Statistical Significance Tests Research Articles

Why and How to Replace Statistical Significance Tests with Better Methods to Evaluate Hypotheses

Why and How to Replace Statistical Significance Tests with Better Methods to Evaluate Hypotheses

Pre-morbid frailty is associated with poor outcome after thrombolysis in older patients with ST-elevation Myocardial Infarction

Introduction: In recent years, the association of frailty has been established with a poor outcome after percutaneous intervention following an acute cardiovascular event. However, a larger proportion of the world population is unable to access the prohibitively expensive tertiary cardiac care and receives the more readily available, affordable and acceptable thrombolytic therapy in emergency situations. The current study was designed to explore the association of pre-morbid frailty with immediate and short-term outcome of thrombolysis in older subjects presenting with ST-elevation myocardial infarction to our hospital. Methods: This was an observational prospective cohort study completed between 2015 and 2017 at a tertiary care teaching hospital in Delhi. Patients older than 60 years who presented to the hospital with ST-elevation myocardial infarction and underwent successful thrombolysis were included for the study. Complications such as bleeding, reperfusion reactions and allergic reactions were recorded whenever these were observed. In addition, complications such as re-infarction, stroke, cardiac arrest, cardiogenic shock and death were also recorded. In addition, a short-term outcome in terms of discharge, death, recovery was noted. A pre-morbid frailty score was historically computed with inputs from the patients and their primary caretakers using a deficit count approach on a pre-defined list of fifty self-reported deficits. The descriptive statistical analysis comprised of calculating means (standard deviations) and proportions (frequencies and percentages). The association of premorbid deficit score with thrombolysis success and other variables was tested by calculating mean ranks, and Mann Whitney U test was used as a statistical test of significance. Spearman correlation coefficient was used to determine the association between frailty and complications and morbidity and mortality indicators. Univariable logistic regression models were used to evaluate independent variables associated with outcome of thrombolysis to further explore the association between frailty and outcome. Independent variables found significantly associated with poor outcome were entered into a multivariable logistic regression model (forward) in addition to those considered scientifically relevant. Results: In the present study, we found a significant association between a higher pre-morbid frailty status assessed by an interview-based deficit count score and poorer outcome of thrombolysis. Every unit increment in the frailty deficit count score on a scale of 50 points increased the odds of failed thrombolysis by 1.14 times. Frailty was also associated with an increased risk of reperfusion arrhythmias and cardiac arrest following thrombolysis. Additionally, we noted that higher the deficit score, lesser the resolution of ST segment on ECG, 90 minutes following thrombolysis. Conclusions: Our study indicates that frailty determined by a premorbid count of health deficits is associated with the outcome of thrombolysis following myocardial infarction in older patients. The patients with greater count of deficits have a higher chance of failure. Our findings will help informed decision-making while managing older patients presenting with myocardial infarction and in-turn improve morbidity and mortality.

A Discrete JAYA Algorithm Based on Reinforcement Learning and Simulated Annealing for the Traveling Salesman Problem

The JAYA algorithm is a population-based meta-heuristic algorithm proposed in recent years which has been proved to be suitable for solving global optimization and engineering optimization problems because of its simplicity, easy implementation, and guiding characteristic of striving for the best and avoiding the worst. In this study, an improved discrete JAYA algorithm based on reinforcement learning and simulated annealing (QSA-DJAYA) is proposed to solve the well-known traveling salesman problem in combinatorial optimization. More specially, firstly, the basic Q-learning algorithm in reinforcement learning is embedded into the proposed algorithm such that it can choose the most promising transformation operator for the current state to update the solution. Secondly, in order to balance the exploration and exploitation capabilities of the QSA-DJAYA algorithm, the Metropolis acceptance criterion of the simulated annealing algorithm is introduced to determine whether to accept candidate solutions. Thirdly, 3-opt is applied to the best solution of the current iteration at a certain frequency to improve the efficiency of the algorithm. Finally, to evaluate the performance of the QSA-DJAYA algorithm, it has been tested on 21 benchmark datasets taken from TSPLIB and compared with other competitive algorithms in two groups of comparative experiments. The experimental and the statistical significance test results show that the QSA-DJAYA algorithm achieves significantly better results in most instances.

