Tag: statistics

J Neural Transm (Vienna). 2021 May 18. doi: 10.1007/s00702-021-02352-w. Online ahead of print.

ABSTRACT

The level of functioning of individuals with autism spectrum disorder (ASD) varies widely. To better understand the neurobiological mechanism associated with high-functioning ASD, we studied the rare case of a female patient with an exceptional professional career in the highly competitive academic field of Mathematics. According to the Research Domain Criteria (RDoC) approach, which proposes to describe the basic dimensions of functioning by integrating different levels of information, we conducted four fMRI experiments targeting the (1) social processes domain (Theory of mind (ToM) and face matching), (2) positive valence domain (reward processing), and (3) cognitive domain (N-back). Patient’s data were compared to data of 14 healthy controls (HC). Additionally, we assessed the subjective experience of our case during the experiments. The patient showed increased response times during face matching and achieved a higher total gain in the Reward task, whereas her performance in N-back and ToM was similar to HC. Her brain function differed mainly in the positive valence and cognitive domains. During reward processing, she showed reduced activity in a left-hemispheric frontal network and cortical midline structures but increased connectivity within this network. During the working memory task patients’ brain activity and connectivity in left-hemispheric temporo-frontal regions were elevated. In the ToM task, activity in posterior cingulate cortex and temporo-parietal junction was reduced. We suggest that the high level of functioning in our patient is rather related to the effects in brain connectivity than to local cortical information processing and that subjective report provides a fruitful framework for interpretation.

PMID:34003357 | DOI:10.1007/s00702-021-02352-w

Z Rheumatol. 2021 May 18. doi: 10.1007/s00393-021-01012-4. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Health workforce shortage in German rheumatology has been identified as a healthcare service and delivery problem. Health policy has increased staffing targets, yet effective intervention strategies are lacking. This research aimed to systematically map the rheumatology workforce to improve the evidence for interventions and explore possibilities for more effective health workforce management.

METHODS: The WHO National Health Workforce Accounts provided a conceptual framework for the mapping exercise. Four major sets of indicators were selected, comprising staffing levels, health labor market flows, composition and education/training. A comparison of age groups and time series was applied to explore trends. Public statistics and other secondary sources served our analysis using descriptive methodology.

RESULTS: In Germany there are 1076 physicians specialized in internal medical rheumatology. Absolute numbers have nearly doubled (91%) since 2000 but with a strong demographic bias. Between 2000 and 2019 numbers markedly increased in the group aged 50 years and older but only by 9% in the younger group under 50 years; since 2010 the group aged 40-50 years even faces a decrease. In 2019, the absolute numbers of rheumatologists in retirement age exceeded those aged 40 years and under. Since 2015 an expanding workforce trend has overall flattened but this was strongest in the hospital sector; the numbers in resident training did not show any relevant growth.

CONCLUSION: Health workforce trends reveal that an available number of rheumatologists cannot meet new health policy planning targets. There is a need for effective health workforce management, focusing on innovation in resident training, improved task delegation and gender equality.

PMID:34003376 | DOI:10.1007/s00393-021-01012-4

Diabetologia. 2021 May 18. doi: 10.1007/s00125-021-05468-6. Online ahead of print.

ABSTRACT

AIMS/HYPOTHESIS: The circadian clock influences both diabetes and immunity. Our goal in this study was to characterise more thoroughly the circadian patterns of immune cell populations and cytokines that are particularly relevant to the immune pathology of type 1 diabetes and thus fill in a current gap in our understanding of this disease.

METHODS: Ten individuals with established type 1 diabetes (mean disease duration 11 years, age 18-40 years, six female) participated in a circadian sampling protocol, each providing six blood samples over a 24 h period.

