Nevin Manimala

JAMA Netw Open. 2021 May 3;4(5):e2110432. doi: 10.1001/jamanetworkopen.2021.10432.

ABSTRACT

IMPORTANCE: Low socioeconomic status (SES) has been identified as a risk factor for the development of dementia. However, few studies have focused on the association between SES and dementia diagnostic evaluation on a population level.

OBJECTIVE: To investigate whether household income (HHI) is associated with dementia diagnosis and cognitive severity at the time of diagnosis.

DESIGN, SETTING, AND PARTICIPANTS: This population- and register-based cross-sectional study analyzed health, social, and economic data obtained from various Danish national registers. The study population comprised individuals who received a first-time referral for a diagnostic evaluation for dementia to the secondary health care sector of Denmark between January 1, 2017, and December 17, 2018. Dementia-related health data were retrieved from the Danish Quality Database for Dementia. Data analysis was conducted from October 2019 to December 2020.

EXPOSURES: Annual HHI (used as a proxy for SES) for 2015 and 2016 was obtained from Statistics Denmark and categorized into upper, middle, and lower tertiles within 5-year interval age groups.

MAIN OUTCOMES AND MEASURES: Dementia diagnoses (Alzheimer disease, vascular dementia, mixed dementia, dementia with Lewy bodies, Parkinson disease dementia, or other) and cognitive stages at diagnosis (cognitively intact; mild cognitive impairment but not dementia; or mild, moderate, or severe dementia) were retrieved from the database. Univariable and multivariable logistic and linear regressions adjusted for age group, sex, region of residence, household type, period (2017 and 2018), medication type, and medical conditions were analyzed for a possible association between HHI and receipt of dementia diagnosis.

RESULTS: Among the 10 191 individuals (mean [SD] age, 75 [10] years; 5476 women [53.7%]) included in the study, 8844 (86.8%) were diagnosed with dementia. Individuals with HHI in the upper tertile compared with those with lower-tertile HHI were less likely to receive a dementia diagnosis after referral (odds ratio, 0.65; 95% CI, 0.55-0.78) and, if diagnosed with dementia, had less severe cognitive stage (β, -0.16; 95% CI, -0.21 to -0.10). Individuals with middle-tertile HHI did not significantly differ from those with lower-tertile HHI in terms of dementia diagnosis (odds ratio, 0.92; 95% CI, 0.77-1.09) and cognitive stage at diagnosis (β, 0.01; 95% CI, -0.04 to 0.06).

CONCLUSIONS AND RELEVANCE: The results of this study revealed a social inequality in dementia diagnostic evaluation: in Denmark, people with higher income seem to receive an earlier diagnosis. Public health strategies should target people with lower SES for earlier dementia detection and intervention.

PMID:34003271 | DOI:10.1001/jamanetworkopen.2021.10432

Artif Intell Med. 2021 May;115:102060. doi: 10.1016/j.artmed.2021.102060. Epub 2021 Mar 26.

ABSTRACT

BACKGROUND: Oral cancer can show heterogenous patterns of behavior. For proper and effective management of oral cancer, early diagnosis and accurate prediction of prognosis are important. To achieve this, artificial intelligence (AI) or its subfield, machine learning, has been touted for its potential to revolutionize cancer management through improved diagnostic precision and prediction of outcomes. Yet, to date, it has made only few contributions to actual medical practice or patient care.

OBJECTIVES: This study provides a systematic review of diagnostic and prognostic application of machine learning in oral squamous cell carcinoma (OSCC) and also highlights some of the limitations and concerns of clinicians towards the implementation of machine learning-based models for daily clinical practice.

DATA SOURCES: We searched OvidMedline, PubMed, Scopus, Web of Science, and Institute of Electrical and Electronics Engineers (IEEE) databases from inception until February 2020 for articles that used machine learning for diagnostic or prognostic purposes of OSCC.

ELIGIBILITY CRITERIA: Only original studies that examined the application of machine learning models for prognostic and/or diagnostic purposes were considered.

