Complicated Patterns Research Articles

Predicting Chronic Liver Disease and Jaundice Detection an Integrated Approach Using Statistical Feature Extraction and Machine Learning Algorithms

An important health concern with chronic liver disease is early identification, which is essential for management and therapy. This work suggests an integrated method to identify tattoo-induced jaundice and forecast chronic liver disease by combining statistical feature extraction with machine learning techniques. First, we use statistical techniques based on projections to extract pertinent aspects from patient data, such as test results and clinical markers. We then use Artificial Neural Networks (ANN), KNN, and Naive Bayes to categorize individuals according to the probability that they have chronic liver illness and to pinpoint jaundice episodes associated with tattooing. The KNN technique offers interpretability, managing categorical data is made simple by Naive Bayes, and complicated patterns are captured by ANN using layers of neural networks. These models' performance is assessed using the following metrics: F1 score, recall, accuracy, and precision. Our research aims to improve prediction accuracy and offer practical advice for early diagnosis and individualized treatment plans. By utilizing advanced data analysis and machine learning instruments, the integrated strategy shows promise in enhancing healthcare outcomes.

Deep Learning-Based Identification of Immoral Posts on Social Media Using Fine-tuned Bert Model

The propagation of immoral content on social media poses substantial worries to online societal well-being and communication standards. While beneficial, traditional machine learning (ML) methods fall short of capturing the difficulty of textual and sequential data. This work reports this gap by suggesting a deep learning-based technique for detecting immoral posts on social media. The proposed model presents a fine-tuned Bidirectional Encoder representation from Transformers (BERT) with word embedding methods. Word2Vec and Global Vectors for Word Representation (GloVe) are employed to improve the identification of immoral posts on social media platforms to advance detection accuracy and strength. The incentive behind this study stems from the increasing demand for more sophisticated methods to struggle with damaging content. The proposed model is considered to capture the complicated patterns and semantic nuances in immoral posts by decreasing the dependence on manual feature engineering. The model is trained and assessed using benchmark datasets containing SARC and HatEval, which deliver a detailed set of labelled user-generated posts. The proposed model shows the best performance compared to traditional ML approaches. The fine-tuned Bert-based Word2Vec embeddings achieved a precision of 95.68%, recall of 96.85 %, and F1 scores of 96.26% on the SARC dataset. Fine-tuned Bert-based GloVe on the HatEval dataset achieved superior precision of 96.65, recall of 97.75, and F1-score of 97.20. The proposed results highlight the potential of the deep learning (DL) approach and fine-tuned BERT models, considerably refining the detection of unethical content on social networks.

Assessing Geopolitical Risks and Their Economic Impact on the USA Using Data Analytics

Understanding geopolitical risks is a paramount aspect of examining the stability and resilience of national economies, specifically in today’s rapidly evolving global surroundings. Advanced analytics in the big data era open unparalleled avenues toward the quantification and comprehension of geopolitical risks on the performance of the economy of the United States. The prime objective of this study was to analyze the impact of geopolitical events on the U.S. economy, to identify key risk factors and their economic implications as well as propose strategies for mitigating adverse effects. Datasets used in this exploration were collected from different reliable sources to assess sources of geopolitical risk data and their economic impact on the U.S. First, data on geopolitical risk were collated from a combination of real-time news reports, government databases, and international organizations involved in monitoring geopolitical events. Key sources for this included GDELT news and sentiment data, official reports from U.S. government agencies such as the Department of State and the Department of Defense about foreign policy, conflict, and security, while major financial news outlets like Bloomberg and Reuters provided moment-by-moment coverage of events in the geopolitical sphere. We applied the Geo-Risk-Regressor model, a form of multimodal design to predict geopolitical threats arising from economic indicators, real-time news sentiment, and government reports on geopolitical events. The Geo-Risk-Regression Model is an integrated set of machine learning algorithms, from time-series and NLP to econometric regression, on structured and unstructured data comprising economic indicators, real-time news sentiment, and government reports on geopolitical events. A rigorous structured procedure was followed in implementing the Geo-Risk-Regressor to analyze the economic impact of geopolitical risks in the U.S. To assess and evaluate the performance of the algorithms, two key performance evaluation metrics were utilized MSE & R-squared. Among all the models, the best performance was that of XG-Boost; it had the lowest MSE and highest R². Thus, XG-Boost is the best model fitted for the prediction of GPRD_THREAT, probably because of its robust optimization and also its capability to capture a lot of complicated patterns in data. The geopolitical threat level perceived using the proposed models will enable business organizations in the USA to identify and manage risks that may affect the operations of the business organizations. Companies can, therefore, understand factors that contribute to risk and develop contingency plans, enabling them to take proactive measures to mitigate negative impacts from geopolitical events. Predictive models will help businesses in America estimate the potential risks to their supply chains and create strategies for mitigating any disruptions that might come through geopolitical events.

