Alternative Prediction Models Research Articles

Bridging Data Gaps: Predicting Sub-national Maternal Mortality Rates in Kenya Using Machine Learning Models.

Introduction Maternal mortality remains a critical global health issue, with ongoing efforts to reduce its incidence as part of international health priorities. Kenya, a sub-Saharan country that has a disproportionate number of maternal mortality is likely to miss this target unless evidence-based interventions are deployed. The paucity of reliable maternal health data calls for the development of alternative predictive models to complement the impaired civil registration system and the aperiodic national surveys. Methods We utilized DHS surveys from several Sub-Saharan African countries to estimate parameters for predicting Kenya's maternal mortality rate (MMR) in the absence of recent Kenya Demographic and Health Survey (KDHS) data. We developed a multiple linear regression model using supervised machine learningusing the R-programming suite. Our model leverages machine learning techniques to analyze regional trends and predict sub-national MMR variations. We then applied the model to predict MMR for Kenyan counties using the data for the KDHS 2022 survey. Results Using Pearson's correlation, we observed a significant positive correlation between MMR and total fertility (r = 0.32, p = 0.025) and a significant negative correlation between MMR and maternal age at first birth (r = -0.40, p = 0.005). Additionally, a significant correlation was observed with the cumulative percentage of mothers attending post-natal clinics, the prevalence of thinness (r = 0.77, p < 0.001), HIV infection in women (r = 0.20, p = 0.164), and physical violence during pregnancy. The model estimate of national MMR in 2022 was 367 deaths per 100,000 live births, ranging from 49 deaths per 100,000 live births in Kisii County to 1794 deaths per 100,000 live births in Turkana County. Conclusion Although MMR in Kenya displayed a general downward trend, our model's estimates for DHS 2022 indicate an increase compared to the 2019 National Census and Housing Survey estimate of 355 deaths per 100,000 live births. This rise may be attributed to COVID-19-related maternal deaths during the same period. The integration of predictive models to inform interventions and resource allocation could play a crucial role in enhancing maternal healthcare outcomes in Kenya.

Research on the prediction method of wing structure noise based on the combination of conditional generative adversarial neural network and numerical methods

This paper presents a technique for predicting noise generated by airfoil structures that combines deep learning techniques with traditional numerical methods. In traditional numerical methods, accurately predicting the noise of airfoil structures requires significant computational resources, making it challenging to perform low-noise optimization design for these structures. To expedite the prediction process, this study introduces Conditional Generative Adversarial Networks (CGAN). By replacing the generator and discriminator of CGAN with traditional regression neural network models, the suitability of CGAN for regression prediction is ensured. In this study, the data computation was accelerated by expanding the kernel function in the traditional boundary element method using a Taylor series. Based on the resulting data, an alternative predictive model for wing structure noise was developed by integrating Conditional Generative Adversarial Networks (CGAN). Finally, the effectiveness and feasibility of the proposed method are demonstrated through three case studies.

Measuring the impact of enterprise risk management on performance, value, and risk indicators of Borsa Istanbul XBANK companies with data mining prediction models

Risk management (RM) is viewed by organizations from a holistic perspective instead of a silo-based point of view and a change in basic assumptions has occurred in recent years. The comprehensive approach to RM that is developed based on a holistic perspective and is adopted by companies is called enterprise risk management (ERM). From the general point of view, it is expected that companies will have sustainable operations, improved performance and value, and controlled risks by using the ERM concept. In this article, the relations of ERM adaptation with firm performance, firm value, and risks were researched through ordinal variables such as the implementation level of ERM and the sophistication level of the organizational structure of ERM in regression models based on panel data (PD). Empirical evidence depending on a sample of ten banking companies listed on the Borsa Istanbul (BIST) Banks index (XBANK) for the period from 2019 to 2022 confirms the above basic argument for firm performance, firm value, and the insolvency risk of banks in general terms. In addition, the prediction accuracy of PD models is calculated for the performance, value, and risk indicators of banks, and the partial least squares regression model is proposed as the alternative prediction model of data mining.

