Category: Statistics

Front Digit Health. 2021 Jul;3:714741. doi: 10.3389/fdgth.2021.714741. Epub 2021 Jul 26.

ABSTRACT

Transient increases in peripheral vasoconstriction frequently occur in obstructive sleep apnea and periodic leg movement disorder, both of which are common in sickle cell disease (SCD). These events reduce microvascular blood flow and increase the likelihood of triggering painful vaso-occlusive crises (VOC) that are the hallmark of SCD. We recently reported a significant association between the magnitude of vasoconstriction, inferred from the finger photoplethysmogram (PPG) during sleep, and the frequency of future VOC in 212 children with SCD. In this study, we present an improved predictive model of VOC frequency by employing a two-level stacking machine learning (ML) model that incorporates detailed features extracted from the PPG signals in the same database. The first level contains seven different base ML algorithms predicting each subject’s pain category based on the input PPG characteristics and other clinical information, while the second level is a meta model which uses the inputs to the first-level model along with the outputs of the base models to produce the final prediction. Model performance in predicting future VOC was significantly higher than in predicting VOC prior to each sleep study (F1-score of 0.43 vs 0.35, p-value < 0.0001), consistent with our hypothesis of a causal relationship between vasoconstriction and future pain incidence, rather than past pain leading to greater propensity for vasoconstriction. The model also performed much better than our previous conventional statistical model (F1=0.33), as well as all other algorithms that used only the base-models for predicting VOC without the second tier meta model. The modest F1 score of the present predictive model was due in part to the relatively small database with substantial imbalance (176:36) between low-pain and high-pain subjects, as well as other factors not captured by the sleep data alone. This report represents the first attempt ever to use noninvasive finger PPG measurements during sleep and a ML-based approach to predict increased propensity for VOC crises in SCD. The promising results suggest the future possibility of embedding an improved version of this model in a low-cost wearable system to assist clinicians in managing long-term therapy for SCD patients.

PMID:34396363 | PMC:PMC8360353 | DOI:10.3389/fdgth.2021.714741

JACC CardioOncol. 2021 Jun 15;3(2):305-315. doi: 10.1016/j.jaccao.2021.04.008. eCollection 2021 Jun.

ABSTRACT

BACKGROUND: There are limited data to guide oncology and cardiology decision-making in patients with a left ventricular assist device (LVAD) and concurrent active malignancy.

OBJECTIVES: The goal of this study was to describe cancer treatment approaches, complications, and survival among patients with active cancer on LVAD support in 2 tertiary heart failure and oncology programs.

METHODS: In this retrospective cohort study, LVAD databases were reviewed to identify patients with a cancer diagnosis at the time of or after LVAD implantation. We created a 3:1 matched cohort based on age, sex, etiology of cardiomyopathy, LVAD implant strategy, and INTERMACS profile stratified by site. Kaplan-Meier analysis and Cox proportional hazards models were used to compare survival between patients with cancer and non-cancer comparators.

RESULTS: Among 1,123 patients who underwent LVAD implantation between 2005 and 2019, 22 patients with LVADs with active cancer and 66 matched non-cancer comparators were identified. Median age was 62 years (range 41 to 73 years); 50% of patients with cancer were African-American, and 27% were women. Prostate cancer, followed by renal cell cancer and hematologic malignancies were the most common diagnoses. There was no significant difference in unadjusted Kaplan-Meier median survival estimates from the time of LVAD placement between patients with cancer (3.53 years; 95% confidence interval [CI]: 1.41 to 5.33) and non-cancer comparators (3.03 years; 95% CI: 1.83 to 5.26; log-rank P = 0.99). In Cox proportional hazard models, cancer diagnosis as a time-varying variable was associated with a statistically significant increase in death (hazard ratio: 2.05; 95% CI: 1.03 to 4.12; P = 0.04). Patients with cancer had less gastrointestinal bleeding compared with matched non-cancer comparators (P = 0.016). Other complications were not significantly different.

CONCLUSIONS: Our study provides initial feasibility and safety data and set a framework for multidisciplinary team management of patients with cancer and LVADs.

PMID:34396339 | PMC:PMC8352017 | DOI:10.1016/j.jaccao.2021.04.008

Public Health Pract (Oxf). 2021 Aug 8:100173. doi: 10.1016/j.puhip.2021.100173. Online ahead of print.

ABSTRACT

OBJECTIVES: COVID-19 is a disease of varying presentation and neurological sequelae of the disease are being studied. Following a cluster of paediatric facial nerve palsy (FNP) cases in an area of South Wales with a high prevalence of COVID-19, we conducted an opportunistic study to determine whether there has been an increase in incidence of FNP and if there is an association between the FNP and COVID-19 in children.