Knowledge and Attitude of Specialist Hospital Health Care Workers to Dental Services in Benin City.

Objective: To examine the knowledge and attitude to dental services among Health Care Workers in a specialist hospital setting.
 Methods: This descriptive study was carried out among all cadres of workers in Edo Specialist Hospital (ESH); a government-owned secondary health facility located in Benin City. A structured online questionnaire created using Google forms was used to collect data anonymously from participants. The online form extracted information on demographic characteristics, oral health awareness, pattern of dental visits, and utilization of dental services at Edo Specialist Hospital. The data obtained were analysed using SPSS version 26.0 for frequency distribution and cross tabulation. Test for statistical significance was done using chi-square statistics.
 Results: Majority of the participants had never visited a dentist before (59, 54.6%). Majority (48, 44.4%) of the respondents reported that they had not seen the need to visit. Among the respondents, the commonest reasons for previous dental visits were toothache (15, 13.9%) and Stains and deposits on the teeth (13, 12.0%). Majority (76, 70.4%) of respondents had a good or fair understanding of the causes of dental caries. All participants (108,100%) were aware that there was a dental clinic at Edo Specialist Hospital (ESH). However, majority (86, 79.6%) had never visited it. Among the respondents, the commonest reason given for not attending the dental clinic at ESH was that they never saw the need to visit (54, 50.0%). On the other hand, the commonest reasons given for visiting the dental clinic at ESH were toothache (12, 11.2%) and Stains and deposits on the teeth (5, 4.7%). There was a significant relationship between the Staff cadre and previous dental visits.
 Conclusion: Knowledge of dental care and service utilization was poor. Clinically indicated dental visit was seen among healthcare workers in a specialist healthcare facility
 
 dental clinic

Intentional deep overfit learning for patient-specific dose predictions in adaptive radiotherapy.

The framework of adaptive radiation therapy (ART) was crafted to address the underlying sources of intra-patient variation that were observed throughout numerous patients' radiation sessions. ART seeks to minimize the consequential dosimetric uncertainty resulting from this daily variation, commonly through treatment planning re-optimization. Re-optimization typically consists of manual evaluation and modification of previously utilized optimization criteria. Ideally, frequent treatment plan adaptation through re-optimization on each day's computed tomography (CT) scan may improve dosimetric accuracy and minimize dose delivered to organs at risk (OARs) as the planning target volume (PTV) changes throughout the course of treatment. Re-optimization in its current form is time-consuming and inefficient. In response to this ART bottleneck, we propose a deep learning based adaptive dose prediction model that utilizes a head and neck (H&N) patient's initial planning data to fine-tune a previously trained population model towards a patient-specific model. Our fine-tuned, patient-specific (FT-PS) model, which is trained using the intentional deep overfit learning (IDOL) method, may enable clinicians and treatment planners to rapidly evaluate relevant dosimetric changes daily and re-optimize accordingly. An adaptive population (AP) model was trained using adaptive data from 33 patients. Separately, 10 patients were selected for training FT-PS models. The previously trained AP model was utilized as the base model weights prior to re-initializing model training for each FT-PS model. Ten FT-PS models were separately trained by fine-tuning the previous model weights based on each respective patient's initial treatment plan. From these 10 patients, 26 ART treatment plans were withheld from training as the test dataset for retrospective evaluation of dose prediction performance between the AP and FT-PS models. Each AP and FT-PS dose prediction was compared against the ground truth dose distribution as originally generated during the patient's course of treatment. Mean absolute percent error (MAPE) evaluated the dose differences between a model's prediction and the ground truth. MAPE was calculated within the 10% isodose volume region of interest for each of the AP and FT-PS models dose predictions and averaged across all test adaptive sessions, yielding 5.759% and 3.747% respectively. MAPE differences were compared between AP and FT-PS models across each test session in a test of statistical significance. The differences were statistically significant in a paired t-test with two-tailed p-value equal to and 95% confidence interval (CI) equal to [-2.483, -1.542]. Furthermore, MAPE was calculated using each individually segmented structure as an ROI. Nineteen of 24 structures demonstrated statistically significant differences between the AP and FT-PS models. We utilized the IDOL method to fine-tune a population-based dose prediction model into an adaptive, patient-specific model. The averaged MAPE across the test dataset was 5.759% for the population-based model versus 3.747% for the fine-tuned, patient-specific model, and the difference in MAPE between models was found to be statistically significant. Our work demonstrates the feasibility of patient-specific models in adaptive radiotherapy, and offers unique clinical benefit by utilizing initial planning data that contains the physician's treatment intent.