Contemporary comparative surgical outcomes of type A aortic dissection in US and China: an analysis of the national inpatient sample database and a Chinese multi-institutional registry.

To investigate the contemporary comparative inpatient prognosis among US and Chinese patients with type A aortic dissection (TAAD). Data from Chinese multi-institutional TAAD registry and the US National Inpatient Sample databases were analyzed. We used multivariable logistic regression models to compare in-hospital mortality and perioperative complication rates between the US and China. Length of stay and overall costs were fitted with quantile regression models. Independent prognostic factors associated with post-operative survival were assessed via Cox proportional hazards models. Among 3,121 eligible TAAD patients, 1,073 were from China (25.0% female; mean ± SD age, 53.9 ± 12.4) and 2,048 were from the US (31.2% female; mean ± SE age, 59.8 ± 0.3). During the study period, the in-hospital mortality rates in China and the US were 15.5% and 13.3%, yet the difference was insignificant after adjustment (aOR, 1.16; 95% CI, 0.69-1.97). While there was no significant difference in overall perioperative complications (aOR, 1.07; 95% CI, 0.52-2.18), the patterns of complications differed between two cohorts. While Chinese TAAD patients experienced significantly longer duration of hospitalization (median difference, + 10.4 days; 95% CI, 9.2-11.5), the US TAAD cohort had significantly greater overall hospitalization costs (49.9; 95% CI, 55.4-44.5, in 1000 USD). Notwithstanding significant differences in demographic and clinical characteristics, TAAD patients from China and the US demonstrated comparable in-hospital mortality and overall perioperative complication rates. Future initiatives should focus on expanding surgical eligibility to the elderly Chinese TAAD patients and optimizing the duration of hospitalization without undermining meaningful clinical outcomes. KY20220425-05, April 5th 25 2022.

Measuring 15N and 13C Enrichment Levels in Sparsely Labeled Proteins Using High-Resolution and Tandem Mass Spectrometry.

Isotope labeling of both 15N and 13C in selected amino acids in a protein, known as sparse labeling, is an alternative to uniform labeling and is particularly useful for proteins that must be expressed using mammalian cells, including glycoproteins. High levels of enrichment in the selected amino acids enable multidimensional heteronuclear NMR measurements of glycoprotein three-dimensional structure. Mass spectrometry provides a means to quantify the degree of enrichment. Mass spectrometric measurements of tryptic peptides of a selectively labeled glycoprotein expressed in HEK293 cells revealed complicated isotope patterns which consisted of many overlapping isotope patterns from intermediately labeled peptides, which complicates the determination of the label incorporation. Two challenges are uncovered by these measurements. Metabolic scrambling of amino groups can reduce the 15N content of enriched amino acids or increase the 15N in nontarget amino acids. Also, undefined, unlabeled medium components may dilute the enrichment level of labeled amino acids. The impact of this unexpected metabolic scrambling was overcome by simulating isotope patterns for all isotope-labeled peptide states and generating linear combinations to fit to the data. This method has been used to determine the percent incorporation of 15N and 13C labels and has identified several metabolic scrambling effects that were previously undetected in NMR experiments. Ultrahigh mass resolution is also utilized to obtain isotopic fine structure, from which enrichment levels of 15N and 13C can be assigned unequivocally. Finally, tandem mass spectrometry can be used to confirm the location of heavy isotope labels in the peptides.

