-
Frontiers in Neurology 2024Upwards of 50% of acute ischemic stroke (AIS) survivors endure varying degrees of disability, with a recurrence rate of 17.7%. Thus, the prediction of outcomes in AIS...
BACKGROUND AND OBJECTIVES
Upwards of 50% of acute ischemic stroke (AIS) survivors endure varying degrees of disability, with a recurrence rate of 17.7%. Thus, the prediction of outcomes in AIS may be useful for treatment decisions. This study aimed to determine the applicability of a machine learning approach for forecasting early outcomes in AIS patients.
METHODS
A total of 659 patients with new-onset AIS admitted to the Department of Neurology of both the First and Second Affiliated Hospitals of Bengbu Medical University from January 2020 to October 2022 included in the study. The patient' demographic information, medical history, Trial of Org 10,172 in Acute Stroke Treatment (TOAST), National Institute of Health Stroke Scale (NIHSS) and laboratory indicators at 24 h of admission data were collected. The Modified Rankine Scale (mRS) was used to assess the 3-mouth outcome of participants' prognosis. We constructed nine machine learning models based on 18 parameters and compared their accuracies for outcome variables.
RESULTS
Feature selection through the Least Absolute Shrinkage and Selection Operator cross-validation (Lasso CV) method identified the most critical predictors for early prognosis in AIS patients as white blood cell (WBC), homocysteine (HCY), D-Dimer, baseline NIHSS, fibrinogen degradation product (FDP), and glucose (GLU). Among the nine machine learning models evaluated, the Random Forest model exhibited superior performance in the test set, achieving an Area Under the Curve (AUC) of 0.852, an accuracy rate of 0.818, a sensitivity of 0.654, a specificity of 0.945, and a recall rate of 0.900.
CONCLUSION
These findings indicate that RF models utilizing general clinical and laboratory data from the initial 24 h of admission can effectively predict the early prognosis of AIS patients.
PubMed: 38938777
DOI: 10.3389/fneur.2024.1407152 -
JMIR Bioinformatics and Biotechnology Feb 2024Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by...
BACKGROUND
Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by allowing for more complex modeling.
OBJECTIVE
We sought to improve PPH prediction and compare machine learning and traditional statistical methods.
METHODS
We developed models using the Consortium for Safe Labor data set (2002-2008) from 12 US hospitals. The primary outcome was a transfusion of blood products or PPH (estimated blood loss of ≥1000 mL). The secondary outcome was a transfusion of any blood product. Fifty antepartum and intrapartum characteristics and hospital characteristics were included. Logistic regression, support vector machines, multilayer perceptron, random forest, and gradient boosting (GB) were used to generate prediction models. The area under the receiver operating characteristic curve (ROC-AUC) and area under the precision/recall curve (PR-AUC) were used to compare performance.
RESULTS
Among 228,438 births, 5760 (3.1%) women had a postpartum hemorrhage, 5170 (2.8%) had a transfusion, and 10,344 (5.6%) met the criteria for the transfusion-PPH composite. Models predicting the transfusion-PPH composite using antepartum and intrapartum features had the best positive predictive values, with the GB machine learning model performing best overall (ROC-AUC=0.833, 95% CI 0.828-0.838; PR-AUC=0.210, 95% CI 0.201-0.220). The most predictive features in the GB model predicting the transfusion-PPH composite were the mode of delivery, oxytocin incremental dose for labor (mU/minute), intrapartum tocolytic use, presence of anesthesia nurse, and hospital type.
CONCLUSIONS
Machine learning offers higher discriminability than logistic regression in predicting PPH. The Consortium for Safe Labor data set may not be optimal for analyzing risk due to strong subgroup effects, which decreases accuracy and limits generalizability.
PubMed: 38935950
DOI: 10.2196/52059 -
Brain Sciences Jun 2024Porcine Liver Decomposition Product (PLDP) was obtained by treating pig liver homogenate with protease and filling it into capsules. We have already confirmed from three...