A Framework for Utilizing Permutational Multiple Analysis of Variance as a Precursor for Nonparametric Statistical Learning with Cyber Network Data

INTRODUCTION: Although scientific hypothesis testing methodologies are well established, their application to falsifiable hypothesis testing for assessing causal relationships potentially identified by machine learning and artificial intelligence models is rare due to the primarily nonparametric statistical nature of these systems.OBJECTIVES: The primary objective of this study is to demonstrate the potential for applying nonparametric statistical tests to a mixed qualitative and quantitative cyber network dataset as a method to pre-assess the feasibility of applying forms of statistical hypothesis testing before a machine learning algorithm models the data.METHODS: A mixture of permuted analysis of variance models augmented by the use of transformed non-Euclidean multivariate distances between curated dependent variable classes produced this research data. Quasi-experimental data from an enclosed laboratory environment utilizing a monitored, locally unrestricted network that introduced known Internet of Things (IoT) malware software supplied network flow events.RESULTS: A PERMANOVA model was executed against 62,000 records of the network flow observations, using Euclidean distance measurements with variable-dependent relationship ordering, using terms added sequentially (first to last) in the order encountered in the raw network flow dataset, using 200 permutations. This precursor test resulted in a p-value for the PERMANOVA model that incorporated terms added sequentially of 0.02985, providing an F value of 0.00017 with which to determine the ratio of explained to unexplained variance. Utilizing an analysis of the F values for all of the residuals, we show 29,998 degrees of freedom with a residual F model score of 0.99983, indicating that there is a strong proportion of explained to unexplained variance across all of the independent variables contained in the model. The model is thus statistically significant with a p-value below the alpha test statistic of 0.05.CONCLUSION: This research has demonstrated that it is possible to apply tests of falsifiability that incorporate reproducible methods into the quasi-experiment design and apply this to the field of machine learning. Applied to AI/ML (artificial intelligence/machine learning) models, this pre-assessment methodology supports the appropriateness of cyber network flow datasets in which a final test of statistical significance would be required. The authors believe that this represents a substantially useful precursor assessment stage for the suitability and reliability of the utilization of any nonparametric statistical learning algorithms applied to cyber network data predictive analytics.

Concurrent chemotherapy with partial breast irradiation in triple negative breast cancer patients may improve disease control compared with sequential therapy.

To report outcomes on a subset of patients with triple negative breast cancer (TNBC) treated on prospective trials with post-lumpectomy partial breast irradiation and concurrent chemotherapy (PBICC) and compare them to a retrospectively assessed similar cohort treated with whole breast irradiation after adjuvant chemotherapy (WBIaC). Women with T1-2, N0-1 invasive breast cancer with ≥ 2mm lumpectomy margins were offered therapy on one of two PBICC trials. PBI consisted of 40.5 Gy in 15 daily 2.7 Gy fractions delivered concurrently with the first 2 cycles of adjuvant chemotherapy. The comparison cohort received WBI to a median dose of 60.7 Gy, (including boost, range 42.5 - 66 Gy), after completion of non-concurrent, adjuvant chemotherapy. We evaluated disease-free survival (DFS), and local/loco-regional/distant recurrence-free survival (RFS). We compared survival rates using Kaplan-Meier curves and log-rank test of statistical significance. Nineteen patients with TNBC were treated with PBICC on prospective protocol, and 49 received WBIaC. At a median follow-up of 35.5 months (range 4.8-71.9), we observed no deaths in the PBICC cohort and 2 deaths in the WBIaC cohort (one from disease recurrence). With a median time of 23.4 (range 4.8 to 47) months, there were 7 recurrences (1 nodal, 4 local, 4 distant), all in the WBIaC group. At 5 years, there was a trend towards increased local RFS (100% vs. 85.4%, p=0.17) and loco-regional RFS (100% vs. 83.5, p=0.13) favoring the PBICC cohort. There was no significant difference in distant RFS between the two groups (100% vs. 94.4%, p=0.36). Five-year DFS was 100% with PBICC vs.78.9% (95% CI: 63.2 to 94.6%, p=0.08) with WBIaC. This study suggests that PBICC may offer similar and possibly better outcomes in patients with TNBC compared to a retrospective cohort treated with WBIaC. This observation is hypothesis-generating for prospective trials.

