Short-term Data Research Articles

Influence of neoadjuvant treatment strategy on perioperative outcomes in locally advanced rectal cancer.

Neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer facilitates tumour downstaging and complete pathological response (pCR). The goal of neoadjuvant systemic chemotherapy (total neoadjuvant chemotherapy, TNT) is to further improve local and systemic control. While some patients forgo surgery, total mesorectal excision (TME) remains the standard of care. While TNT appears to be noninferior to nCRT with respect to short-term oncological outcomes few data exist on perioperative outcomes. Perioperative morbidity including anastomotic leaks is associated with a negative effect on oncological outcomes, probably due to a delay in proceeding to adjuvant therapy. Thus, we aimed to compare conversion rates, rates of sphincter-preserving surgery and anastomosis formation rates in patients undergoing rectal resection after either TNT or standard nCRT. An institutional colorectal oncology database was searched from January 2018 to July 2023. Inclusion criteria comprised patients with histologically confirmed rectal cancer who had undergone neoadjuvant therapy and TME. Exclusion criteria comprised patients with a noncolorectal primary, those operated on emergently or who had local excision only. Outcomes evaluated included rates of conversion to open, sphincter-preserving surgery, anastomosis formation and anastomotic leak. A total of 119 patients were eligible for inclusion (60 with standard nCRT, 59 with TNT). There were no differences in rates of sphincter preservation or primary anastomosis formation between the groups. However, a significant increase in conversion to open (p = 0.03) and anastomotic leak (p = 0.03) was observed in the TNT cohort. In this series TNT appears to be associated with higher rates of conversion to open surgery and higher anastomotic leak rates. While larger studies will be required to confirm these findings, these factors should be considered alongside oncological benefits when selecting treatment strategies.

Regression modeling of subjective probability of river inundation with epistemic uncertainty: a short-term panel data analysis

Lack of sufficient knowledge about flood risk can lead to “don’t know” responses or non-response in risk perception surveys, and incorrect treatment of these responses can lead to bias in the results. In this study, we focus on the possibility that the “50%” response actually means “fifty-fifty” and thus reflects epistemic uncertainty in the subjective probability of river flooding. We conduct an analysis that introduces a concomitant-variable latent class model as a method to adjust for this epistemic uncertainty. The results of the analysis accounting for epistemic uncertainty suggest that risk communication, such as simulated evacuation experiences and flood-related information distribution, increases subjective probability. Moreover, the proportion of latent classes with epistemic uncertainty decreased with each successive wave of the survey, thereby suggesting that knowledge acquisition and learning through the demonstration experiment led to a reduction in epistemic uncertainty. The analysis using the evacuation decision-making model also suggested that the introduction of subjective probability contributed to improving the likelihood of the model. These results suggest that knowledge acquisition through risk communication and short-term panel survey can lead to correct risk perception estimations and influence evacuation decisions.

Generation and application of typical meteorological year data for PV system potential assessment: A case study in China

The potential assessment of photovoltaic(PV) systems is of great significance for installing and laying out PV. Short-term meteorological data cannot reflect the local climate characteristics, so it is not suitable for the potential assessment of PV. A typical meteorological year(TMY) can reflect a region's climatic characteristics, and therefore, it is appropriate for the potential assessment of PV. Although the generation methods of TMY for building energy consumption simulation are mature, there are still limited studies on TMY for PV. Given this, this study employs a method to generate TMY data suitable for the Chinese region, while redefining the influencing factors and their respective weights. A TMY dataset was built for 90 cities based on 38 years of measured data in China and applied to BAPV potential assessment. The study assesses annual generation, CO2 reduction, levelized cost of electricity (LCOE), and net returns(NR). The results reveal the highest annual electricity generation in the Northwest region, with Shiquanhe, Golmud, and Ejina sites reaching 215.65 MWh, 201.2 MWh, and 197.5 MWh, respectively. Conversely, southern and coastal regions, notably Chongqing, exhibit the lowest generation at 75.75 MWh. BAPV in Class I tariff areas, along with some Class II and III areas, can achieve demand-side parity (DSP) in full on-grid mode. Through operational adjustments, DSP can be implemented in 23 currently ineligible areas. This study provides dataset support for calculating PV system power generation and analyzes PV potential across diverse cities. The results contribute to policy formulation and future solar energy research, facilitating precise calculations for efficient green power planning in pursuit of carbon neutrality.