DATA EXTRACTION: Independent extraction of articles was done by two researchers (A.R. & O.Y) using predefine study selection criteria. We used the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) in the searching and screening processes. We also used Prediction model Risk of Bias Assessment Tool (PROBAST) for assessing the risk of bias (ROB) and quality of included studies.

RESULTS: A total of 41 studies were published to have used machine learning to aid in the diagnosis/or prognosis of OSCC. The majority of these studies used the support vector machine (SVM) and artificial neural network (ANN) algorithms as machine learning techniques. Their specificity ranged from 0.57 to 1.00, sensitivity from 0.70 to 1.00, and accuracy from 63.4 % to 100.0 % in these studies. The main limitations and concerns can be grouped as either the challenges inherent to the science of machine learning or relating to the clinical implementations.

CONCLUSION: Machine learning models have been reported to show promising performances for diagnostic and prognostic analyses in studies of oral cancer. These models should be developed to further enhance explainability, interpretability, and externally validated for generalizability in order to be safely integrated into daily clinical practices. Also, regulatory frameworks for the adoption of these models in clinical practices are necessary.

PMID:34001326 | DOI:10.1016/j.artmed.2021.102060

Artif Intell Med. 2021 May;115:102063. doi: 10.1016/j.artmed.2021.102063. Epub 2021 Mar 31.

ABSTRACT

PURPOSE: Here we aimed to automatically classify human emotion earlier than is typically attempted. There is increasing evidence that the human brain differentiates emotional categories within 100-300 ms after stimulus onset. Therefore, here we evaluate the possibility of automatically classifying human emotions within the first 300 ms after the stimulus and identify the time-interval of the highest classification performance.

METHODS: To address this issue, MEG signals of 17 healthy volunteers were recorded in response to three different picture stimuli (pleasant, unpleasant, and neutral pictures). Six Linear Discriminant Analysis (LDA) classifiers were used based on two binary comparisons (pleasant versus neutral and unpleasant versus neutral) and three different time-intervals (100-150 ms, 150-200 ms, and 200-300 ms post-stimulus). The selection of the feature subsets was performed by Genetic Algorithm and LDA.

RESULTS: We demonstrated significant classification performances in both comparisons. The best classification performance was achieved with a median AUC of 0.83 (95 %- CI [0.71; 0.87]) classifying brain responses evoked by unpleasant and neutral stimuli within 100-150 ms, which is at least 850 ms earlier than attempted by other studies.

CONCLUSION: Our results indicate that using the proposed algorithm, brain emotional responses can be significantly classified at very early stages of cortical processing (within 300 ms). Moreover, our results suggest that emotional processing in the human brain occurs within the first 100-150 ms.

PMID:34001320 | DOI:10.1016/j.artmed.2021.102063

Artif Intell Med. 2021 May;115:102059. doi: 10.1016/j.artmed.2021.102059. Epub 2021 Mar 26.

ABSTRACT

In the healthcare domain, trust, confidence, and functional understanding are critical for decision support systems, therefore, presenting challenges in the prevalent use of black-box deep learning (DL) models. With recent advances in deep learning methods for classification tasks, there is an increased use of deep learning in healthcare decision support systems, such as detection and classification of abnormal Electrocardiogram (ECG) signals. Domain experts seek to understand the functional mechanism of black-box models with an emphasis on understanding how these models arrive at specific classification of patient medical data. In this paper, we focus on ECG data as the healthcare data signal to be analyzed. Since ECG is a one-dimensional time-series data, we target 1D-CNN (Convolutional Neural Networks) as the candidate DL model. Majority of existing interpretation and explanations research has been on 2D-CNN models in non-medical domain leaving a gap in terms of explanation of CNN models used on medical time-series data. Hence, we propose a modular framework, CNN Explanations Framework for ECG Signals (CEFEs), for interpretable explanations. Each module of CEFEs provides users with the functional understanding of the underlying CNN models in terms of data descriptive statistics, feature visualization, feature detection, and feature mapping. The modules evaluate a model’s capacity while inherently accounting for correlation between learned features and raw signals which translates to correlation between model’s capacity to classify and it’s learned features. Explainable models such as CEFEs could be evaluated in different ways: training one deep learning architecture on different volumes/amounts of the same dataset, training different architectures on the same data set or a combination of different CNN architectures and datasets. In this paper, we choose to evaluate CEFEs extensively by training on different volumes of datasets with the same CNN architecture. The CEFEs’ interpretations, in terms of quantifiable metrics, feature visualization, provide explanation as to the quality of the deep learning model where traditional performance metrics (such as precision, recall, accuracy, etc.) do not suffice.