Early Endocrine and Metabolic Complications in Childhood Cancer Survivors—Experience from a Tertiary Care Pediatric Oncology Center in South India

Background Endocrine abnormalities and metabolic complications remain one of the common late effects after cancer therapy in children. Data on the incidence and pattern of complications would help to guide appropriate monitoring and treatment of childhood cancer survivors. Methods, Aims, and Objectives Purpose of study is to determine endocrine and metabolic effects in childhood cancer survivors including both hematological malignancies and solid tumors due to cancer per se and treatment-related, including different chemotherapeutic agents and radiotherapy. Results Among 97 participants, 84 children (84.5%) had at least one endocrine or metabolic complication; 41 children (42.3%) had more than two endocrine/metabolic complications. Common endocrine complications included precocious puberty (6.2%), short stature (6.2%), and hypothyroidism (5.1%). Among metabolic complications, dyslipidemia was the highest with an incidence of 68%, followed by fasting hyperinsulinism (32%), diastolic hypertension (18.6%), systolic hypertension (11.3%), obesity (8.8%), and metabolic syndrome (8.2%) and impaired fasting glucose (4.1%).Among endocrine complications, there was a significant increase in incidence of hypothyroidism among children receiving radiotherapy (odds ratio [OR]: 7.13, 95% confidence interval [CI]: 1.1–46.2), and among metabolic complications, a significant increase in incidence of metabolic syndrome in children treated with L-asparaginase compared with those not treated with L-asparaginase was observed (OR: 5.61, 95% CI: 1.07–29.5). There was no significant difference between incidence of observed endocrine and metabolic complications based on type of tumor, gender, and puberty status of study participants. Conclusion This study suggests that there is significant incidence of endocrine and metabolic complications in childhood cancer survivors, hence timely and appropriate recognition of these complications by appropriate screening recommendations and pursuing further endocrine evaluation rationally is needed.

Inhomogeneous Skin Formation and Its Effect on the Tensile Behavior of a High Pressure Die Cast Recycled Secondary AlSi10MnMg(Fe) Alloy

AbstractThe current study investigated the microstructure evolution, mechanical properties, and fracture behavior of a high pressure die cast (HPDC) novel secondary alloy. The as-cast microstructure comprised (i) Primary α-Al, (ii) α-Al15(FeMn)3Si2 intermetallics, and (iii) Al–Si eutectics. The microstructure starting from the surface through the depth of the HPDC casting consisted of (i) fine-grained skin at surface, (ii) increased Al–Si eutectics at intermediate location, and (iii) coarse α-Al dendrites at center. Accordingly, the hardness increased from skin to the intermediate section and then decreased toward the center of the casting. The formation of skin layer was highly discontinuous, which was attributed to the complicated fluid flow pattern inside the die cavity. The skin layer indicated to slightly improve the strength of the HPDC alloy; however, it restricted the ductility of the material with a large variation. Such ductility behavior resulted from a fracture mechanism triggered by the inhomogeneous skin because of its poor bonding with the adjacent matrix. Even though the secondary alloy contained casting defects and α-Al15(FeMn)3Si2 intermetallics that are known to be driving factors for the fracture in such materials, the effects from the inhomogeneous skin turned out to be predominant in the current study.

Rapid-response electrochromic devices with self-wrinkling polyaniline for enhanced infrared emissivity modulation

Electrochromic devices (ECDs) based on polyaniline (PANI) can alter their optical properties reversely by varying applied voltages, showing great potential in infrared (IR) information concealment. However, the traditional ECD with a flat PANI layer tends to perform unsatisfactorily in IR emissivity regulation and response time, resulting in risks of information leakage and low transfer efficiency. To address these challenges, a wrinkled microstructure is incorporated into the PANI layer (PANI-W) of the ECD (ECD-W) through a self-wrinkling method. Theoretic simulations combined with experimental results verify that the PANI-W endows an enhanced antireflection effect and a more complete redox degree. As a result, the ECD-W exhibits an exceptional IR emissivity modulation (0.375) and a short response time (1.8 s/2.6 s), allowing it to realize a temperature modulation of 8.9 °C. Moreover, various patterned and anti-patterned ECDs-W are feasibly prepared without masks, and more complicated patterns can be realized by erasing the unnecessary part of PANI-W on the ECDs-W. Two encryption/decryption strategies based on these ECDs-W are presented to provide more secure ways for IR information concealment. This research offers guidance to achieve high-performance ECDs with more effective spectrum regulation and faster responses, showing great potential in thermal regulation and IR information protection.