STUDY DESIGN: A retrospective cohort study. Using the case series from 2020 and comparing it with previous years.

METHODS: We reviewed the incidence of FNP between 2015-2020 across two hospitals within the health board. The incidence was compared with that in 2020 including a cluster of six children in 14 weeks, presenting to the Royal Glamorgan Hospital between June and October.

RESULTS: There were 48 cases of children with FNP across both hospital within the study years. Seven (7) cases in 2020. The incidence was not statistically different in comparison to other years.Five out of six of these children in 2020 had antibody testing for COVID-19. All serology testing (100%) returned negative for SARS-CoV- 2 antibodies.In high prevalence area for COVID-19, cases of children with FNP have not shown a commensurate increase. we have found no causal link between COVID-19 and FNP in children. While this is a small study, larger cohort studies are needed to support this finding.

CONCLUSION: As new strains of COVID-19 are being reported in UK, South Africa and Brazil, physicians need to continue to be vigilant for consistent pattern of signs and symptoms, especially in children.

PMID:34396357 | PMC:PMC8349358 | DOI:10.1016/j.puhip.2021.100173

JACC CardioOncol. 2021 Jun 15;3(2):221-232. doi: 10.1016/j.jaccao.2021.03.006. eCollection 2021 Jun.

ABSTRACT

BACKGROUND: Patients with cancer have an increased risk of atrial fibrillation (AF). However, there is a paucity of information regarding the association between cancer type and risk of AF.

OBJECTIVES: This study sought to evaluate the risk of AF according to the type of cancer.

METHODS: We enrolled 816,811 patients who were diagnosed with cancer from the Korean National Health Insurance Service database between 2009 and 2016. Age- and sex-matched noncancer control subjects (1:2; n = 1,633,663) were also selected. Newly diagnosed AF was identified based on the type of cancer.

RESULTS: During a median follow-up of 4.5 years, AF was newly diagnosed in 25,356 patients with cancer (6.6 per 1,000 person-years). In multivariable Fine and Gray’s regression analysis, cancer was an independent risk factor for incident AF (adjusted subdistribution hazard ratio [aHR]: 1.63; 95% confidence interval [CI]: 1.61 to 1.66). Multiple myeloma showed a higher association with incident AF (aHR: 3.34; 95% CI: 2.98 to 3.75). Esophageal cancer showed the highest risk among solid cancers (aHR: 2.69; 95% CI: 2.45 to 2.95), and stomach cancer showed the lowest association with AF risk (aHR: 1.27; 95% CI 1.23 to 1.32).

CONCLUSIONS: Although patients with cancer were found to have a higher risk of AF, the impact on AF development varied by cancer type.

PMID:34396327 | PMC:PMC8352078 | DOI:10.1016/j.jaccao.2021.03.006

JACC CardioOncol. 2020 Aug 28;2(3):400-410. doi: 10.1016/j.jaccao.2020.07.001. eCollection 2020 Sep.

ABSTRACT

BACKGROUND: Cardiovascular disease (CVD) and cancer share many common risk factors; patients with CVD also may be at risk of developing cancer.

OBJECTIVES: The aim of this study was to derive and externally validate prediction models for the estimation of lifetime and 10-year risk for total, colorectal, and lung cancer in patients with established CVD.

METHODS: Data from patients with established CVD from the UCC-SMART cohort (N = 7,280) were used for model development, and from the CANTOS trial (N = 9,322) for model validation. Predictors were selected based on previously published cancer risk scores, clinical availability, and presence in the derivation dataset. Fine and Gray competing risk-adjusted lifetime models were developed for the outcomes total, colorectal, and lung cancer.

RESULTS: Selected predictors were age, sex, smoking, weight, height, alcohol use, antiplatelet use, diabetes, and C-reactive protein. External calibration for the 4-year risk of lung, colorectal, and total cancer was reasonable in our models, as was discrimination with C-statistics of 0.74, 0.64, and 0.63, respectively. Median predicted lifetime and 10-year risks in CANTOS were 26% (range 1% to 52%) and 13% (range 1% to 31%) for total cancer; 4% (range 0% to 13%) and 2% (range 0% to 6%) for colorectal cancer; and 5% (range 0% to 37%) and 2% (range 0% to 24%) for lung cancer.

CONCLUSIONS: Lifetime and 10-year risk of total, colorectal, and lung cancer can be estimated reasonably well in patients with established CVD with readily available clinical predictors. With additional study, these tools could be used in clinical practice to further aid in the emphasis of healthy lifestyle changes and to guide thresholds for targeted diagnostics and screening.