PMID:34001319 | DOI:10.1016/j.artmed.2021.102059

Clin Exp Rheumatol. 2021 May 5. Online ahead of print.

ABSTRACT

OBJECTIVES: To search for predictors of polyarticular extension in children with oligoarticular-onset juvenile idiopathic arthritis (JIA) and to develop a prediction model for an extended course.

METHODS: The clinical charts of consecutive patients with oligoarticular-onset JIA and ≥2 years of disease duration were reviewed. Predictor variables included demographic data, number and type of affected joints, presence of iridocyclitis, laboratory tests including antinuclear antibodies, and therapeutic interventions in the first 6 months. Joint examinations were evaluated to establish whether after the first 6 months of disease patients had persistent or extended course (i.e. involvement of 4 or less, or 5 or more joints). Statistics included univariable and multivariable analyses. Regression coefficients (β) of variables that entered the best-fitting logistic regression model were converted and summed to obtain a “prediction score” for an extended course.

RESULTS: A total of 480 patients with a median disease duration of 7.4 years were included. 61.2% had persistent oligoarthritis, whereas 38.8% experienced polyarticular extension. On multivariable analysis, independent correlations with extended course were identified for the presence of ≥2 involved joints and a CRP >0.8 mg/dl in the first 6 months. The prediction score ranged from 0 to 6 and its cut-off that discriminated best between patients who had or did not have polyarticular extension was >1. Sensitivity and specificity were 59.6 and 79.8, respectively.

CONCLUSIONS: The number of affected joints and the CRP level in the first 6 months were the strongest predictors of polyarticular extension in our children with oligoarticular-onset JIA.

PMID:34001309

Clin Exp Rheumatol. 2021 May 5. Online ahead of print.

ABSTRACT

OBJECTIVES: To analyse rheumatoid arthritis (RA)-patients depending on their individual peak radiographic progression.

METHODS: We selected for the individual peak radiographic progression (Δ Ratingen scores/time) in patients of the Swiss registry SCQM. The baseline disease characteristics were compared using standard descriptive statistics. The change of DAS 28 (disease activity sore) and HAQ-DI (Health Assessment Questionnaire Disability Index) before and after peak progression was analysed with Wilcoxon signed rank tests.

RESULTS: Of the 4,033 patients in the analysis, 3,049 patients had a peak radiographic progression rate between 0 and ≤10 in the Ratingen score per year, 773 between 10 and ≤20, 150 between 20 and ≤30, and 61 of >30 (defining groups A-D). Rheumatoid factor was more frequent in patient groups with a higher peak radiographic progression (71.1%, 79.2%, 85.3%, 88.5%, groups A-D). Peak radiographic progression at a rate >20/year (groups C-D) was not detected after December 2012. When the rate of radiographic progression before and after peak progression was analysed, it was significantly lower. The DAS 28 was significantly higher in all patient groups before peak progression and lower thereafter (p<0.001). Average HAQ-DI scores increased after peak radiographic progression in group D (p=0.005) whereas it was stable or even decreased among the patients of the other patient groups.