A knowledge graph–GCN–community detection integrated model for large-scale stock price prediction

Owing to uncertainty in the stock market, stock price prediction has always been a challenging research hotspot. In recent years, many stock prediction methods have used stock price series and technical indicators as inputs and the time series algorithm to predict, but they often ignore the influence of deeper factors such as the situation of the stock company and current situation of the stock industry. In addition, most of them predict based on small-scale stock datasets with limited characteristics and have certain defects such as bias, poor stability of prediction results, and lack of statistical significance tests on experimental results. To solve these problems, we propose a new method for stock price prediction based on knowledge graph (KG) and graph convolution neural network (GCN) models. First, stock KG is constructed, and the semantic relationships between stocks are described in the form of triples. Second, the correlations between stocks are quantified by fully utilizing their explicit/implicit relationships in the KG. Third, K-means, community detection (CD), and GCNs are merged to obtain accurate clustering results for similar stocks. Finally, the historical prices of similar stocks are used as the input characteristics of the time series models to predict stock price trends. We collect 4684 A-share market stocks in China from 2013 to 2019 and predicted the stock price trends for 762 of them. The experimental results and significance test show that the proposed method achieve the best accuracy, precision, and F1-measure on large-scale stock datasets and have the best stability, proving that the overall prediction effect outperforms that by state-of-the-art methods.

Usefulness and limitations of convergent cross sorting and continuity scaling methods for their application in simulated and real-world time series

Causality detection methods are valuable tools for detecting causal links in complex systems. The efficiency of continuity scaling (CS) and the convergent cross sorting (CSS) methods to detect causality was analysed. Usefulness and limitations of both methods in their application to simulated and real-world time series was explored under different scenarios. We find that CS is more robust and efficient than the CSS method for all simulated systems, even when increasing noise levels were considered. Both methods were not able to infer causality when time series with a marked difference in their main frequencies were analysed. Minimum time-series length required for the detection of a causal link depends on intrinsic system dynamics and on the method selected to detect it. Using simulated time series, only the CS method was capable to detect bidirectional causality. Causality detection, using the CS method, should at least include: (i) causality strength convergence analysis, (ii) statistical tests of significance, (iii) time-series standardization, and (iv) causality strength ratios as a strength indicator of relative causality between systems. Causality cannot be detected by either method in simulated time series that exhibit generalized synchronization.

Evaluating sustainable development practices in a zero‑carbon university campus: A pre and post-COVID-19 pandemic recovery study

This paper aims to understand the critical areas for sustainable behavioural change on a university campus in order to achieve the net zero‑carbon ambition pre- and post-COVID-19 pandemic recovery. For this purpose, the current empirical study is the first attempt to statistically examine the whole campus as a system, considering staff and student views (campus users), by developing an index measuring propensity for sustainable behavioural change to achieve a net zero‑carbon campus. The novelty of this study is based on the following: (i) The impact of environmental sustainability measures due to COVID-19 is examined on three themes: physical activity routines on a daily basis, research, and teaching and learning, and (ii) the index that is compatible with quantifying the behavioural change. A multi-indicator questionnaire is used to collect empirical data for each of the three themes. Based on 630 responses, descriptive statistical analysis, normality tests, significance tests, and t-tests are performed using statistical and graphical software, and conducting uncertainty and sensitivity analyses on this quantitative data. The study found that 95 % of campus users agreed to use reusable materials on campus, and 74 % were willing to pay more for sustainable products. In addition, 88 % agreed to seek alternative and sustainable transportation for short research trips, while 71 % prioritised online conferences and project meetings for sustainable hybrid working. Moreover, the COVID-19 pandemic had a negative impact on the frequency of reusable material usage among campus users, as indicated by the index analysis, which showed a significant decrease from 0.8536 to 0.3921. The statistical findings show that campus users are more likely to initiate and endorse environmental sustainability measures in research and daily life than in teaching and learning, and there is no difference in their propensity for change. This research provides net zero‑carbon sustainability researchers and leaders with a crucial baseline for scientific advances in the sustainability field. It also offers practical guidelines for implementing a net zero‑carbon campus, engaging users from various disciplines, which has important implications and contributions.