Faktor Penentu Pertumbuhan Ekonomi Indonesia

This research aims to determine: the effect of inflation on Indonesia's economic growth, the effect of HDI on Indonesia's economic growth and the effect of unemployment on economic growth in Indonesia. The data used in this research is secondary data sourced from the websites of various agencies including BPS, aseanstats.org, and kidb.adb.org, from 1993-2022. This research uses the Autoregressive Distributed Lag or ARDL analysis tool model. The ARDL model is a combination of autoregressive (AR) and distributed lag (DL) methods. The AR method is a method that uses one or more past data from the dependent variable, while DL is a regression method that involves data at the present and past times from the independent variable. This model can differentiate short-term and long-term responses of the variables studied. The findings of this study indicate that there is cointegration between the variables used in this study so that the ARDL test can be carried out. The results of short-term data processing show that inflation has had a negative and significant effect on Indonesia's economic growth in the current year, two and three years previously. Meanwhile, HDI has a significant influence in the current year and the previous two years. Meanwhile, unemployment has had a significant negative influence in the current year on Indonesia's economic growth. In long-term estimates, inflation and unemployment have a negative and significant effect on economic growth, however, HDI does not have a significant effect on Indonesia's economic growth.

Efficient implementation of a wavelet neural network model for short-term traffic flow prediction: Sensitivity analysis

The concept of a smart city is emerging to address significant challenges arising from rapid urbanization, economic growth, and climate change. Innovative technologies can be used as a means to promote sustainable and inclusive urban development. These technolgies include the deployment of the internet of things (IoT), artificial intelligence (AI), energy management, and smart transportation. In a smart city, intelligent transportation systems (ITS) play a vital role in efficient traffic management. This paper explores the use of hybrid artificial intelligence techniques for predicting short-term traffic flow data from M25 motorways in the UK. Since volume traffic flow data are non-stationary, wavelet transform (WT) as a powerful signal analyzer is applied for signal decomposition for the elimination of redundant data from input matrices. The feature selection method based on Gram-Schmidt (GS) is used for the selection of more valuable features. The elimination of redundant data can speed up the learning process and improve the generalisation capability of the prediction models. After a pre-processing stage, a wavelet neural network (WNN) with a simple structure is applied as a powerful prediction tool. Two separate structures are considered for the prediction of weekday and weekend traffic volume data. The experiments explore that the debauchies-4 (db4) wavelet function with 7 decomposition levels leads to the best detection accuracy. Moreover, the range of forecasting, the type of the day, the level of decomposition, and other factors all have an impact on prediction stability. Compared with existing prediction methods, the proposed approach produces lower values of root mean square error (RMSE) and mean absolute percentage error (MAPE) for all step-horizons analyzed. These findings provide valuable implications and insights into the development of an efficient and reliable road condition monitoring system for delivering secure and sustainable transportation services.

Advancing the drug development process in metastatic prostate cancer through machine learning.