Unveiling the True Price: Assessing the Economic Impact of Cosmetic Surgery Tourism on a Single Tertiary Center in Bahrain

Abstract Background In light of the escalating cost of cosmetic surgery in Bahrain, the burgeoning “Cosmetic Surgery Tourism” sector has captured the attention of many Bahrainis. Neighboring countries aggressively promote affordable packages on numerous social media platforms, luring individuals with the allure of a vacation experience. However, insufficient postoperative care abroad has far-reaching implications that jeopardize both patient well-being and the integrity of the healthcare system. Objectives This study aims to assess the present patterns of complications related to cosmetic surgery tourism and the resulting financial burden on the Bahraini healthcare system. Methods A retrospective cost analysis and chart review were performed for all patients who presented with complaints associated with cosmetic surgeries between January 2018 and September 2023. After identifying patient demographics, procedure characteristics, admission data, length of stay, and intervention needs, a comprehensive cost analysis was conducted. Results A total of thirty patients manifested complications. Complications associated with abdominoplasty were the most prevalent. Iran emerged as the most frequented destination, with Egypt and Turkey following in order of prevalence. Surgical-site infections constituted the most common complications. Required interventions included admission for intravenous antibiotics, hyperbaric wound care, implant removal, and critical care admission. The projected expense to the hospital was 65,970 BHD (175,000 USD), equating to an average expenditure of 2,200 BHD (5,852 USD) per patient. Conclusions The allure of cost-effective cosmetic treatments often leads to complications that impose substantial economic burdens. The study concludes with policy recommendations to balance individuals’ freedom to seek healthcare abroad with long-term sustainability and equitable access to Bahrain's healthcare system.

A survey on feature extraction and learning techniques for link prediction in homogeneous and heterogeneous complex networks

Complex networks are commonly observed in several real-world areas, such as social, biological, and technical systems, where they exhibit complicated patterns of connectedness and organised clusters. These networks have intricate topological characteristics that frequently elude conventional characterization. Link prediction in complex networks, like data flow in telecommunications networks, protein interactions in biological systems, and social media interactions on platforms like Facebook, etc., is an essential element of network analytics and presents fresh research challenges. Consequently, there is a growing emphasis in research on creating new link prediction methods for different network applications. This survey investigates several strategies related to link prediction, ranging from feature extraction based to feature learning based techniques, with a specific focus on their utilisation in dynamic and developing network topologies. Furthermore, this paper emphasises on a wide variety of feature learning techniques that go beyond basic feature extraction and matrix factorization. It includes advanced learning-based algorithms and neural network techniques specifically designed for link prediction. The study also presents evaluation results of different link prediction techniques on homogeneous and heterogeneous network datasets, and provides a thorough examination of existing methods and potential areas for further investigation.

Collapsible tree: interactive web app to present collapsible hierarchies.

A crucial component of intuitive data visualization is presenting a hierarchical tree structure with interactive functions. For example, single-cell transcriptomics studies may generate gene expression values with developmental trajectories or cell lineage structures. Two common visualization methods, t-SNE and UMAP, require two separate figures to depict the distribution of cell types and gene expression data, with low-dimension projections that may not capture the hierarchical structures among cells. Here, we present a JavaScript framework and an interactive web app named Collapsible Tree, which presents values jointly with interactive, expandable, and collapsible lineage structures. For example, the Collapsible Tree presents cellular states and gene expression from single-cell transcriptomics within a single hierarchical plot, enabling comparisons of gene expression across lineages and subtle patterns between sub-lineages. Our framework can facilitate the exploration of complicated value patterns that are not evident in UMAP or t-SNE plots. The Collapsible Tree web interface is available at https://collapsibletree.data2in.net. The JavaScript library source code is available at https://github.com/data2intelligence/collapsible_tree.