CONCLUSIONS: These data show that the highest radiographic progression rates are rare and get less frequent over the last years. Higher disease activity precedes radiographic peak progression. Only the highest individual peak (change of Ratingen score >30/year) radiographic progression was followed by an increase of HAQ-DI scores.

PMID:34001300

Psychol Med. 2021 May 18:1-10. doi: 10.1017/S0033291721001628. Online ahead of print.

ABSTRACT

BACKGROUND: While evidence-based psychotherapy (EBP) for posttraumatic stress disorder (PTSD) is a first-line treatment, its real-world effectiveness is unknown. We compared cognitive processing therapy (CPT) and prolonged exposure (PE) each to an individual psychotherapy comparator group, and CPT to PE in a large national healthcare system.

METHODS: We utilized effectiveness and comparative effectiveness emulated trials using retrospective cohort data from electronic medical records. Participants were veterans with PTSD initiating mental healthcare (N = 265 566). The primary outcome was PTSD symptoms measured by the PTSD Checklist (PCL) at baseline and 24-week follow-up. Emulated trials were comprised of ‘person-trials,’ representing 112 discrete 24-week periods of care (10/07-6/17) for each patient. Treatment group comparisons were made with generalized linear models, utilizing propensity score matching and inverse probability weights to account for confounding, selection, and non-adherence bias.

RESULTS: There were 636 CPT person-trials matched to 636 non-EBP person-trials. Completing ⩾8 CPT sessions was associated with a 6.4-point greater improvement on the PCL (95% CI 3.1-10.0). There were 272 PE person-trials matched to 272 non-EBP person-trials. Completing ⩾8 PE sessions was associated with a 9.7-point greater improvement on the PCL (95% CI 5.4-13.8). There were 232 PE person-trials matched to 232 CPT person-trials. Those completing ⩾8 PE sessions had slightly greater, but not statistically significant, improvement on the PCL (8.3-points; 95% CI 5.9-10.6) than those completing ⩾8 CPT sessions (7.0-points; 95% CI 5.5-8.5).

CONCLUSIONS: PTSD symptom improvement was similar and modest for both EBPs. Although EBPs are helpful, research to further improve PTSD care is critical.

PMID:34001290 | DOI:10.1017/S0033291721001628

Neurol Res Pract. 2021 May 17;3(1):27. doi: 10.1186/s42466-021-00125-0.

ABSTRACT

BACKGROUND: Emergency intubation is an inherent risk of procedural sedation regimens for endovascular treatment (EVT) of acute ischemic stroke. We aimed to characterize the subgroup of patients, who had to be emergently intubated, to identify predictors of the need for intubation and assess their outcomes.

METHODS: This is a retrospective analysis of the single-center study KEEP SIMPLEST, which evaluated a new in-house SOP for EVT under primary procedural sedation. We used descriptive statistics and regression models to examine predictors and functional outcome of emergently intubated patients.

RESULTS: Twenty of 160 (12.5%) patients were emergently intubated. National Institutes of Health Stroke Scale (NIHSS) on admission, premorbid modified Rankin scale (mRS), Alberta Stroke Program Early CT Score, age and side of occlusion were not associated with need for emergency intubation. Emergency intubation was associated with a lower rate of successful reperfusion (OR, 0.174; 95%-CI, 0.045 to 0.663; p = 0.01). Emergently intubated patients had higher in-house mortality (30% vs 6.4%; p = 0.001) and a lower rate of mRS 0-2 at 3 months was observed in those patients (10.5% vs 37%, p = 0.024).

CONCLUSIONS: Emergency intubation during a primary procedural sedation regimen for EVT was associated with lower rate of successful reperfusion. Less favorable outcome was observed in the subgroup of emergently intubated patients. More research is required to find practical predictors of intubation need and to determine, whether emergency intubation is safe under strict primary procedural sedation regimens for EVT.

PMID:34001285 | DOI:10.1186/s42466-021-00125-0

Infect Dis Poverty. 2021 May 17;10(1):69. doi: 10.1186/s40249-021-00836-1.