Porcine Liver Decomposition Product (PLDP) was obtained by treating pig liver homogenate with protease and filling it into capsules. We have already confirmed from three clinical trials that PLDP enhances visual memory and delays memory recall, and we believe that its activity is due to various phospholipids, including phosphatidylcholine (PC). In this study, we clinically evaluated PLDP for depressive symptoms caused by a decline in cognitive function. This clinical trial was conducted using the Revised Hasegawa Dementia Scale (HDS-R). The HDS-R (maximum score is 30 points) is a test similar to the Mini-Mental State Examination (MMSE), which is commonly used in Japan. Dementia is suspected if the score falls below 20 on the HDS-R. Additionally, in a previous clinical trial, there was no change in scores in the placebo group after three doses of the HDS-R. In order to clearly confirm the effectiveness of PLDP, this study was conducted under stricter conditions (HDS-R points of 15 to 23) than previous clinical trials (all participants had scores of 20 or higher). Therefore, from ethical considerations, a clinical trial was conducted using the scores before PLDP administration as a control. In this study, PLDP was administered orally at 4 capsules per day, and the HDS-R was confirmed 2 and 4 weeks after administration. A significant increase in HDS-R scores was observed at 2 and 4 weeks after PLDP administration. Additionally, regarding each item of the HDS-R, PLDP significantly increased 2 and 4 weeks after oral administration for the question items assessing delayed recall, and the question item assessing verbal fluency tasks was recognized. From the above results, we confirmed the reproducibility of the effect of PLDP in improving the delayed recall of verbal memories. Furthermore, increasing scores on verbal fluency tasks suggest that PLDP may enhance frontal lobe function and prevent or improve depressive symptoms. The effects observed in this study may differ from the mechanisms of action of existing antidepressants, and we believe that this may lead to the discovery of new antidepressants.
PubMed: 38928586
DOI: 10.3390/brainsci14060586 -
Appetite Jun 2024This study investigates implicit and explicit attitudes toward products before and beyond the best-before date (BBD) using an Implicit Association Test and an online...
This study investigates implicit and explicit attitudes toward products before and beyond the best-before date (BBD) using an Implicit Association Test and an online questionnaire. Moreover, we test whether consumer perception of and behavior toward products beyond the BBD can be manipulated using a priming task. We use a three-group between-subjects design where respondents had to recall either a frugal, a wasteful, or an unrelated behavior. Results show that consumers have negative implicit associations with products beyond the BBD. Reduced health and safety perceptions, consumers' strategies to determine edibility, and general risk perception of products beyond the BBD predict consumption of these products. While recalling a frugal behavior does not have significant effects, recalling a wasteful behavior prior to evaluating products beyond the BBD leads to a decrease in the perceived safety and healthfulness of these products.
PubMed: 38876149
DOI: 10.1016/j.appet.2024.107556 -
Frontiers in Aging Neuroscience 2024The lack of cognitive awareness, anosognosia, is a clinical deficit in Alzheimer's disease (AD) dementia. However, an increased awareness of cognitive function,...
INTRODUCTION
The lack of cognitive awareness, anosognosia, is a clinical deficit in Alzheimer's disease (AD) dementia. However, an increased awareness of cognitive function, hypernosognosia, may serve as a marker in the preclinical stage. Subjective cognitive decline (SCD) might correspond to the initial symptom in the dynamic trajectory of awareness, but SCD might be absent along with low awareness of actual cognitive performance in the preclinical stage. We hypothesized that distinct meta-cognitive profiles, both hypernosognosia and anosognosia, might be identified in preclinical-AD. This research evaluated the association between cerebrospinal fluid (CSF) AD biomarkers and the awareness of episodic memory, further exploring dyadic (participant-partner) SCD reports, in the preclinical Alzheimer's continuum.