Short-Term Electrical Load Forecasting Based on Fuzzy Rough Set Feature Selection and Multi-kernel Extreme Learning Machine

As the complexity of power systems increases, accurate load forecasting becomes crucial. This paper proposes a method for short-term electrical load forecasting that integrates fuzzy rough set (FRS) theory and multi-kernel extreme learning machine (MKELM) to improve both the accuracy and reliability of load predictions. First, we introduce the FRS theory for pre-selecting features. Next, we use correlation analysis (CA) to get rid of redundant features and choose the most important ones as prediction targets. Second, we introduce a novel prediction model based on the multi-kernel extreme learning machine (MKELM), utilizing an enhanced differential evolution algorithm (DEA) to optimize the kernel function’s parameters and the model’s weights. This approach allows for effective adaptation to various feature subsets. Experimental results on actual power load data demonstrate that our approach achieves high accuracy and reliability in short-term load forecasting. Moreover, comparative evaluations reveal that the proposed method outperforms alternative prediction models on key metrics. ANOVA and multiple comparisons further validate the statistical significance and superiority of the proposed method.

Yield prediction models for some wheat varieties with satellite‐based drought indices and machine learning algorithms

AbstractIn recent years, frequent drought events in Konya, one of Türkiye's most important cereal production centres, have led to increased pressure on water and soil resources, resulting in yield losses, particularly in wheat production. Alternative yield prediction models, especially those that play a crucial role in agricultural import–export planning in the region, are important for economic contributions and the development of early warning systems. In this context, the aim of this study is to develop models that can be used in the yield prediction of wheat varieties widely grown in the Konya Altınova region. Agricultural drought indices obtained from Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST) products of the Terra Moderate Resolution Imaging Spectroradiometer (MODIS) satellite were used to obtain model inputs. These indices are the Vegetation Condition Index (VCI), Temperature Condition Index (TCI), Vegetation Health Index (VHI) and Vegetation Supply Water Index (VSWI). In obtaining the input parameters for the models, the growth periods of the varieties in the region were also considered. Using various machine learning algorithms, 21 yield prediction models for Bayraktar‐2000, 12 for Kızıltan‐91 and 8 for Bezostaya‐1 were presented as alternatives, with model performances (coefficient of determination, R2) ranging between 0.74 and 0.97, 0.73 and 0.96, and 0.69 and 0.87, respectively.

Sensitivity analysis of the calibration factor resulting from the application of the HSM predictive method to Italian rural two-lane, two-way roads. The Emilia-Romagna case study

The present study investigates the adoption of predictive methods for road safety in the Italian context. The main goal of predictive methods is to describe safety performances of a road infrastructure according to the real number of occurred crashes and the actual infrastructure characteristics. Currently, the most reliable and widely used model is reported in the Highway Safety Manual (HSM), initially developed for the United States. In order to adapt the HSM existing model to the Italian context a calibration procedure is required. The main purpose of this study is to conduct the sensitivity analysis of the calibration factor, to evaluate the influence of various road characteristics (expressed in terms of Crash Modification Factors – CMFs) on the reliability of the model. Results show that the most influential factors are represented by planimetric curve radius, followed by shoulder type and width and Roadside Hazard Rating (RHR). In addition, the Italian roads taken into account for the present case study, which are single carriageway rural roads located in Emilia Romagna region, have generally exhibited more critical conditions compared to American roads. As a consequence, CMFs expressing the aforementioned infrastructure characteristics are typically greater than 1. Furthermore, road features and driving habits vary significantly with the orographic context (mountain, hill, or valley) and geographical area, factors that cannot be neglected when calibrating predictive models. As a result, a layered calibration would bring to the most reliable solution and, in specific situations, alternative predictive models to HSM could be developed.

Prognostic value of the Favard classification for patients before and after reverse shoulder arthroplasty performed for rotator cuff tear arthropathy