Contralateral breast cancer risk in patients with breast cancer and a germline-BRCA1/2 pathogenic variant undergoing radiation.

Radiation-induced secondary breast cancer (BC) may be a concern after radiation therapy (RT) for primary breast cancer (PBC), especially in young patients with germline (g)BRCA-associated BC who already have high contralateral BC (CBC) risk and potentially increased genetic susceptibility to radiation. We sought to investigate whether adjuvant RT for PBC increases the risk of CBC in patients with gBRCA1/2-associated BC. The gBRCA1/2 pathogenic variant carriers diagnosed with PBC were selected from the prospective International BRCA1/2 Carrier Cohort Study. We used multivariable Cox proportional hazards models to investigate the association between RT (yes vs no) and CBC risk. We further stratified for BRCA status and age at PBC diagnosis (<40 and >40 years). Statistical significance tests were 2-sided. Of 3602 eligible patients, 2297 (64%) received adjuvant RT. Median follow-up was 9.6 years. The RT group had more patients with stage III PBC than the non-RT group (15% vs 3%, P < .001), received chemotherapy more often (81% vs 70%, P < .001), and received endocrine therapy more often (50% vs 35%, P < .001). The RT group had an increased CBC risk compared with the non-RT group (adjusted hazard ratio [HR] = 1.44; 95% confidence interval [CI] = 1.12 to 1.86). Statistical significance was observed in gBRCA2 (HR = 1.77; 95% CI = 1.13 to 2.77) but not in gBRCA1 pathogenic variant carriers (HR = 1.29; 95% CI = 0.93 to 1.77; P = .39 for interaction). In the combined gBRCA1/2 group, patients irradiated when they were younger than or older than 40 years of age at PBC diagnosis showed similar risks (HR = 1.38; 95% CI = 0.93 to 2.04 and HR = 1.56; 95% CI = 1.11 to 2.19, respectively). RT regimens minimizing contralateral breast dose should be considered in gBRCA1/2 pathogenic variant carriers.

Forecast of China’s natural gas demand based on the double-logarithmic model with stepwise regression method

ABSTRACT In the current world’s energy system, natural gas, as a clean energy source, is gradually becoming the main energy source. However, the volume of natural gas demand could be able to be influenced by numerous factors, in order to forecast the future trend of the requirement more precisely, it is necessary to further explore effective driving factors influencing the volume of demand and construct a brand new function model of forecasting natural gas demand. In this study, the relative gray relational degree is used to quantitatively describe the correlation among variables, diagnosing whether there are serious multicollinearity problems among these factors. According to the principle of correlation degree: first and then small, a stepwise regression analysis is adopted to refine the analysis of factors influencing natural gas demand. On the basis of statistical significance testing, in-depth studying is conducted on the effective influencing factors of natural gas demand. This helps to develop a more accurate prediction model. In this study, we find that: (1) China’s energy consumption structure and economic development influence its natural gas demand. (2) The stepwise regression double logarithmic demand function model based on the effective drivers has good forecasting performance. Researchers can use it to forecast the natural gas demand for medium- and long-term in different regions, and the forecasting results can be considered an important reference basis for scientific natural gas policy formulation. (3) Over the coming 15 years, Natural gas demand in China will continue to grow. It will reach about 6910 × 10 8 m 3 by 2035. It is concluded that the development of China’s natural gas demand would be promoted in an increasing scale trend by striving to promote China’s high-quality economic development, carefully building a new pattern of high-quality energy development, and increasing the proportion of natural gas consumption.