METHODS
We analyzed 314 cognitively unimpaired (CU) middle-aged individuals (mean age: 60, SD: 4) from the ALFA+ cohort study. Episodic memory was evaluated with the delayed recall from the Memory Binding Test (MBT). Awareness of episodic memory, meta-memory, was defined as the normalized discrepancy between objective and subjective performance. SCD was defined using self-report, and dyadic SCD profiles incorporated the study partner's report using parallel SCD-Questionnaires. The relationship between CSF Aβ42/40 and CSF p-tau181 with meta-memory was evaluated with multivariable regression models. The role of SCD and the dyadic contingency was explored with the corresponding stratified analysis.
RESULTS
CSF Aβ42/40 was non-linearly associated with meta-memory, showing an increased awareness up to Aβ-positivity and a decreased awareness beyond this threshold. In the non-SCD subset, the non-linear association between CSF Aβ42/40 and meta-memory persisted. In the SCD subset, higher Aβ-pathology was linearly associated with increased awareness. Individuals presenting only study partner's SCD, defined as unaware decliners, exhibited higher levels of CSF p-tau181 correlated with lower meta-memory performance.
DISCUSSION
These results suggested that distinct meta-cognitive profiles can be identified in preclinical-AD. While most individuals might experience an increased awareness associated with the entrance in the AD continuum, hypernosognosia, some might be already losing insight and stepping into the anosognosic trajectory. This research reinforced that an early anosognosic profile, although at increased risk of AD-related decline, might be currently overlooked considering actual diagnostic criteria, and therefore its medical attention delayed.
PubMed: 38872632
DOI: 10.3389/fnagi.2024.1394460 -
Critical Reviews in Toxicology Jun 2024Over the past several decades, there have been many epidemiology studies on talc and cancer published in the scientific literature, and several reviews and meta-analyses... (Review)
Review
Over the past several decades, there have been many epidemiology studies on talc and cancer published in the scientific literature, and several reviews and meta-analyses of talc and respiratory, female reproductive, and stomach cancers, specifically. To help provide a resource for the evaluation of talc as a potential human carcinogen, we applied a consistent set of examination methods and criteria for all epidemiology studies that examined the association between talc exposure (by various routes) and cancers (of various types). We identified 30 cohort, 35 case-control, and 12 pooled studies that evaluated occupational, medicinal, and personal-care product talc exposure and cancers of the respiratory system, the female reproductive tract, the gastrointestinal tract, the urinary system, the lymphohematopoietic system, the prostate, male genital organs, and the central nervous system, as well as skin, eye, bone, connective tissue, peritoneal, and breast cancers. We tabulated study characteristics, quality, and results in a systematic manner, and evaluated all cancer types for which studies of at least three unique populations were available in a narrative review. We focused on study quality aspects most likely to impact the interpretation of results. We found that only one study, of medicinal talc use, evaluated direct exposure measurements for any individuals, though some used semi-quantitative exposure metrics, and few studies adequately assessed potential confounders. The only consistent associations were with ovarian cancer in case-control studies and these associations were likely impacted by recall and potentially other biases. This systematic review indicates that epidemiology studies do not support a causal association between occupational, medicinal, or personal talc exposure and any cancer in humans.
PubMed: 38868996
DOI: 10.1080/10408444.2024.2351081 -
Heliyon Jun 2024The aim of this study was to investigate the effects of temporal instability and possible heterogeneity on pedestrian accident severity, 48786 accident data from 2018 to...
The aim of this study was to investigate the effects of temporal instability and possible heterogeneity on pedestrian accident severity, 48786 accident data from 2018 to 2021 in the UK STATS database were used as the study object, and accident severity was used as the dependent variable, and 49 accident characteristics were selected as independent variables from 6 characteristics of accident pedestrian, driver, vehicle, road, environment and time to construct the pedestrian accident mean heterogeneity random-parameter logit model and examined its temporal stability. The results of model estimation and likelihood ratio tests indicate that the variables affecting pedestrian injury severity are highly variable and not stable over the years. And further demonstrates the potential of models that address unobserved heterogeneity for significant relationships in pedestrian accident severity analyses.