192 Background: Despite advances in the development of systemic therapeutics, metastatic prostate cancer (mPC) remains a lethal disease. The drug approval process is slow, and delays in approving active agents translate into lives lost, and increased morbidity for men living with mPC. Clinical benefit end points proximate to survival that could support regulatory approval have been sought. Methods that accelerate the prediction of overall survival (OS) from baseline and short-term clinical data could dramatically accelerate the "readout" timeline for registrational studies. Methods: Curated, anonymized data from 5,679 mPC patients (pts) across six completed clinical trials were used: COU-AA-301, COU-AA302, ACIS, GALAHAD, LATITUDE, and TITAN. These trials comprise heterogeneous pts across castrate sensitive (TITAN, LATITUDE) and castrate resistant (COU-AA-301, COU-AA-302, ACIS, GALAHAD) populations. Transcriptomic profiles of primary tumors were available from a subset of these pts (N = 605) in COU-AA-302, ACIS, TITAN using the DECIPHER platform (Decipher Biosciences, Inc.). We harmonized pts study data and are developing machine learning models in an attempt to predict long term outcomes using baseline clinical features, short term PSA kinetics, and transcriptional profiling data. Associations between clinical and transcriptional signature profiles and overall survival were assessed with the Cox proportional hazards model. Results: Pts were assigned to training (N = 3167) and test (N = 2,512) cohorts. Cohorts were balanced by age, self-reported race, ECOG performance status, extent of disease, and disease site, and had statistically indistinguishable survival curves. At month 3 on study, 97% of pts had PSA data available; 88% had ≥ 2 PSA values. Matched genomic data was evaluated in 504 and 101 pts in training and test sets respectively. Training cohort pts with a 50% reduction in PSA by month 3 (m3-PSA50) had significantly longer OS (HR 0.51 [0.38-0.67]; p = 1.2 x 106, median 26 vs. 38 months). ANOVA analysis identified expression signatures in the Decipher GRID that significantly improved OS model performance when added to a model including only m3-PSA50. We stratified pts by a combined m3-PSA50 and signature score and identified signatures that improved model fit over m3-PSA50 alone and significantly stratified pts in the test cohort (P < 0.05). Conclusions: In this early analysis (prior to applying machine learning), m3-PSA50 was significantly associated with OS in a heterogeneous group of mPC pts. Although the transcriptomic analysis was conducted on primary tumors obtained many years earlier, we identified transcriptional signatures that significantly improved OS models (independent of m3-PSA50) in men who subsequently developed mPC many years later. These results suggest adding genomic signature data to models for predicting outcome using PSA kinetics may provide improved predictive power.

Developing a Novel Read-Across Concept for Ecotoxicological Risk Assessment of Phosphate Chemicals: A Case Study.

This study introduces a novel concept approach for a read-across assessment, considering species sensitivity differences among phosphate chemicals within structurally similar compound groups. Twenty-five organic chemicals, with a log Kow of 5 or less, were categorized into three functional groups based on acetylcholinesterase (AChE) inhibition as a specific mode of action (MOA). The short-term aquatic toxicity data (LC50) for fish, crustaceans, and insects were collected from the U.S. EPA Ecotoxicology (ECOTOX) Knowledgebase. A geometric mean calculation method was applied for multiple toxic endpoints. Performance metrics for the new read-across concept, including correlation coefficient, bias, precision, and accuracy, were calculated. Overall, a slightly higher overestimation (49.2%) than underestimation (48.4%) in toxicity predictions was observed in two case studies. In Case study I, a strong positive correlation (r = 0.93) between the predicted and known toxicity values of target chemicals was observed, while in Case study II, with limited information on species and their ecotoxicity, showed a moderate correlation (r = 0.75). Overall, the bias and precision for Case study I were 0.32 ± 0.01, while Case study II showed 0.65 ± 0.06; however, the relative bias (%) increased from 37.65% (Case study I) to 91.94% (Case study II). Bland-Altman plots highlight the mean differences of 1.33 (Case study I) and 1.24 (Case study II), respectively. The new read-across concept, focusing on AChE inhibition and structural similarity, demonstrated good reliability, applicability, and accuracy with minimal bias. Future studies are needed to evaluate various types of chemical substances, diverse modes of action, functional groups, toxic endpoints, and test species to ensure overall comprehensiveness and robustness in toxicity predictions.