An interactive ACO enriched with an eclectic multi-criteria ordinal classifier to address many-objective optimisation problems

Despite the vast research on many-objective optimisation problems, the presence of many objective functions is still a challenge worthy of further study. A way to treat this kind of problem is to incorporate the preferences of the decision maker (DM) into the optimisation process. In this paper, we introduce an interactive ant colony optimisation combined with an ordinal classification method in which classes are described by characteristic profiles. Through several interactions, the DM is supposed to identify some representative solutions of the classes ‘satisfactory’ and ‘dissatisfactory,’ which are used to initialise an ordinal classifier that increases the selective pressure by discriminating in favour of the ‘satisfactory’ class. This method can work with any either asymmetric or symmetric binary preference relation, a feature that confers a very wide generality. As another advantage, the interaction with the DM has minimal cognitive demands, which is an advisable feature for any approach based on interaction. Although the preference model is quite general, the proposal was tested using an eclectic model which combines compensatory preferences, veto conditions, and interval numbers to handle imprecise values; those preferences are aggregated in an asymmetric preference relation. Our approach performs particularly well in 10-objective problems according to the standards in the state-of-the-art literature. Numerical results and tests for statistical significance on the DTLZ and WFG test suites support this claim.

HiT-MST: Dynamic facial expression recognition with hierarchical transformers and multi-scale spatiotemporal aggregation

Facial expression recognition rarely explores complex spatiotemporal dependencies among facial regions at different scales. This paper proposes a transformer-based three-layer hierarchical architecture that incorporates multi-scale spatiotemporal aggregation for dynamic facial expression recognition. The hierarchical structure consists of bottom-to-top layers, each comprising transformer encoders with local self-attention mechanisms. These encoders gradually expand their receptive fields through hierarchical spatiotemporal aggregation, enabling the modeling of spatiotemporal context dependencies among facial regions at different scales and across consecutive frames. Consequently, the bottom-to-top layers correspond to learning the fine-grained, coarse-grained, and global facial representations. To evaluate the performance of our proposed framework, we conducted extensive experiments on four public datasets. The comparison results demonstrate that our proposed framework outperforms the state-of-the-art, with accuracies of 79.09%, 62.19%, 64.85%, and 59.79% on the RML, eNTERFACE'05, RAVDESS, and AFEW datasets, respectively. Ablation experiments, statistical significance tests, and visualization analyses indicate that the proposed framework successfully learns emotional-salient facial representations.

Analyzing differences of highway lane-changing behavior using vehicle trajectory data

Analyzing fine-resolution lane-changing behavior is of great significance in the traffic flow modeling and safety assessment. The fact that lane-changing behavior varies over different environment and operation factors poses great challenges for lane-changing behavior modeling and analysis. To explore the differences of highway lane-changing behavior in complicated scenarios, the analysis of this study stems from a large volume of lane-changing trajectories (i.e., 6506 lane-changing trajectories) collected from the Highway Drone (HighD) dataset. In real-world scenarios, to identify and extract lane-changing start and end points of lane-changing behavior from trajectories, we present a fusion method by using frame interval and lateral displacement variation in trajectory data, which can be calibrated by the visualization. The empirical results show that: (a) the relative error between the extracted lane-changing time and real one is less than 4%; (b) the lane-changing time is ranged from 2.88 s to 7.32 s, while the lane-changing speed is ranged from 18.83 m/s to 43.30 m/s. For the difference analysis, we use the tests of statistical significance and heatmaps to analyze the differences of lane-changing behavior under complicated scenarios that involve different lane numbers, lane-changing directions, vehicle types, and speed limit condition. The results demonstrate that the lane-changing behavior varies over different scenarios significantly. Overall, the systematical analysis of lane-changing behavior in this study provides insight into the microscopic traffic flow modeling.

Using machine learning to characterize lung cancer microenvironment and the development of a model to predict the presence of similar microenvironment in other cancers.