ABSTRACT

BACKGROUND: COVID-19 can lead to increased psychological symptoms such as post-traumatic stress disorder (PTSD), depression, and anxiety among patients with COVID-19. Based on the previous mindfulness-based interventions proved to be effective, this protocol reports a design of a randomized controlled trial aiming to explore the efficacy and possible mechanism of a mindful living with challenge (MLWC) intervention developed for COVID-19 survivors in alleviating their psychological problems caused by both the disease and the pandemic.

METHODS: In April 2021, more than 1600 eligible participants from Hubei Province of China will be assigned 1:1 to an online MLWC intervention group or a waitlist control group. All participants will be asked to complete online questionnaires at baseline, post-program, and 3-month follow-up. The differences of mental health status (e.g. PTSD) and physical symptoms including fatigue and sleeplessness between the COVID-19 survivors who receiving the online MLWC intervention and the control group will be assessed. In addition, the possible mediators and moderators of the link between the MLWC intervention and target outcomes will be evaluated by related verified scales, such as the Five Facets Mindfulness Questionnaire. Data will be analyzed based on an intention-to-treat approach, and SPSS software will be used to perform statistical analysis.

DISCUSSION: The efficacy and potential mechanism of MLWC intervention in improving the quality of life and psychological status of COVID-19 survivors in China are expected to be reported. Findings from this study will shed light on a novel and feasible model in improving the psychological well-being of people during such public health emergencies. Trial registration Chinese Clinical Trial Registry (ChiCTR), ChiCTR2000037524; Registered on August 29, 2020, http://www.chictr.org.cn/showproj.aspx?proj=60034 .

PMID:34001277 | DOI:10.1186/s40249-021-00836-1

Genome Med. 2021 May 17;13(1):83. doi: 10.1186/s13073-021-00904-z.

ABSTRACT

BACKGROUND: While genome-wide associations studies (GWAS) have successfully elucidated the genetic architecture of complex human traits and diseases, understanding mechanisms that lead from genetic variation to pathophysiology remains an important challenge. Methods are needed to systematically bridge this crucial gap to facilitate experimental testing of hypotheses and translation to clinical utility.

RESULTS: Here, we leveraged cross-phenotype associations to identify traits with shared genetic architecture, using linkage disequilibrium (LD) information to accurately capture shared SNPs by proxy, and calculate significance of enrichment. This shared genetic architecture was examined across differing biological scales through incorporating data from catalogs of clinical, cellular, and molecular GWAS. We have created an interactive web database (interactive Cross-Phenotype Analysis of GWAS database (iCPAGdb)) to facilitate exploration and allow rapid analysis of user-uploaded GWAS summary statistics. This database revealed well-known relationships among phenotypes, as well as the generation of novel hypotheses to explain the pathophysiology of common diseases. Application of iCPAGdb to a recent GWAS of severe COVID-19 demonstrated unexpected overlap of GWAS signals between COVID-19 and human diseases, including with idiopathic pulmonary fibrosis driven by the DPP9 locus. Transcriptomics from peripheral blood of COVID-19 patients demonstrated that DPP9 was induced in SARS-CoV-2 compared to healthy controls or those with bacterial infection. Further investigation of cross-phenotype SNPs associated with both severe COVID-19 and other human traits demonstrated colocalization of the GWAS signal at the ABO locus with plasma protein levels of a reported receptor of SARS-CoV-2, CD209 (DC-SIGN). This finding points to a possible mechanism whereby glycosylation of CD209 by ABO may regulate COVID-19 disease severity.

CONCLUSIONS: Thus, connecting genetically related traits across phenotypic scales links human diseases to molecular and cellular measurements that can reveal mechanisms and lead to novel biomarkers and therapeutic approaches. The iCPAGdb web portal is accessible at http://cpag.oit.duke.edu and the software code at https://github.com/tbalmat/iCPAGdb .

PMID:34001247 | DOI:10.1186/s13073-021-00904-z