Comparison between the short-term observed and long-term estimated wind power density using Artificial Neural Networks. A case study

The economic feasibility of a wind project is dependent on the wind regime since it relies on the power output of the turbines over the installation’s working life. Consequently, the interannual variability of wind speed at a potential wind energy conversion site is an issue of capital importance. Usually a wind data measurement campaign is limited to a period no longer than one year (i.e. short-term). Therefore, the process of decision-making for wind farm constructors must be based in this short-term data. Various methods have been proposed in the scientific literature for estimation of the long-term wind speed characteristics at such sites. These methods use simultaneous measurements of the wind speed at the site in question and at one or several nearby reference sites with a long history of wind data measurements. In this paper, long-term wind power densities which have been estimated through the use Artificial Neural Networks (ANNs), will be compared to those which have been calculated by means of the short-term wind data (i.e. considered to be representative of long-term wind performance). Mean hourly wind speeds and directions calculated in a 10 year period of time at six weather stations located on six different islands in the Canarian Archipelago (Spain) were used in this study. Among the different conclusions which this study revealed, we can highlight that the wind resource estimation based on ANNs is better than that dependant on short-term wind data. This is true when the correlation coefficient between the reference and candidate weather station is of 0.6.

Testing for statistically significant differences in predictions obtained from competing creep models

It is important to be able to predict the creep life and other creep properties of materials used in power plants and aeroengines. Whilst existing studies have compared different creep models using different measures of predictive performance, none have identified whether these differences are real from a statistical significance perspective. This paper proposes several tests based on a review of the literature. These tests were applied to two creep models using failure time data on 2.25Cr–1Mo steel to develop a recommended approach for practitioners to adopt when selecting a creep model. All such tests concluded that the Evans model produced better long-term life predictions using only short-term data, and that this difference was statistically significant at the 5% significance level.

Data-driven modelling of neurodegenerative disease progression: thinking outside the black box.

Data-driven disease progression models are an emerging set of computational tools that reconstruct disease timelines for long-term chronic diseases, providing unique insights into disease processes and their underlying mechanisms. Such methods combine a priori human knowledge and assumptions with large-scale data processing and parameter estimation to infer long-term disease trajectories from short-term data. In contrast to 'black box' machine learning tools, data-driven disease progression models typically require fewer data and are inherently interpretable, thereby aiding disease understanding in addition to enabling classification, prediction and stratification. In this Review, we place the current landscape of data-driven disease progression models in a general framework and discuss their enhanced utility for constructing a disease timeline compared with wider machine learning tools that construct static disease profiles. We review the insights they have enabled across multiple neurodegenerative diseases, notably Alzheimer disease, for applications such as determining temporal trajectories of disease biomarkers, testing hypotheses about disease mechanisms and uncovering disease subtypes. We outline key areas for technological development and translation to a broader range of neuroscience and non-neuroscience applications. Finally, we discuss potential pathways and barriers to integrating disease progression models into clinical practice and trial settings.

PreSTNet: Pre-trained Spatio-Temporal Network for traffic forecasting

Traffic forecasting stands as a cornerstone in urban planning, yet existing methods mainly fall short in capturing long-term spatio-temporal patterns. To be specific, various exquisite modules are designed in current works, while bringing heavy computing costs with the length of historical data. Furthermore, any replacement or reintegration of modules could weaken final performance, and the whole model needs to be trained from scratch on different datasets. To address the above shortcomings, inspired by pre-training methodologies, we introduce a novel Pre-trained Spatio-Temporal Network (PreSTNet), a two-phase framework comprising pre-training and fine-tuning. In the first pre-training phase, PreSTNet undertakes a data masking and recovery task, which is facilitated through a dedicated long sequence embedding module and an encoder–decoder structure with temporal attention layers and graph convolution operators. The recovery task involves masking several data, forcing the model to capture correlations between unmasked data and finally recover the masked part, which facilitates the extraction of long-term spatio-temporal features from extensive data. The second phase involves freezing the learned parameters and replacing the decoder with a forecasting header. This header, designed as a meta-learning fusion module and spatio-temporal convolution layers, can integrate long-term and short-term traffic data, and is trained in the manner of supervised learning to suit the target task. Rigorous experiments on real-world datasets underscore the superiority of PreSTNet. Further case studies reveal that the pre-trained encoder, coupled with an intuitive linear regression, achieves comparable performance to advanced methods. These findings affirm the robust capabilities of the proposed PreSTNet in addressing the complexities of traffic forecasting.