BackgroundAlthough the Favard classification is commonly utilized by surgeons to describe the supero-inferior morphology of the glenoid when treating rotator cuff arthropathy (RCA), its utility in prognosticating patients’ clinical state before and after reverse shoulder arthroplasty (RSA) remains unproven. We assessed the prognostic value of the Favard glenoid classification on preoperative clinical state and postoperative clinical and radiographic outcomes in RSA. MethodsA prospectively collected, multicenter database for a single-platform shoulder arthroplasty system was queried for patients with RCA who underwent RSA with a minimum 2-year clinical follow-up. Differences in patient reported outcome scores (PROMs) (Simple Shoulder Test, American Shoulder and Elbow Surgeons, Shoulder Pain and Disability Index, visual analog scale pain, Shoulder Function score), combined patient-reported and clinical-input scores (Constant, University of California Los Angeles, Shoulder Arthroplasty Smart), active range of motion values (forward elevation, abduction, external rotation [ER], internal rotation [IR]), radiographic outcomes (humeral radiolucency line rates, scapular notching rate), and the incidence of postoperative complications and revision surgery were compared by glenoid deformity type per the Favard classification. Comparisons were performed to assess the ability of the Favard classification to prognosticate the preoperative, postoperative, and improved state after RSA. Results400 RSAs performed for RCA were included. Comparison of outcomes between Favard glenoid types resulted in 6 pairwise comparisons of 12 clinical outcome metrics, yielding 72 total Favard glenoid pairwise comparisons for each clinical state (preoperative, postoperative, improvement). Of the 216 possible pairwise Favard glenoid type/metric comparisons, statistical significance was only reached for 3% of the combinations (7/216). Among E0, E1, and E2 glenoids, the only statistically significant pairwise comparison identified among all three clinical states was a more favorable preoperative American Shoulder and Elbow Surgeons score for E0 vs. E2 glenoids. Preoperatively, E3 glenoids had poorer ER, IR, and Shoulder Arthroplasty Smart scores compared to E0 glenoids and poorer ER compared to E2 glenoids. Postoperatively, E3 glenoids had a poorer IR score compared to E0 glenoids and poorer ER compared to E1 glenoids. No pairwise differences in preoperative to postoperative improvement were found. There were no statistically significant pairwise differences in humeral lucency rate, scapular notching rate, complication rates, or revision rates between Favard glenoid types. ConclusionAlthough useful for describing degenerative changes to the glenohumeral joint, the Favard classification offers little prognostic information regarding patient outcomes before and after RSA aside from poorer preoperative and postoperative axial rotation in E3 glenoids. Alternative glenoid classification systems or predictive models should be considered for more precise prognoses of patients undergoing RSA for RCA.

Performance prediction of a ground source heat pump system using denoised long short-term memory neural network optimised by fast non-dominated sorting genetic algorithm-II

The ground source heat pump (GSHP) is a commonly employed technique that utilises geothermal resources to heat or cool buildings, offering an advantageous alternative for reducing conventional energy consumption. Considering that the output energy of GSHP system is a critical criterion for evaluating the geothermal energy extraction, this study proposes an improved long short-term memory (LSTM) model for predicting the energy output of geothermal heat exchangers (GHE) EGHE-PT and the electrical energy consumption EEC-PT of a GSHP system. The model is trained and validated using a comprehensive real-time monitoring dataset gathered over a four-year period from a three-story residential house situated in Cleveland, Ohio, USA. To process the raw data, the wavelet denoising method is employed, while the fast non-dominated sorting genetic algorithm-II (NSGA-II) is employed to automatically determine the optimal hyperparameters for the LSTM model. Comparative analyses with alternative prediction models demonstrate the superior performance of the Denoised-LSTM-NSGA-II model. The results indicate that the Denoised-LSTM-NSGA-II model yields reasonable prediction for the two performance indicators: EGHE-PT and EEC-PT (with the R2 of 0.91 and 0.89, respectively). Further examination reveals that outdoor temperature holds a significantly high importance rank within the Denoised-LSTM-NSGA-II model. This implies that the proposed method can achieve an acceptable level of accuracy by only utilising weather data from the preceding 5 days. The aforementioned findings present a potentially cost-effective approach for predicting the performance of GSHP system based on limited monitoring data.

How to select oil price prediction models — The effect of statistical and financial performance metrics and sentiment scores

Predicting crude oil prices is an important yet challenging forecasting problem due to various influencing quantitative and qualitative factors. To address the growing number of potential prediction models and model parameters to consider during model selection, we highlight the need to systematically compare alternative prediction models and variables while taking the specific context of their application into account. Specifically, we provide a novel perspective on oil price prediction models by comparing a variety of different forecasting models and considering both their statistical and financial performance. In addition to common statistical measures, to assess the usefulness in a practical setting we evaluate the potential financial impact of the predictions in a simulation of a simple trading strategy. We show that the ranking of different approaches depends on the selected evaluation metric and that small differences between models in one evaluation metric can translate into large differences in another metric. For instance, forecasts that are not considered statistically different can lead to substantially different financial performance when the forecasts are used in a trading strategy. Finally, we show that including qualitative information in the prediction models through sentiment analysis can yield both statistical and financial performance improvements.

