similar symptoms. Patients with lactose malabsorption have a lactase nonpersistent (LNP) phenotype. Recent studies found 2 single nucleotide polymorphisms associated with LNP: G/A-22018 and C/T-13910. STUDY: Genotyping the MCM6-13910 variant of LNP in 538 IBS patients and 317 controls (without IBS). Subjects completed questionnaires pertaining to gastrointestinal problems and dietary consumption, with charts abstracted. RESULTS: Self-reported DS was higher in IBS (45%) than controls (9.8%, odds ratio=6.46, P<0.001). The C/C-13910 genotype was similar in IBS cases and controls, 81 (15.1%) and 47 (14.8%). Among subjects reporting DS, 49 (18.0%) had the C/C genotype. Overall agreement between genotype and self-reported DS was 0.06 in IBS and 0.07 in controls. There were 20 subjects with LHMBT results; 3 had positive results, 17 were negative. LNP genotypes were found in all 3 of positive LHMBT results; 16 had negative LHMBT among the 17 who were lactase persistent. Agreement between C/C-13910 genotype and LHMBT was excellent with κ-statistic of 0.83 (0.50-1.00). CONCLUSIONS: In IBS patients, self-report of lactose intolerance are highly prevalent but are a poor indicator of underlying C/C-13910 genotype. LHMBT had excellent agreement with C/C-13910 genotype.

Natural language processing of radiology reports for identification of skeletal site-specific fractures.

BACKGROUND: Osteoporosis has become an important public health issue. Most of the population, particularly elderly people, are at some degree of risk of osteoporosis-related fractures. Accurate identification and surveillance of patient populations with fractures has a significant impact on reduction of cost of care by preventing future fractures and its corresponding complications. METHODS: In this study, we developed a rule-based natural language processing (NLP) algorithm for identification of twenty skeletal site-specific fractures from radiology reports. The rule-based NLP algorithm was based on regular expressions developed using MedTagger, an NLP tool of the Apache Unstructured Information Management Architecture (UIMA) pipeline to facilitate information extraction from clinical narratives. Radiology notes were retrieved from the Mayo Clinic electronic health records data warehouse. We developed rules for identifying each fracture type according to physicians' knowledge and experience, and refined these rules via verification with physicians. This study was approved by the institutional review board (IRB) for human subject research. RESULTS: We validated the NLP algorithm using the radiology reports of a community-based cohort at Mayo Clinic with the gold standard constructed by medical experts. The micro-averaged results of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.930, 1.0, 1.0, 0.941, 0.961, respectively. The F1-score is 1.0 for 8 fractures, and above 0.9 for a total of 17 out of 20 fractures (85%). CONCLUSIONS: The results verified the effectiveness of the proposed rule-based NLP algorithm in automatic identification of osteoporosis-related skeletal site-specific fractures from radiology reports. The NLP algorithm could be utilized to accurately identify the patients with fractures and those who are also at high risk of future fractures due to osteoporosis. Appropriate care interventions to those patients, not only the most at-risk patients but also those with emerging risk, would significantly reduce future fractures.

A clinical text classification paradigm using weak supervision and deep representation.

BACKGROUND: Automatic clinical text classification is a natural language processing (NLP) technology that unlocks information embedded in clinical narratives. Machine learning approaches have been shown to be effective for clinical text classification tasks. However, a successful machine learning model usually requires extensive human efforts to create labeled training data and conduct feature engineering. In this study, we propose a clinical text classification paradigm using weak supervision and deep representation to reduce these human efforts. METHODS: We develop a rule-based NLP algorithm to automatically generate labels for the training data, and then use the pre-trained word embeddings as deep representation features for training machine learning models. Since machine learning is trained on labels generated by the automatic NLP algorithm, this training process is called weak supervision. We evaluat the paradigm effectiveness on two institutional case studies at Mayo Clinic: smoking status classification and proximal femur (hip) fracture classification, and one case study using a public dataset: the i2b2 2006 smoking status classification shared task. We test four widely used machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron Neural Networks (MLPNN), and Convolutional Neural Networks (CNN), using this paradigm. Precision, recall, and F1 score are used as metrics to evaluate performance. RESULTS: CNN achieves the best performance in both institutional tasks (F1 score: 0.92 for Mayo Clinic smoking status classification and 0.97 for fracture classification). We show that word embeddings significantly outperform tf-idf and topic modeling features in the paradigm, and that CNN captures additional patterns from the weak supervision compared to the rule-based NLP algorithms. We also observe two drawbacks of the proposed paradigm that CNN is more sensitive to the size of training data, and that the proposed paradigm might not be effective for complex multiclass classification tasks. CONCLUSION: The proposed clinical text classification paradigm could reduce human efforts of labeled training data creation and feature engineering for applying machine learning to clinical text classification by leveraging weak supervision and deep representation. The experimental experiments have validated the effectiveness of paradigm by two institutional and one shared clinical text classification tasks.