Cost-Effectiveness of Onasemnogene Abeparvovec Compared With Nusinersen and Risdiplam in Patients With Spinal Muscular Atrophy Type 1 in Brazil: Custo-Efetividade do Onasemnogeno Abeparvoveque (AVXS-101) em Comparação ao Nusinersena e Risdiplam em Pacientes com Atrofia Muscular Espinhal Tipo 1 no Brasil

ObjectivesThis study aimed to evaluate the cost-effectiveness of the onasemnogene abeparvovec in relation to nusinersen and risdiplam in the treatment of spinal muscular atrophy type 1 from the perspective of the Brazilian Unified Health System. MethodsA Markov model was built on a lifetime horizon. Short-term data were obtained from clinical trials of the technologies and from published cohort survival curves (long term). Costs were measured in current 2022 local currency (R$) values and benefits in quality-adjusted life-years (QALYs). Utility values were derived from type 1 spinal muscular atrophy literature, whereas costs related to technologies and maintenance care in each health state were obtained from official sources of reimbursement in Brazil. Deterministic and probabilistic, as well as scenario, sensitivity analyses were performed. ResultsCompared with the less costly strategy (nusinersen), the use of onasemnogene abeparvovec resulted in an incremental cost of R$2.468.448,06 ($975 671.169 – purchasing power parity [PPP]) and a 3-QALY increment and incremental cost-effectiveness ratio of R$742.890,92 ($293 632.774 – PPP)/QALY. Risdiplam had an extended dominance from other strategies, resulting in an incremental cost-effectiveness ratio of R$926.586,22 ($366 239.612 – PPP)/QALY compared with nusinersen. Sensitivity analysis showed a significant impact of the follow-up time of the cohort and the cost of acquiring onasemnogene abeparvovec. ConclusionsOver a lifetime horizon, onasemnogene abeparvovec seems to be a potentially more effective option than nusinersen and risdiplam, albeit with an incremental cost. Such a trade-off should be weighed in efficiency criteria during decision making and outcome monitoring from the perspective of the Brazilian Unified Health System.

A novel few shot learning derived architecture for long-term HbA1c prediction

Regular monitoring of glycated hemoglobin (HbA1c) levels is important for the proper management of diabetes. Studies demonstrated that lower levels of HbA1c play an essential role in reducing or delaying microvascular difficulties that arise from diabetes. In addition, there is an association between elevated HbA1c levels and the development of diabetes-related comorbidities. The advanced prediction of HbA1c enables patients and physicians to make changes to treatment plans and lifestyle to avoid elevated HbA1c levels, which can consequently lead to irreversible health complications. Despite the impact of such prediction capabilities, no work in the literature or industry has investigated the futuristic prediction of HbA1c using current blood glucose (BG) measurements. For the first time in the literature, this work proposes a novel FSL-derived algorithm for the long-term prediction of clinical HbA1c measures. More importantly, the study specifically targeted the pediatric Type-1 diabetic population, as an early prediction of elevated HbA1c levels could help avert severe life-threatening complications in these young children. Short-term CGM time-series data are processed using both novel image transformation approaches, as well as using conventional signal processing methods. The derived images are then fed into a convolutional neural network (CNN) adapted from a few-shot learning (FSL) model for feature extraction, and all the derived features are fused together. A novel normalized FSL-distance (FSLD) metric is proposed for accurately separating the features of different HbA1c levels. Finally, a K-nearest neighbor (KNN) model with majority voting is implemented for the final classification task. The proposed FSL-derived algorithm provides a prediction accuracy of 93.2%.