The effect of covariates on Soil Organic Matter and pH variability: a digital soil mapping approach using random forest model

ABSTRACT This research focuses on understanding the spatial variation of Soil Organic Matter (SOM) and pH levels in the North of Morocco. The study employs a comprehensive approach to enhance predictive modelling, incorporating the Boruta algorithm for effective environmental covariates selection and optimizing model parameters through hyperparameter optimization. Utilizing a Random Forest (RF) model with remote sensing indices and topographic features, the research predicts SOM and pH to identify key contributors to their spatial variability. SOM prediction saw significant success, with a notable correlation to remote sensing indices such as the RVI, NDVI, and TNDVI. These indices, indicative of vegetation health and productivity, emerged as primary influencers of SOM. In comparison, the influence of topographic features like elevation, slope, and aspect was found to be less significant. Conversely, predicting pH was challenging due to the minimal spatial variability within the dataset. Addressing this limitation could involve dataset expansion or alternative models for low-correlated data handling. Despite the RF model’s limited efficacy in pH prediction, an observable correlation between SOM and pH was identified, consistent with prior research. Areas with higher SOM exhibited lower pH values, indicating relative soil acidification from organic matter decomposition. The study’s RF model demonstrated potential in SOM prediction using remote sensing indices, but enhancing pH prediction is essential. Future research may explore dataset expansion, diverse sampling, or testing alternative predictive models for better performance with low-correlated datasets. The study offers valuable insights for advanced predictive model development and enriches understanding of soil management practices.

Corporate Bankruptcy Prediction Models: A Comparative Study for the Construction Sector in Greece

This study focuses on testing the efficiency of alternative bankruptcy prediction models (Altman, Ohlson, Zmijewski) and on assessing the possible reasons that led to the confirmation or not of the prevailing model. Data from financial statements of listed (Greek) construction companies before the economic crisis were utilized. The results showed that Altman’s main predictive model as well as the revised models have low overall predictability for all three years before bankruptcy.

Assessing the Predictive Value of Haematological Parameters (NLR, LMR, PLR) for COVID-19 Disease Severity as quantified by CT Severity Scores: A Prospective Cohort Study

Introduction: In the relentless global battle against the Coronavirus Disease-2019 (COVID-19) pandemic, accurate prediction of disease severity remains a critical challenge, with profound implications for patient outcomes and healthcare resource allocation. As the virus continues to evolve and pose new threats, the need for reliable prognostic indicators becomes increasingly urgent. Effective identification of patients at highrisk of developing severe illness not only facilitates timely intervention and personalised treatment strategies but also optimises healthcare resource utilisation. In this context, the exploration of novel biomarkers and predictive models holds immense promise for enhancing ones understanding of disease progression and improving clinical decision-making. Aim: To study the association between haematological parameters, including Neutrophil-to-Lymphocyte Ratio (NLR), Lymphocyte-to-Monocyte Ratio (LMR), and Platelet-toLymphocyte Ratio (PLR), with Computed Tomography Scan Severity Score (CTSS) in COVID-19 patients. Materials and Methods: A prospective cohort study was conducted from March 2021 to July 2022 at Government General Hospital (GGH) Nizamabad, Telangana, India. The study encompassed all three COVID-19 waves, included a sample size of 159 Reverse Transcriptase Polymerase Chain Reaction (RT-PCR) positive patients, excluding pregnant women and children under 10 years. Upon admission, CTSS and ratios of NLR, LMR, and PLR were recorded in an MS Excel sheet before any medical intervention and then analysed using Statistical Package for Social Sciences (SPSS) software 22.0. Results: The study comprised 159 patients with a mean age of 50.86±13.89 years (ranging from 16 to 85), predominantly male 90 (56.61%). The highest infection rate 85 (53.45%) was in the 41-60 years age group. The NLR was significantly elevated from a mean value of 4.58 to 11.24 (r value=0.78, p-value=&lt;0.001), and LMR notably reduced from 8.27 to 3.80 (r value=0.67, p-value=0.003) in correlation with the severity as indicated by CTSS. Although PLR values were higher in severe cases, increasing from 173.07 in mild cases to 272.29 in severe cases, there was no significant correlation with CTSS (r-value=-0.78, p-value=0.177). Conclusion: CTSS emerges as a valuable radiological biomarker for predicting COVID-19 severity. However, due to its cost and limited availability in grassroots-level hospitals, there is a need for alternative severity prediction models. Present study proposes a predictive model using NLR and LMR biomarkers as alternatives to CTSS for assessing COVID-19 severity.