2634 Background: Poor response to immune checkpoint inhibitors (ICI) in colorectal cancer (CRC) is believed to be due to lack of immune suppressive tumor microenvironment (TME). In contrast, lung cancer TME is believed to be significantly more immunologically active and responsible for the relative success of ICI in lung cancer. We evaluated the TME in lung cancer and CRC using 43 immune biomarkers quantified using RNA sequencing and developed a model to classify TME into immunologically active (similar to lung cancer) vs inactive (similar to colorectal). These 43 immune biomarkers included B- and T-cell markers, cytokines and chemokines. Methods: RNA was extracted from FFPE samples from 707 patients with lung cancer, 227 patients with CRC, 131 patients with breast cancer, 111 patients with ovarian cancer, and 72 patients with pancreatic cancer. The expression levels of the 42 immunological markers were quantified using next generation sequencing (NGS) as a part of larger targeted RNA sequencing panel of 1408 genes. Using a machine learning algorithm, we first selected the relative genes that distinguish between two classes using two criteria: performance of each gene with K-fold cross-validation (K=12) and second based on stability measure using statistical significance tests. The selected genes were then used to predict one class from the other using random forest classifier. Samples were divided into a training set (67%) and testing set (33%). Results: A Bayesian-based algorithm selected the expression of 20 genes that were significantly relevant in differentiating between immunologically active and inactive TME. Using these 20 genes in Random Forest model, we can distinguish between lung and CRC with AUC of 0.997 (95% CI: 0.992-1.00) in the training set and AUC of 0.923 (95% CI: 0.880-0.966) in the testing set. Testing 131 breast cancer samples showed 23 (18%) with TME that can be classified as immunologically active. Of 111 ovarian samples 13 (12%) showed immunologically active TME and of 72 pancreatic samples, 17 (24%) showed microenvironment classified as active. The 20 genes that were adequate to distinguish between TME active vs inactive are: CD74, FCGBP, IL1R1, CD44, CD274, FCGR2B, IL21R, IL1RAP, IL7R, CD79A, CCL2, CYFIP2, CD19, IL2RA, CD8A, CD79B, ID1, CD22, FZD10, and IL1B, listed in order of their importance. Conclusions: This data shows that lung cancer TME is significantly different from that of CRC. Only 20 immune biomarkers adequate to distinguish between the two TME. The relevant biomarkers included CD274 (PD-L1) as well as one marker for T-cells (CD8A) but three markers for B-cells (CD19, CD22 and CD79B). This suggests that B-cells play a significant role in immunologically active TME and should be explored further as biomarkers for predicting response to ICI therapy.

Being certain about uncertainties: a robust evaluation method for high-dose-rate prostate brachytherapy treatment plans including the combination of uncertainties

In high-dose-rate (HDR) prostate brachytherapy the combined effect of uncertainties cause a range of possible dose distributions deviating from the nominal plan, and which are not considered during treatment plan evaluation. This could lead to dosimetric misses for critical structures and overdosing of organs at risk. A robust evaluation method to assess the combination of uncertainties during plan evaluation is presented and demonstrated on one HDR prostate ultrasound treatment plan retrospectively. A range of uncertainty scenarios are simulated by changing six parameters in the nominal plan and calculating the corresponding dose distribution. Two methods are employed to change the parameters, a probabilistic approach using random number sampling to evaluate the likelihood of variation in dose distributions, and a combination of the most extreme possible values to access the worst-case dosimetric outcomes. One thousand probabilistic scenarios were run on the single treatment plan with 43.2% of scenarios passing seven of the eight clinical objectives. The prostate D90 had a standard deviation of 4.4%, with the worst case decreasing the dose by up to 27.2%. The urethra D10 was up to 29.3% higher than planned in the worst case. All DVH metrics in the probabilistic scenarios were found to be within acceptable clinical constraints for the plan under statistical tests for significance. The clinical significance of the results from the robust evaluation method presented on any individual treatment plan needs to be compared in the context of a historical data set that contains patient outcomes with robustness analysis data to ascertain a baseline acceptance.

Parkinson's Disease Detection from Voice Recordings Using Associative Memories.