PubMed: 38867994
DOI: 10.1016/j.heliyon.2024.e32013 -
The Lancet. Oncology Jun 2024
Topics: United States Food and Drug Administration; United States; China; Humans; Safety-Based Drug Withdrawals; Drug Approval
PubMed: 38821082
DOI: 10.1016/S1470-2045(24)00025-1 -
Risk Analysis : An Official Publication... May 2024In today's highly competitive business environment, firms strive to maximize profitability by minimizing or eliminating disruptions and failures to maintain a...
In today's highly competitive business environment, firms strive to maximize profitability by minimizing or eliminating disruptions and failures to maintain a competitive edge. This study focuses on evaluating risks in a hydraulic pump factory as a means to achieve sustainable growth. To accomplish this, a team of experts was formed to identify potential errors, utilizing a combination of risk priority number criteria weighted by Fuzzy Shannon's entropy and a fusion of multi-criteria decision-making and failure mode and effects analysis for evaluating and ranking failures. Moreover, the study emphasizes the importance of considering the interaction among risk assessment indicators, the inclusion of cost of failure, and modeling under fuzzy uncertainty circumstances, as they have a notable impact on the final ranking of failures to be processed for risk mitigation action planning. This research brings a new dimension to enhance the overall effectiveness of risk assessment by aggregation, as evidenced by a novel use of data classification in machine learning and correlation in statistics. The findings indicate that the aggregated ranking data series is best matched and most influenced by the weighted aggregated sum product assessment method, with the highest rate of recall and precision accomplished.
PubMed: 38818965
DOI: 10.1111/risa.14338 -
Frontiers in Medicine 2024Human Immunodeficiency Virus (HIV) remains a global health challenge, and novel approaches to improve HIV control are significantly important. The cell and gene therapy...
Human Immunodeficiency Virus (HIV) remains a global health challenge, and novel approaches to improve HIV control are significantly important. The cell and gene therapy product AGT103-T was previously evaluated (NCT04561258) for safety, immunogenicity, and persistence in seven patients for up to 180 days post infusion. In this study, we sought to investigate the impact of AGT103-T treatment upon analytical treatment interruptions (ATIs). Six patients previously infused with AGT103-T were enrolled into an ATI study (NCT05540964), wherein they suspended their antiretroviral therapy (ART) until their viral load reached 100,000 copies/mL in two successive visits, or their CD4 count was reduced to below 300 cells/μL. During the ATI, all patients experienced viral rebound followed by a notable expansion in HIV specific immune responses. The participants demonstrated up to a five-fold increase in total CD8 counts over baseline approximately 1-2 weeks followed by the peak viremia. This coincided with a rise in HIV-specific CD8 T cells, which was attributed to the increase in antigen availability and memory recall. Thus, the protocol was amended to include a second ATI with the first ATI serving as an "auto-vaccination." Four patients participated in a second ATI. During the second ATI, the Gag-specific CD8 T cells were either maintained or rose in response to viral rebound and the peak viremia was substantially decreased. The patients reached a viral set point ranging from 7,000 copies/mL to 25,000 copies/mL. Upon resuming ART, all participants achieved viral control more rapidly than during the first ATI, with CD4 counts remaining within 10% of baseline measurements and without any serious adverse events or evidence of drug resistance. In summary, the rise in CD8 counts and the viral suppression observed in 100% of the study participants are novel observations demonstrating that AGT103-T gene therapy when combined with multiple ATIs, is a safe and effective approach for achieving viral control, with viral setpoints consistently below 25,000 copies/mL and relatively stable CD4 T cell counts. We conclude that HIV cure-oriented cell and gene therapy trials should include ATI and may benefit from designs that include multiple ATIs when induction of CD8 T cells is required to establish viral control.
PubMed: 38808136
DOI: 10.3389/fmed.2024.1342476