Machine Learning Model for Construction Time Prediction: A Case of Selected Public Building Projects in Hosanna, Ethiopia

The duration of a construction project is a vital factor to consider before the commencement of the new project. Nowadays, the common problem in the construction industry is time overrun. The main reason for this is the poor prediction of construction contract durations. Therefore, the objective of this study is to evaluate and validate Bromilow’s time‐cost model and Love et al.’s time‐floor model to estimate early project durations for public building construction projects in the Hadiya Zone. The study also suggested an alternative duration machine learning prediction model by considering possibly influential project influencing factors. A questionnaire survey is designed to collect data, and subsequently, the study was performed using the Python programming language for development and validation purposes with different libraries used. The study developed Bromilow’s time‐cost model using a simple linear regression algorithm and Love et al.’s time‐floor model using a multiple linear regression algorithm and proposed a parametric model using random forest, XGBoost, decision tree, K‐nearest neighbor, and polynomial regression algorithms. This study extends the body of knowledge related to construction time performance, and it contributes valuable insights that inform the implementation of machine learning model for construction time prediction.

Analysis and Prediction of Airfield Area Conflict Risk Under Dynamic Time‐Varying Network

To ensure the safety of operations in the airfield area, it is crucial to address the increased conflict risks resulting from the growing number of vehicles and aircraft. Based on the complex network theory, this study takes aircraft and vehicles in the airfield area as nodes and selects five different indicators (average degree, average node weight, average weighted clustering coefficient, network density, and network efficiency) to characterize the operation state of the airfield area, so as to identify conflict risks. Building on this framework, an ATT‐Bi‐LSTM innovation prediction model based on LSTM network architecture is established to forecast the evolution of network indicators over time. By leveraging the algorithm to predict the temporal evolution of indicators, valuable insights into the future evolution of conflict risk can be gleaned from the prediction results. Real operational data from Xi’an Xianyang Airport are utilized as a demonstrative example in this study. The results of the experiments illustrate that the analytical approach proposed in this study achieves a precise identification of the indicators. The experimental results are then compared with data from other predictive models that operate on the same data set. Compared to alternative prediction models, the accuracy is increased by nearly 10%, reaching 89.78%. The results of the study help to accurately identify conflict risks in the airfield area in advance and provide strategic conflict avoidance strategies for relevant staff. This is essential to ensure the security of airfield area.

Predicting feed intake in confined beef cows.

Six existing equations (three for nonlactating and three for lactating; NRC, 1987, Predicting feed intake of food-producing animals. Washington, DC: The National Academies Press, National Academy of Science; doi: 10.17226/950; NRC, 1996, Nutrient requirements of beef cattle, 7th Revised Edition: Update 1996. Washington, DC: The National Academies Press; doi: 10.17226/9791; Hibberd and Thrift, 1992. Supplementation of forage-based diets. J. Anim. Sci. 70:181. [Abstr]) were evaluated for predicting feed intake in beef cows. Each of the previously published equations are sensitive to cow-shrunk BW and feed energy concentration. Adjustments in feed intake prediction are provided for level of milk yield in NRC (1987. Predicting feed intake of food-producing animals. Washington, DC: The National Academies Press, National Academy of Science; doi: 10.17226/950) and NRC (1996 Nutrient requirements of beef cattle, 7th Revised Edition: Update 1996. Washington, DC: The National Academies Press; doi: 10.17226/9791) equations. The equation published in 1996 used data generated between 1979 and 1993. Our objectives were to validate the accuracy of the published equations using more recent data and to propose alternative prediction models. Criteria for inclusion in the evaluation dataset included projects conducted or published since 2002, direct measurement of feed intake, adequate protein supply, and pen feeding (no metabolism crate data). After removing outliers, the dataset included 53 treatment means for nonlactating cows and 32 treatment means for lactating cows. Means for the nonlactating dataset were dry matter intake (DMI) = 13.2 ± 2.9kg/d, shrunk body weight (SBW) = 578 ± 83.9kg, body condition score = 5.7 ± 0.73, and Mcal net energy for maintenance (NEm)/kg of feed = 1.27 ± 0.15 Mcal/kg. Means for the lactating dataset were DMI = 14.6 ± 2.24kg/d, SBW = 503 ± 73.4kg, body condition score = 4.7 ± 0.58, and Mcal NEm/kg feed = 1.22 ± 0.16. Simple linear regression was used to determine slope, intercept, and bias when observed DMI (y) was regressed against predicted DMI (x). The NRC (1996. Nutrient requirements of beef cattle, 7th Revised Edition: Update 1996. Washington, DC: The National Academies Press; doi: 10.17226/9791) nonlactating equation underestimated feed intake in diets moderate to high in energy density with intercept differing from 0 and slope differing from one (P ≤ 0.01). Average deviation from observed values was 2.4kg/d. Similarly, when the NRC (1996. Nutrient requirements of beef cattle, 7th Revised Edition: Update 1996. Washington, DC: The National Academies Press; doi: 10.17226/9791) equation was used to predict DMI in lactating cows, the slope differed from one (P < 0.01) with average deviation from observed values of 3.0kg/d. New models were developed by pooling the two datasets and including a categorical variable for stage of production (0 = nonlactating and 1 = lactating). Continuous variables included study-average SBW0.75 and diet NEm, Mcal/kg. The best-fit empirical model accounted for 68% of the variation in daily feed intake with standard error of the estimate Sy root mean squared error = 1.31. The proposed equation needs to be validated with independent data.