Parkinson's disease (PD) is a neurological condition that is chronic and worsens over time, which presents a challenging diagnosis. An accurate diagnosis is required to recognize PD patients from healthy individuals. Diagnosing PD at early stages can reduce the severity of this disorder and improve the patient's living conditions. Algorithms based on associative memory (AM) have been applied in PD diagnosis using voice samples of patients with this health condition. Even though AM models have achieved competitive results in PD classification, they do not have any embedded component in the AM model that can identify and remove irrelevant features, which would consequently improve the classification performance. In this paper, we present an improvement to the smallest normalized difference associative memory (SNDAM) algorithm by means of a learning reinforcement phase that improves classification performance of SNDAM when it is applied to PD diagnosis. For the experimental phase, two datasets that have been widely applied for PD diagnosis were used. Both datasets were gathered from voice samples from healthy people and from patients who suffer from this condition at an early stage of PD. These datasets are publicly accessible in the UCI Machine Learning Repository. The efficiency of the ISNDAM model was contrasted with that of seventy other models implemented in the WEKA workbench and was compared to the performance of previous studies. A statistical significance analysis was performed to verify that the performance differences between the compared models were statistically significant. The experimental findings allow us to affirm that the proposed improvement in the SNDAM algorithm, called ISNDAM, effectively increases the classification performance compared against well-known algorithms. ISNDAM achieves a classification accuracy of 99.48%, followed by ANN Levenberg-Marquardt with 95.89% and SVM RBF kernel with 88.21%, using Dataset 1. ISNDAM achieves a classification accuracy of 99.66%, followed by SVM IMF1 with 96.54% and RF IMF1 with 94.89%, using Dataset 2. The experimental findings show that ISNDAM achieves competitive performance on both datasets and that statistical significance tests confirm that ISNDAM delivers classification performance equivalent to that of models published in previous studies.

A statistical significance test for spatio-temporal receptive field estimates obtained using spike-triggered averaging of binary pseudo-random sequences

A statistical significance test for spatio-temporal receptive field estimates obtained using spike-triggered averaging of binary pseudo-random sequences

An Intelligent IoT-Cloud-Based Air Pollution Forecasting Model Using Univariate Time-Series Analysis.

Air pollution is a significant environmental issue affecting public health and ecosystems worldwide, resulting from various sources such as industrial activities, vehicle emissions, and fossil fuel burning. Air pollution contributes to climate change and can cause several health problems, such as respiratory illnesses, cardiovascular disease, and cancer. A potential solution to this problem has been proposed by using different artificial intelligence (AI) and time-series models. These models are implemented in the cloud environment to forecast the Air Quality Index (AQI)utilizing Internet of things (IoT) devices. The recent influx of IoT-enabled time-series air pollution data poses challenges for traditional models. Various approaches have been explored to forecast AQI in the cloud environment using IoT devices. The primary objective of this study is to assess the efficacy of an IoT-Cloud-based model for forecasting the AQI under different meteorological conditions. To achieve this, we proposed a novel BO-HyTS approach that combines seasonal autoregressive integrated moving average (SARIMA) and long short-term memory (LSTM) and fine-tuned it byusing Bayesian optimization to predict air pollution levels. The proposed BO-HyTS model can capture both linear and nonlinear characteristics of the time-series data, thus augmenting the accuracy of the forecasting process. Additionally, several AQI forecasting models, including classical time-series, machine learning, and deep learning, are employed to forecast air quality from time-series data. Five statistical evaluation metrics are incorporated to evaluate the effectiveness ofmodels. While comparing the various algorithms among themselves becomes difficult, anon-parametric statistical significance test (Friedman test) is applied to assess the performance of the different machine learning, time-series, and deep learning models. The findings reveal that the proposed BO-HyTS model produced significantly better results than their competitor's, providing the most accurate and efficient forecasting model, with an MSE of 632.200, RMSE of 25.14, Med AE of 19.11, Max Error of 51.52, and MAE of 20.49. The results of this study provide insights into the future patterns of AQI in various Indian states and set a standard for these states as governments develop their healthcare policies accordingly. The proposed BO-HyTS model has the potential to inform policy decisions and enable governments and organizations to protect better and manage the environment beforehand.