PMID:34396248 | PMC:PMC8352343 | DOI:10.1016/j.jaccao.2020.07.001

JACC CardioOncol. 2020 Jul 6;2(3):428-440. doi: 10.1016/j.jaccao.2020.06.001. eCollection 2020 Sep.

ABSTRACT

BACKGROUND: Many patients with cancer have a hypercoagulable state and an increased risk of developing venous thromboembolism (VTE), arterial occlusion, and pulmonary emboli. Patients with cancer may also have an increased risk of bleeding with anticoagulant treatment. Recent trials have reported that direct oral anticoagulants (DOACs) are noninferior to the low-molecular-weight heparin, dalteparin, in preventing VTE, but have a higher bleeding rate.

OBJECTIVES: This study compared the efficacy and risks of DOACs versus dalteparin in patients with cancer-related VTEs across all randomized controlled trials (RCTs).

METHODS: This study performed a systematic analysis of RCTs published in PubMed, SCOPUS, and Google Scholar from September 1, 2007 through March 31, 2020 that reported clinical outcomes of treatment with DOACs versus dalteparin in patients with cancer with acute VTE. Two investigators independently performed study selection and data extraction. Extracted data were recorded and exported to statistical software for all analyses (OpenMetaAnalyst).

RESULTS: This study included 4 randomized trials (N = 2,907). Compared with DOACs, dalteparin was associated with higher VTE recurrence (risk ratio [RR]: 1.55; 95% confidence interval [CI]: 1.19 to 2.03; p = 0.001), whereas clinically relevant nonmajor bleeding (CRNMB) was significantly less frequent with dalteparin than that with DOACs (RR: 0.68; 95% CI: 0.54 to 0.86; p = 0.001). The risk of CRNMB was largely observed with patients with gastrointestinal malignancies. No significant differences were observed in major bleeding (RR: 0.74; 95% CI: 0.52 to 1.06; p = 0.11).

CONCLUSIONS: DOACs were noninferior to dalteparin in preventing VTE recurrence in patients with cancer without a significantly increased risk of major bleeding. However, DOACs were associated with higher rates of CRNMB compared with dalteparin, primarily in patients with gastrointestinal malignancies.

PMID:34396250 | PMC:PMC8352218 | DOI:10.1016/j.jaccao.2020.06.001

Brain Commun. 2021 Jul 11;3(3):fcab156. doi: 10.1093/braincomms/fcab156. eCollection 2021.

ABSTRACT

Brain network models derived from graph theory have the potential to guide functional neurosurgery, and to improve rates of post-operative seizure freedom for patients with epilepsy. A barrier to applying these models clinically is that intracranial EEG electrode implantation strategies vary by centre, region and country, from cortical grid & strip electrodes (Electrocorticography), to purely stereotactic depth electrodes (Stereo EEG), to a mixture of both. To determine whether models derived from one type of study are broadly applicable to others, we investigate the differences in brain networks mapped by electrocorticography and stereo EEG in a cohort of patients who underwent surgery for temporal lobe epilepsy and achieved a favourable outcome. We show that networks derived from electrocorticography and stereo EEG define distinct relationships between resected and spared tissue, which may be driven by sampling bias of temporal depth electrodes in patients with predominantly cortical grids. We propose a method of correcting for the effect of internodal distance that is specific to electrode type and explore how additional methods for spatially correcting for sampling bias affect network models. Ultimately, we find that smaller surgical targets tend to have lower connectivity with respect to the surrounding network, challenging notions that abnormal connectivity in the epileptogenic zone is typically high. Our findings suggest that effectively applying computational models to localize epileptic networks requires accounting for the effects of spatial sampling, particularly when analysing both electrocorticography and stereo EEG recordings in the same cohort, and that future network studies of epilepsy surgery should also account for differences in focality between resection and ablation. We propose that these findings are broadly relevant to intracranial EEG network modelling in epilepsy and an important step in translating them clinically into patient care.

PMID:34396112 | PMC:PMC8361393 | DOI:10.1093/braincomms/fcab156

Brain Commun. 2021 Jul 16;3(3):fcab164. doi: 10.1093/braincomms/fcab164. eCollection 2021.