Probabilistic Nearest Neighbors Classification.

Analysis of the currently established Bayesian nearest neighbors classification model points to a connection between the computation of its normalizing constant and issues of NP-completeness. An alternative predictive model constructed by aggregating the predictive distributions of simpler nonlocal models is proposed, and analytic expressions for the normalizing constants of these nonlocal models are derived, ensuring polynomial time computation without approximations. Experiments with synthetic and real datasets showcase the predictive performance of the proposed predictive model.

Replicability and reproducibility of predictive models for diagnosis of depression among young adults using Electronic Health Records

BackgroundRecent advances in machine learning combined with the growing availability of digitized health records offer new opportunities for improving early diagnosis of depression. An emerging body of research shows that Electronic Health Records can be used to accurately predict cases of depression on the basis of individual’s primary care records. The successes of these studies are undeniable, but there is a growing concern that their results may not be replicable, which could cast doubt on their clinical usefulness.MethodsTo address this issue in the present paper, we set out to reproduce and replicate the work by Nichols et al. (2018), who trained predictive models of depression among young adults using Electronic Healthcare Records. Our contribution consists of three parts. First, we attempt to replicate the methodology used by the original authors, acquiring a more up-to-date set of primary health care records to the same specification and reproducing their data processing and analysis. Second, we test models presented in the original paper on our own data, thus providing out-of-sample prediction of the predictive models. Third, we extend past work by considering several novel machine-learning approaches in an attempt to improve the predictive accuracy achieved in the original work.ResultsIn summary, our results demonstrate that the work of Nichols et al. is largely reproducible and replicable. This was the case both for the replication of the original model and the out-of-sample replication applying NRCBM coefficients to our new EHRs data. Although alternative predictive models did not improve model performance over standard logistic regression, our results indicate that stepwise variable selection is not stable even in the case of large data sets.ConclusionWe discuss the challenges associated with the research on mental health and Electronic Health Records, including the need to produce interpretable and robust models. We demonstrated some potential issues associated with the reliance on EHRs, including changes in the regulations and guidelines (such as the QOF guidelines in the UK) and reliance on visits to GP as a predictor of specific disorders.

Prognostic value of the Walch classification for patients before and after shoulder arthroplasty performed for osteoarthritis with an intact rotator cuff