Classification and prognostic factors of patients with cervical spondylotic myelopathy after surgical treatment: a cluster analysis

Identifying potential prognostic factors of CSM patients could improve doctors’ clinical decision-making ability. The study retrospectively collected the baseline data of population characteristics, clinical symptoms, physical examination, neurological function and quality of life scores of patients with CSM based on the clinical big data research platform. The modified Japanese Orthopedic Association (mJOA) score and SF-36 score from the short-term follow-up data were entered into the cluster analysis to characterize postoperative residual symptoms and quality of life. Four clusters were yielded representing different patterns of residual symptoms and quality of patients’ life. Patients in cluster 2 (mJOA RR 55.8%) and cluster 4 (mJOA RR 55.8%) were substantially improved and had better quality of life. The influencing factors for the better prognosis of patients in cluster 2 were young age (50.1 ± 11.8), low incidence of disabling claudication (5.0%) and pathological signs (63.0%), and good preoperative SF36-physiological function score (73.1 ± 24.0) and mJOA socre (13.7 ± 2.8); and in cluster 4 the main influencing factor was low incidence of neck and shoulder pain (11.7%). We preliminarily verified the reliability of the clustering results with the long-term follow-up data and identified the preoperative features that were helpful to predict the prognosis of the patients. This study provided reference and research basis for further study with a larger sample data, extracting more patient features, selecting more follow-up nodes, and improving clustering algorithm.

A new tensile creep model for predicting long-term creep strengths with short-term test data for creep resistant alloys

The difficulties in using the conventional Norton creep model to rationalise short-term creep data and to subsequently predict long-term creep rupture strengths for creep resistant alloys are presented and analysed. The results of this study show that these difficulties can be resolved if a new tensile creep model that integrates the tensile strength at creep temperature is applied to rationalise the short-term creep data. This is illustrated with the creep and tensile strength data measured for a grade of Ni-based superalloy. Based on this new tensile creep model, the activation energy of creep determined is independent of stress and the stress exponent is not influenced by temperature. Consequently, the model constants obtained from the short-term creep data can be applied together with the Monkman-Grant relationship to make the long-term creep rupture strength predictions at different temperatures. The factors affecting the reliability of the predictions made by this method are also analysed.

Markov enhanced I-LSTM approach for effective anomaly detection for time series sensor data

Users could engage and interact with their immediate surroundings without effort in smart settings. The emergence of intelligent technologies along with software-based services has made this possible. It is clear that technical advancements have ushered in a new era for both computer processing and sensor technology, facilitating the concept of smart surroundings. Even though their implementation faces a number of obstacles, numerous expansive projects are working to advance their adoption. The problem of anomalies in the sensor data could result inappropriate decisions and could lead unamicable situations to the users. Many such algorithms are already there, which does not provide satisfactory predictions for the sensor data for the time series data. Time series anomaly detection problems are typically stated as finding outlier data points in comparison to some norm or typical signal. Better anomaly detection in time series data is provided by the proposed Markov and enhanced LSTM technique. The Markov model and the enhanced LSTM offer accurate predictions for extra- and short-term data, which is highly useful in situations involving intelligent environments. When compared to the KNN algorithm, the technique offers reduced MAE, RMSE, MSE and MAPE errors. The algorithm also performs better than other LSTM and RNN methods. The proposed algorithm provides 0.00047 reduced error in humidity data, 0.00416 reduced error in temperature and 0.01771 reduced MAE value in case of light intensity when comparing with the KNN algorithm.