ANALYZING USER BEHAVIOR PATTERNS FOR PERSONALIZED RECOMMENDER SYSTEMS IN E-COMMERCE: A LITERATURE REVIEW

Abstract: E-commerce thrives on a user-centric strategy, and recommender systems are at the cutting edge of personalizing the purchasing experience. These systems may forecast preferences and recommend appropriate items by analyzing user behavior patterns, resulting in many benefits such as increased customer satisfaction, increased sales and conversions, and increased efficiency. To accomplish these benefits, recommender systems utilize complex algorithms that examine numerous elements of user behavior such as purchase history, browsing behavior, search queries, demographic data, and implicit feedback. Sophisticated algorithms can recognise complicated patterns in user data, resulting in more accurate and personalized suggestions. Analyzing user reviews, product descriptions, and social media interactions may help you better understand consumer preferences and product features. Systems can make real-time suggestions depending on a user’s current browsing session, resulting in a more dynamic purchasing experience. Personalized recommender systems will play an increasingly important role in molding the future of e-commerce as user behavior analysis techniques are constantly refined. The study intends to make important advances to the field of personalized recommender systems by undertaking a thorough research of user behavior patterns in the e-commerce domain. We strive to improve the performance of recommender systems by extracting insightful features from various data sources and exploring sophisticated machine learning techniques, resulting in a more engaging and tailored user experience that fosters customer satisfaction and drives business growth. A comprehensive review of user behavior patterns and their influence on personalized recommender systems in the e-commerce industry reveals the critical role of data analysis and machine learning algorithms in tailoring product suggestions to individual preferences, thereby enhancing customer satisfaction and driving sales growth. By implementing the tactics and approaches expressed in this study, e-commerce platforms may stay ahead of the curve, providing a smooth and tailored purchasing experience that surpasses customer expectations and contributes to their competitive advantage in the changing e-commerce environment.

High-Resolution Genome-Wide Mapping of Chromatin Accessibility and Torsional Stress.

Torsional stress in chromatin plays a fundamental role in cellular functions, influencing key processes such as transcription, replication, and chromatin organization. Transcription and other processes may generate and be regulated by torsional stress. In the genome, the interplay of these processes creates complicated patterns of both positive (+) and negative (-) torsion. However, a challenge in generating an accurate torsion map is determining the zero-torsion baseline signal, which is conflated with chromatin accessibility. Here, we introduce a high-resolution method based on the intercalator trimethylpsoralen (TMP) to address this challenge. We describe a method to establish the zero-torsion baseline while preserving the chromatin state of the genome. This approach enables both high-resolution mapping of accessibility and torsional stress in chromatin in the cell. Our analysis reveals transcription-generated torsional domains consistent with the twin-supercoiled-domain model of transcription and suggests a role for torsional stress in recruiting topoisomerases and in regulating 3D genome architecture via cohesin. This new method provides a potential path forward for using TMP to measure torsional stress in the genome without the confounding contribution of accessibility in chromatin.

Deep Learning-Adjusted Monitoring of In-Hospital Mortality after Liver Transplantation.

Background: Surgeries represent a mainstay of medical care globally. Patterns of complications are frequently recognized late and place a considerable burden on health care systems. The aim was to develop and test the first deep learning-adjusted CUSUM program (DL-CUSUM) to predict and monitor in-hospital mortality in real time after liver transplantation. Methods: Data from 1066 individuals with 66,092 preoperatively available data point variables from 2004 to 2019 were included. DL-CUSUM is an application to predict in-hospital mortality. The area under the curve for risk adjustment with Model of End-stage Liver Disease (D-MELD), Balance of Risk (BAR) score, and deep learning (DL), as well as the ARL (average run length) and control limit (CL) for an in-control process over 5 years, were calculated. Results: D-MELD AUC was 0.618, BAR AUC was 0.648 and DL model AUC was 0.857. CL with BAR adjustment was 2.3 with an ARL of 326.31. D-MELD reached an ARL of 303.29 with a CL of 2.4. DL prediction resulted in a CL of 1.8 to reach an ARL of 332.67. Conclusions: This work introduces the first use of an automated DL-CUSUM system to monitor postoperative in-hospital mortality after liver transplantation. It allows for the real-time risk-adjusted monitoring of process quality.