RESULTS: Daily ranges of population frequencies were sometimes large and possibly clinically significant. Several immune populations, such as dendritic cells, CD4 and CD8 T cells and their effector memory subpopulations, CD4 regulatory T cells, B cells and cytokine IL-6, exhibited statistically significant circadian rhythmicity. In a comparison with historical healthy control individuals, but using shipped samples, we observed that participants with type 1 diabetes had statistically significant phase shifts occurring in the time of peak occurrence of B cells (+4.8 h), CD4 and CD8 T cells (~ +5 h) and their naive and effector memory subsets (~ +3.3 to +4.5 h), and regulatory T cells (+4.1 h). An independent streptozotocin murine experiment confirmed the phase shifting of CD8 T cells and suggests that circadian dysrhythmia in type 1 diabetes might be an effect and not a cause of the disease.

CONCLUSIONS/INTERPRETATION: Future efforts investigating this newly described aspect of type 1 diabetes in human participants are warranted. Peripheral immune populations should be measured near the same time of day in order to reduce circadian-related variation.

PMID:34003304 | DOI:10.1007/s00125-021-05468-6

Eur J Trauma Emerg Surg. 2021 May 18. doi: 10.1007/s00068-021-01693-1. Online ahead of print.

ABSTRACT

PURPOSE: Traumatic brain injury is one of the leading causes of disability worldwide. Mild traumatic brain injury (TBI) is the most common and benign form of TBI, usually referred to by the medical term “concussion”. The purpose of our systematic review and meta-analysis was to explore the role of serum and CSF neurofilament light chain (NfL) as a potential biomarker in concussion.

METHODS: We systematically searched PubMed, Web of Science, and Cochrane databases using specific keywords. As the primary outcome, we assessed CSF or serum NfL levels in patients with concussion and head impacts versus controls. The role of NfL in patients with concussion and head impacts compared to healthy controls was also assessed, as well as in sports-related and military-related conditions.

RESULTS: From the initial 617 identified studies, we included 24 studies in our qualitative analysis and 14 studies in our meta-analysis. We found a statistically significant increase of serum NfL in patients suffering from a concussion or head impacts compared to controls (p = 0.0023), highlighting its potential role as a biomarker. From our sub-group analyses, sports-related concussion and mild TBI were mostly correlated with increased serum NfL values. Compared to controls, sports-related concussion was significantly associated with higher NfL levels (p = 0.0015), while no association was noted in patients suffering from head impacts or military-related TBI.

CONCLUSION: Serum NfL levels are higher in all patients suffering from concussion compared to healthy controls. The sports-related concussion was specifically associated with higher levels of NfL. Further studies exploring the use of NfL as a diagnostic and prognostic biomarker in mild TBI and head impacts are needed.

PMID:34003313 | DOI:10.1007/s00068-021-01693-1

Eur Radiol. 2021 May 18. doi: 10.1007/s00330-021-08033-2. Online ahead of print.

ABSTRACT

OBJECTIVES: To review the effectiveness and safety of chemical ablation using ethanol or OK-432 for the treatment of TGDCs (thyroglossal duct cysts).

METHODS: MEDLINE and EMBASE databases were searched up to May 29, 2020, to identify studies reporting the safety and efficacy of chemical ablation using ethanol or OK-432 for the treatment of TGDCs. The search query consisted of synonyms of thyroglossal duct cysts and ethanol or OK-432 ablation. The pooled success and complication rates were calculated using the inverse variance method to calculate weights, and pooled proportions were determined using the DerSimonian-Laird random-effects method.

RESULTS: Seven original articles including a total of 129 patients were included. The efficacy of chemical ablation was acceptable, with a pooled success rate of 70% (95% CI, 47-86%). The pooled success rate of ethanol ablation was superior to that of OK-432 ablation, although with equivocal statistical significance (84% vs. 51%, p = 0.055). Repeat ethanol ablation achieved a pooled success rate of 47% (95% CI, 24-71%). The chemical ablation procedures were safe, with a pooled major complication rate of 0.9% (95% CI, 0.1-5.8%).

CONCLUSIONS: Chemical ablation using ethanol or OK-432 for the treatment of TGDCs had acceptable success and low complication rates, and repeat treatment after initial failure was also feasible. In addition, it is an inexpensive and simple procedure and could therefore be considered a first-line treatment for TGDCs.