Construction of Electricity Load Forecasting Model Based on Electricity Data Analysis

Abstract This paper builds a time series prediction model of recurrent neural networks based on time series electricity load forecasting. In this paper, the household electricity consumption record data of some residents in urban area S is taken as the research object, and the laws and characteristics of users’ electricity consumption behavior are analyzed in depth based on the real residential electricity consumption data. External factors such as temperature conditions, holidays, etc. The arithmetic cases are also analyzed using real load data sets. In the short-term continuous electricity data analysis, the smaller the time interval is, the closer its corresponding electricity consumption ratio is to 1. There is a negative correlation between long-term continuous electricity consumption. When the temperature is 30~35oC versus -5~0oC, electricity consumption rises significantly. Comparing and analyzing the time series decomposition-RNN with several models, the time series decomposition-RNN model has the highest fit at 10:00-12:00 and 12:00-14:00, and the result verifies the validity of the model proposed in this paper.

Current Evidence of Single-Port Laparoscopic versus Single Port-Robotic Techniques in Colorectal Surgery: A Meta-Analysis.

Introduction: The primary aim of this meta-analysis was to compare the operative outcomes of single-port laparoscopic versus single-port robotic platforms in colorectal surgery. Materials and Methods: A comprehensive literature search was conducted for studies comparing operative outcomes and short-term follow-up data of single-port laparoscopic versus single-port robotic colectomy. Data from eligible studies were extracted, qualitatively assessed, and included in a meta-analysis. Odds ratios (ORs) and mean differences with 95 per cent confidence intervals were calculated. Results: Three studies with a total of 346 patients (Robotic: 112 cases versus Laparoscopic: 234 cases) were included. There was no statistical difference noted with regard to overall morbidity, length of hospital stay and intra- and postoperative complications between the two groups. However, the robotic approach resulted in higher lymph nodes yield in oncologic cases (SMD -0.25, 95% CI -0.50 to -0.01, p = 0.04, I2 = 0%). Conclusion: Both single-port laparoscopic and robotic techniques appear to be safe and feasible options in colorectal surgery displaying comparable perioperative outcomes. Larger randomized controlled trials are needed to justify their application, particularly with regard to procedurerelated costs.

Insights into Risk: Exploring Retinopathy of Prematurity and Short-term Comorbidities in Moderate-to-Late Preterm Infants.

Retinopathy of prematurity (ROP) and short-term comorbidity data moderate-to-late preterm (MLP) infants in Saudi Arabia are limited. The present study mainly aimed to identify ROP incidence and severity in MLP infants. The secondary objective was to explore whether moderate preterm infants are more prone to systemic short-term comorbidities compared to late preterm infants. This retrospective study was conducted at King Abdulaziz University Hospital, a tertiary center in Jeddah, Saudi Arabia. Two-hundred and sixty-eight MLP infants born with gestational ages (GAs) of 32 to 36 + 6 weeks were included. Births were classified as moderate preterm (GA 32 to 33 + 6 weeks) and late preterm (GA 34 to 36 + 6 weeks) and the two groups were compared with an independent t-test. ROP incidence was 1.5%; all cases were stage 1 and involved zone II or III. No patient had type 1 ROP requiring treatment. The short-term comorbidity incidence was high (76.1%) and included hyperbilirubinemia (n = 206, 76.7%), respiratory distress syndrome (n = 178, 66.4%), hypoglycemia (n = 32, 11.9%,), and transient tachypnea of newborn (n = 25, 9.3%). Moderate preterm infants were more likely to have lower birth weight (P < 0.001), any-stage ROP (P = 0.032), respiratory distress syndrome (P = 0.031), intraventricular hemorrhage (P = 0.038), and hyperbilirubinemia (P < 0.001) compared to the late preterm infants. Any-stage ROP incidence among MLP infants was low, with no type 1 ROP cases requiring treatment. Short-term comorbidity incidence was relatively high among the moderate preterm infants. Despite the low non-type 1 ROP incidence at our center, MLP infants require proper surveillance of systemic short-term comorbidities.

HGMLA: A multi-task learning model for assessment of HbA1c and GA levels using short-term CGM sensor data

HGMLA: A multi-task learning model for assessment of HbA1c and GA levels using short-term CGM sensor data