Experimental investigation on the three-dimensional liquid sloshing behavior in an offshore circular cylindrical container

A series of experimental cases are conducted to explore the three-dimensional sloshing response in a cylindrical container under lateral excitation. When the forcing frequency is in the vicinity of the resonance frequency of the lowest asymmetric mode (1, 1), three different wave regimes are observed: planar, irregular and swirling. The results of the wave regimes at the second asymmetric mode (1, 2) exhibit a number of similarities to those at the mode (1, 1), such as the generation of irregular mode and swirling mode at the forcing frequency close to the resonance frequency of mode (1, 2). The present experiments also exhibit some spectacular phenomena that are unique to the resonant sloshing at the mode (1, 2). In particular, when the sloshing wave builds up sufficient energy, the energy will be transferred to adjacent natural modes, i.e., (3, 1) and (2, 2). As a consequence, the motion of the sloshing wave is dominated by three natural modes and exhibits very complicated wave patterns.

Association between Patterns of Mandibular Third Molar Impaction and Various complications in the Adjacent Second Molar Using Cone Beam Computed Tomography: A Retrospective Study

Association between Patterns of Mandibular Third Molar Impaction and Various complications in the Adjacent Second Molar Using Cone Beam Computed Tomography: A Retrospective Study

The coexistence of low muscle mass and obesity evaluated by dual energy X-ray absorptiometry, rather than low muscle mass or obesity alone, is associated with macrovascular but not microvascular complications in patients with type 2 diabetes mellitus.

The prevalence of the coexistence of low muscle mass and obesity is increasing, particularly with a rising trend observed in patients diagnosed with type 2 diabetes mellitus (T2DM). However, the association between the coexistence of low muscle mass and obesity and diabetic complications remains unclear. This study aimed to investigate these associations in patients with T2D. A retrospective study was conducted, including 2387 hospitalized patients with T2DM. Data on demographic characteristics, biochemical parameters, diabetic complications and body composition was from electronic health records. The participants were categorized as control, low muscle mass, obesity and the coexistence of the low muscle mass and obesity groups according to the body compositions evaluated by dual-energy X-ray absorptiometry. Multiple logistic regression models were applied to assess the associations between the pattern of body composition and complications of diabetes. After adjustment for potential confounders, compared with patients in the control group, the odds ratios [95% confidence intervals (CIs)] of macrovascular complications of diabetes were 0.62 (95% CI, 0.27-1.39) for those in the low muscle mass group, 1.12 (95% CI, 0.59-2.11) in the obesity group, and 2.43 (95% CI, 1.16-5.07) in the coexistence of the low muscle mass and obesity group, respectively; the odds ratios (95% CIs) of microvascular complications of diabetes were 0.86 (95% CI, 0.52-1.43) for those in the low muscle mass group, 0.82 (95% CI, 0.53-1.26) in the obesity group, and 1.21 (95% CI, 0.69-2.15) in the coexistence of the low muscle mass and obesity group, respectively. According to our findings, the coexistence of low muscle mass and obesity, rather than low muscle mass or obesity alone, was significantly associated with a higher prevalence of macrovascular complications in hospitalized patients with T2DM. This association was not observed for diabetic microvascular complications.