KEY POINTS: • The efficacy of chemical ablation using ethanol or OK-432 was acceptable, with a pooled success rate of 70% (95% CI, 47-86%). The pooled success rate of ethanol ablation was superior to that of OK-432 ablation, although with equivocal statistical significance (84% vs. 51%, p = 0.055). • Repeat ethanol ablation was also feasible, with a pooled success rate of 47% (95% CI, 24-71%). • The chemical ablation procedures were safe, with a pooled major complication rate of 0.9% (95% CI, 0.1-5.8%).

PMID:34003346 | DOI:10.1007/s00330-021-08033-2

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

JAMA Netw Open. 2021 May 3;4(5):e218348. doi: 10.1001/jamanetworkopen.2021.8348.

ABSTRACT

IMPORTANCE: The disease burden for primary open-angle glaucoma (POAG) is highest among racial/ethnic minority groups, particularly Black individuals. The prevalence of POAG worldwide is projected to increase from 52.7 million in 2020 to 79.8 million in 2040, a 51.4% increase attributed mainly to Asian and African individuals. Given this increase, key stakeholders need to pay particular attention to creating a diverse study population in POAG clinical trials.

OBJECTIVE: To assess the prevalence of racial/ethnic minorities in POAG clinical research trials compared with White individuals.

DATA SOURCES: This meta-analysis consisted of publicly available POAG clinical trials using ClinicalTrials.gov, PubMed, and Drugs@FDA from 1994 to 2019.

STUDY SELECTION: Randomized clinical trials that reported on interventions for POAG and included demographic subgroups including sex and race/ethnicity.

DATA EXTRACTION AND SYNTHESIS: Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 2 independent reviewers extracted study-level data for a random-effects meta-analysis. A third person served as the tiebreaker on study selection. Microsoft Excel 2016 (Microsoft Corporation) and SAS, version 9.4 (SAS Institute) were used for data collection and analyses.

MAIN OUTCOMES AND MEASURES: The primary outcomes were the prevalence of each demographic subgroup (White, Black, Hispanic/Latino, other race/ethnicity groups, and female or male) in each trial according to the trial start year, study region, and study sponsor. Participation rates are expressed as percentages.

RESULTS: A total of 105 clinical trials were included in the meta-analysis, including 33 428 POAG clinical trial participants (18 404 women [55.1%]). Overall, 70.7% were White patients, 16.8% were Black patients, 3.4% were Hispanic/Latino patients, and 9.1% were individuals of other races/ethnicities, including Asian, Native Hawaiian or Pacific Islander, American Indian or Alaska Native, and unreported as defined by the US Census. The mean (SD) numbers of participants by race/ethnicity were 236.5 (208.2) for White, 58.4 (70.0) for Black, 29.9 (71.1) for Hispanic/Latino, and 31.1 (94.3) for other race/ethnicity. According to the test for heterogeneity using the Cochrane Risk of Bias tool, the I2 statistic was 98%, indicating high heterogeneity of outcomes in the included trials. A multiple linear regression analysis was performed to assess any trend and significance between participation by Black individuals and the year the study started, the region in which the study took place, and the study sponsor. There was no significant increase of Black participant enrollment from 1994 to 2019 (r2 = 0.11; P = .17) and no significant association between Black participant enrollment and clinical trial region (r2 = 0.16; P = .50), but there was a significant association between Black participant enrollment and study sponsor (r2 = 0.94; P = .03).

CONCLUSIONS AND RELEVANCE: This meta-analysis found that compared with White individuals, individuals from racial/ethnic minority groups had a very low participation rate in POAG clinical trials despite having a higher prevalence among the disease population. Despite measures to increase clinical trial diversity, there has not been a significant increase in clinical trial participation among Black individuals, the group most affected by this disease; this disparity in POAG clinical trial representation can raise questions about the true safety and efficacy of approved medical interventions for this disease and should prompt further research on how to increase POAG clinical trial diversity.

PMID:34003274 | DOI:10.1001/jamanetworkopen.2021.8348

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;115:102059. 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

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