The Walch classification is commonly utilized by surgeons when determining the treatment of osteoarthritis (OA). However, its utility in prognosticating patient clinical state before and after TSA remains unproven. We assessed the prognostic value of the modified Walch glenoid classification on preoperative clinical state and postoperative clinical and radiographic outcomes in total shoulder arthroplasty (TSA). A prospectively-collected, multi-center database for a single-platform TSA system was queried for patients with rotator cuff-intact OA and minimum 2 year follow-up after anatomic and reverse TSA (aTSA, rTSA). Differences in patient-reported outcome scores (PROMS) [SST, ASES, SPADI, VAS Pain, Shoulder Function score], combined patient-reported and clinical-input scores (Constant, UCLA, SAS), active range of motion (ROM) values (forward elevation [FE], abduction, external rotation [ER], internal rotation [IR], and radiographic outcomes (humeral and glenoid radiolucency line rates, scapula notching rate) were stratified and compared by glenoid deformity type per the Walch classification for aTSA and rTSA cohorts. Comparisons were performed to assess the ability of the Walch classification to predict the preop, postop, and improved state after TSA. 1,008 TSAs were analyzed including 576 aTSA and 432 rTSA. Comparison of outcomes between Walch glenoid types resulted in 15 pairwise comparisons of 12 clinical outcome metrics, yielding 180 total Walch glenoid pairwise comparisons for each clinical state (preoperative, postoperative, improvement). Of the 180 possible pairwise Walch glenoid type / metric comparisons studied for aTSA and rTSA cohorts, <6% and < 2% significantly differed in aTSA and rTSA cohorts, respectively. Significant differences based on Walch type were seen after adjustment for multiple pairwise comparisons in the aTSA cohort for FE and ER preoperatively, the Constant score postoperatively, and for abduction, FE, ER, Constant score, and SAS score for pre- to postoperative improvement. In the rTSA cohort, significant differences were only seen in abduction and Constant score both postoperatively and for pre- to postoperative improvement. There were no statistically significant differences in humeral lucency rate, glenoid lucency rate (aTSA), scapular notching rate (rTSA), complication rates, or revision rates between Walch glenoid types after TSA. Although useful for describing degenerative changes to the glenohumeral joint, we demonstrate a weak association between preoperative glenoid morphology according to the Walch classification and clinical state when evaluating patients undergoing TSA for rotator cuff-intact OA. Alternative glenoid classification systems or predictive models should be considered to provide more precise prognoses for patients undergoing TSA for rotator cuff-intact OA.

Splicing transcriptome-wide association study to identify splicing events for pancreatic cancer risk.

A large proportion of the heritability of pancreatic cancer risk remains elusive, and the contribution of specific mRNA splicing events to pancreatic cancer susceptibility has not been systematically evaluated. In this study, we performed a large splicing transcriptome-wide association study (spTWAS) using three modeling strategies (Enet, LASSO and MCP) to develop alternative splicing genetic prediction models for identifying novel susceptibility loci and splicing introns for pancreatic cancer risk by assessing 8275 pancreatic cancer cases and 6723 controls of European ancestry. Data from 305 subjects of whom the majority are of European descent in the Genotype-Tissue Expression Project (GTEx) were used and both cis-acting and promoter-enhancer interaction regions were considered to build these models. We identified nine splicing events of seven genes (ABO, UQCRC1, STARD3, ETAA1, CELA3B, LGR4 and SFT2D1) that showed an association of genetically predicted expression with pancreatic cancer risk at a false discovery rate ≤0.05. Of these genes, UQCRC1 and LGR4 have not yet been reported to be associated with pancreatic cancer risk. Fine-mapping analyses supported likely causal associations corresponding to six splicing events of three genes (P4HTM, ABO and PGAP3). Our study identified novel genes and splicing events associated with pancreatic cancer risk, which can improve our understanding of the etiology of this deadly malignancy.

Text-based Question Difficulty Prediction: A Systematic Review of Automatic Approaches

Designing and constructing pedagogical tests that contain items (i.e. questions) which measure various types of skills for different levels of students equitably is a challenging task. Teachers and item writers alike need to ensure that the quality of assessment materials is consistent, if student evaluations are to be objective and effective. Assessment quality and validity are therefore heavily reliant on the quality of the items included in the test. Moreover, the notion of difficulty is an essential factor that can determine the overall quality of the items and the resulting tests.Thus, item difficulty prediction is extremely important in any pedagogical learning environment. Although difficulty is traditionally estimated either by experts or through pre-testing, such methods are criticised for being costly, time-consuming, subjective and difficult to scale, and consequently, the use of automatic approaches as proxies for these traditional methods is gaining more and more traction. In this paper, we provide a comprehensive and systematic review of methods for the priori prediction of question difficulty. The aims of this review are to: 1) provide an overview of the research community regarding the publication landscape; 2) explore the use of automatic, text-based prediction models; 3) summarise influential difficulty features; and 4) examine the performance of the prediction models. Supervised machine learning prediction models were found to be mostly used to overcome the limitations of traditional item calibration methods. Moreover, linguistic features were found to play a major role in the determination of item difficulty levels, and several syntactic and semantic features were explored by researchers in this area to explain the difficulty of pedagogical assessments. Based on these findings, a number of challenges to the item difficulty prediction community are posed, including the need for a publicly available repository of standardised data-sets and further investigation into alternative feature elicitation and prediction models.