A Pattern and Incidence Study of Complications after Emergency Laparotomy

Background and Objectives: The study of emergency laparotomies are being carried out prospectively at the Department of General Surgery at a tertiary care facility affiliated with the Parul Institute of Medical Science and Research (Parul Sevasharam Hospital). Methods: A tertiary care teaching hospital’s Department of General Surgery conducted a prospective study involving 100 emergency laparotomy cases from July 2020 to May 2021. Every patient underwent surgery using a midline vertical incision. The main aim of the study is to identify various complications occurring following emergency laparotomies and various factors influencing them. All patients followed up at least for a period of 6 months after surgery. Results: 60 patients developed one or more complications postoperatively, 19 (31.7%) patients had abdominal complications; 34 (56.7%) had wound complications; 12 (20%) had chest complications and 4 (6.7%) had limb complications Conclusion: Even with the availability of safe anaesthetic, broad range of antibiotics, and advanced experimental or investigational devices, the risk of complications and mortality from emergency laparotomies remains significant. Chest problems were associated with a higher postoperative mortality rate than wound, limb, or abdomen complications.

Combining clinical and molecular data for personalized treatment in acute myeloid leukemia: A machine learning approach

Background and ObjectiveThe standard of care in Acute Myeloid Leukemia patients has remained essentially unchanged for nearly 40 years. Due to the complicated mutational patterns within and between individual patients and a lack of targeted agents for most mutational events, implementing individualized treatment for AML has proven difficult. We reanalysed the BeatAML dataset employing Machine Learning algorithms. The BeatAML project entails patients extensively characterized at the molecular and clinical levels and linked to drug sensitivity outputs. Our approach capitalizes on the molecular and clinical data provided by the BeatAML dataset to predict the ex vivo drug sensitivity for the 122 drugs evaluated by the project. MethodsWe utilized ElasticNet, which produces fully interpretable models, in combination with a two-step training protocol that allowed us to narrow down computations. We automated the genes’ filtering step by employing two metrics, and we evaluated all possible data combinations to identify the best training configuration settings per drug. ResultsWe report a Pearson correlation across all drugs of 0.36 when clinical and RNA sequencing data were combined, with the best-performing models reaching a Pearson correlation of 0.67. When we trained using the datasets in isolation, we noted that RNA Sequencing data (Pearson: 0.36) attained three times the predictive power of whole exome sequencing data (Pearson: 0.11), with clinical data falling somewhere in between (Pearson 0.26). Lastly, we present a paradigm of clinical significance. We used our models’ prediction as a drug sensitivity score to rank an individual's expected response to treatment. We identified 78 patients out of 89 (88 %) that the proposed drug was more potent than the administered one based on their ex vivo drug sensitivity data. ConclusionsIn conclusion, our reanalysis of the BeatAML dataset using Machine Learning algorithms demonstrates the potential for individualized treatment prediction in Acute Myeloid Leukemia patients, addressing the longstanding challenge of treatment personalization in this disease. By leveraging molecular and clinical data, our approach yields promising correlations between predicted drug sensitivity and actual responses, highlighting a significant step forward in improving therapeutic outcomes for AML patients.

VTNet: A multi-domain information fusion model for long-term multi-variate time series forecasting with application in irrigation water level

Time series forecasting is intricately tied to production and life, garnering widespread attention over an extended period. Enhancing the performance of long-term multivariate time series forecasting (MTSF) poses a highly challenging task, as it requires mining complicated and obscure temporal patterns in many aspects. For this reason, this paper proposes a long-term forecasting model based on multi-domain fusion (VTNet) to adaptively capture and refine multi-scale intra- and inter-variate dependencies. In contrast to previous techniques, we devise a dual-stream learning architecture. Firstly, the fast Fourier Transform (FFT) is adopted to extract frequency domain information. The original sequences are then transformed into 2D visual features in the temporal-frequency domain, and a 2D-TBlock is designed for multi-scale dynamic learning. Secondly, a combination of convolution and recurrent networks continues to explore the local temporal features and preserve the global trend. Finally, multi-modal circulant fusion is applied to achieve a more comprehensive and enriched feature fusion representation, further promoting overall performance. Extensive experiments are conducted on 9 public benchmark datasets and the real-world irrigation water level to showcase VTNet’s promoted performance and generalization. Moreover, VTNet yields 46.93% and 25.36% relative improvements for water level forecasting, revealing its potential application value in water-saving planning and extreme event early warning.