ABSTRACT

Quantitative volumetric brain MRI measurement is important in research applications, but translating it into patient care is challenging. We explore the incorporation of clinical automated quantitative MRI measurements in statistical models predicting outcomes of surgery for temporal lobe epilepsy. Four hundred and thirty-five patients with drug-resistant epilepsy who underwent temporal lobe surgery at Cleveland Clinic, Mayo Clinic and University of Campinas were studied. We obtained volumetric measurements from the pre-operative T1-weighted MRI using NeuroQuant, a Food and Drug Administration approved software package. We created sets of statistical models to predict the probability of complete seizure-freedom or an Engel score of I at the last follow-up. The cohort was randomly split into training and testing sets, with a ratio of 7:3. Model discrimination was assessed using the concordance statistic (C-statistic). We compared four sets of models and selected the one with the highest concordance index. Volumetric differences in pre-surgical MRI located predominantly in the frontocentral and temporal regions were associated with poorer outcomes. The addition of volumetric measurements to the model with clinical variables alone increased the model’s C-statistic from 0.58 to 0.70 (right-sided surgery) and from 0.61 to 0.66 (left-sided surgery) for complete seizure freedom and from 0.62 to 0.67 (right-sided surgery) and from 0.68 to 0.73 (left-sided surgery) for an Engel I outcome score. 57% of patients with extra-temporal abnormalities were seizure-free at last follow-up, compared to 68% of those with no such abnormalities (P-value = 0.02). Adding quantitative MRI data increases the performance of a model developed to predict post-operative seizure outcomes. The distribution of the regions of interest included in the final model supports the notion that focal epilepsies are network disorders and that subtle cortical volume loss outside the surgical site influences seizure outcome.

PMID:34396113 | PMC:PMC8361423 | DOI:10.1093/braincomms/fcab164

Mach Learn Sci Technol. 2021 Sep;2(3):035015. doi: 10.1088/2632-2153/abe6d6. Epub 2021 May 13.

ABSTRACT

Allostery is considered important in regulating protein’s activity. Drug development depends on the understanding of allosteric mechanisms, especially the identification of allosteric sites, which is a prerequisite in drug discovery and design. Many computational methods have been developed for allosteric site prediction using pocket features and protein dynamics. Here, we present an ensemble learning method, consisting of eXtreme gradient boosting (XGBoost) and graph convolutional neural network (GCNN), to predict allosteric sites. Our model can learn physical properties and topology without any prior information, and shows good performance under multiple indicators. Prediction results showed that 84.9% of allosteric pockets in the test set appeared in the top 3 positions. The PASSer: Protein Allosteric Sites Server (https://passer.smu.edu), along with a command line interface (CLI, https://github.com/smutaogroup/passerCLI) provide insights for further analysis in drug discovery.

PMID:34396127 | PMC:PMC8360383 | DOI:10.1088/2632-2153/abe6d6

Brain Commun. 2021 Jul 2;3(3):fcab145. doi: 10.1093/braincomms/fcab145. eCollection 2021.

ABSTRACT

Little is known about the characteristics and causes of early-onset cognitive impairment. Responders to the 2001 New York World Trade Center disaster represent an ageing population that was recently shown to have an excess prevalence of cognitive impairment. Neuroimaging and molecular data demonstrate that a subgroup of affected responders may have a unique form of parietal-dominant Alzheimer’s Disease. Recent neuropsychological testing and artificial intelligence approaches have emerged as methods that can be used to identify and monitor subtypes of cognitive impairment. We utilized data from World Trade Center responders participating in a health monitoring program and applied a deep learning approach to evaluate neuropsychological and neuroimaging data to generate a cortical atrophy risk score. We examined risk factors associated with the prevalence and incidence of high risk for brain atrophy in responders who are now at midlife. Training was conducted in a randomly selected two-thirds sample (N = 99) enrolled using of the results of a structural neuroimaging study. Testing accuracy was estimated for each training cycle in the remaining third subsample. After training was completed, the scoring methodology that was generated was applied to longitudinal data from 1441 World Trade Center responders. The artificial neural network provided accurate classifications of these responders in both the testing (Area Under the Receiver Operating Curve, 0.91) and validation samples (Area Under the Receiver Operating Curve, 0.87). At baseline and follow-up, responders identified as having a high risk of atrophy (n = 378) showed poorer cognitive functioning, most notably in domains that included memory, throughput, and variability as compared to their counterparts at low risk for atrophy (n = 1063). Factors associated with atrophy risk included older age [adjusted hazard ratio, 1.045 (95% confidence interval = 1.027-1.065)], increased duration of exposure at the WTC site [adjusted hazard ratio, 2.815 (1.781-4.449)], and a higher prevalence of post-traumatic stress disorder [aHR, 2.072 (1.408-3.050)]. High atrophy risk was associated with an increased risk of all-cause mortality [adjusted risk ratio, 3.19 (1.13-9.00)]. In sum, the high atrophy risk group displayed higher levels of previously identified risk factors and characteristics of cognitive impairment, including advanced age, symptoms of post-traumatic stress disorder, and prolonged duration of exposure to particulate matter. Thus, this study suggests that a high risk of brain atrophy may be accurately monitored using cognitive data.

PMID:34396105 | PMC:PMC8361422 | DOI:10.1093/braincomms/fcab145