Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model.

Deep vein thrombosis (DVT) represents a critical health concern due to its potential to lead to pulmonary embolism, a life-threatening complication. Early identification and prediction of DVT are crucial to prevent thromboembolic events and implement timely prophylactic measures in high-risk individuals. This study aims to examine the risk determinants associated with acute lower extremity DVT in hospitalized individuals. Additionally, it introduces an innovative approach by integrating Q-learning augmented colony predation search ant colony optimizer (QL-CPSACO) into the analysis. This algorithm, then combined with support vector machines (SVM), forms a bQL-CPSACO-SVM feature selection model dedicated to crafting a clinical risk prognostication model for DVT. The effectiveness of the proposed algorithm's optimization and the model's accuracy are assessed through experiments utilizing the CEC 2017 benchmark functions and predictive analyses on the DVT dataset. The experimental results reveal that the proposed model achieves an outstanding accuracy of 95.90% in predicting DVT. Key parameters such as D-dimer, normal plasma prothrombin time, prothrombin percentage activity, age, previously documented DVT, leukocyte count, and thrombocyte count demonstrate significant value in the prognostication of DVT. The proposed method provides a basis for risk assessment at the time of patient admission and offers substantial guidance to physicians in making therapeutic decisions.

Enhancing gastric cancer early detection: A multi-verse optimized feature selection model with crossover-information feedback.

Gastric cancer (GC), an acknowledged malignant neoplasm, threatens life and digestive system functionality if not detected and addressed promptly in its nascent stages. The indispensability of early detection for GC to augment treatment efficacy and survival prospects forms the crux of this investigation. Our study introduces an innovative wrapper-based feature selection methodology, referred to as bCIFMVO-FKNN-FS, which integrates a crossover-information feedback multi-verse optimizer (CIFMVO) with the fuzzy k-nearest neighbors (FKNN) classifier. The primary goal of this initiative is to develop an advanced screening model designed to accelerate the identification of patients with early-stage GC. Initially, the capability of CIFMVO is validated through its application to the IEEE CEC benchmark functions, during which its optimization efficiency is measured against eleven cutting-edge algorithms across various dimensionalities-10, 30, 50, and 100. Subsequent application of the bCIFMVO-FKNN-FS model to the clinical data of 1632 individuals from Wenzhou Central Hospital-diagnosed with either early-stage GC or chronic gastritis-demonstrates the model's formidable predictive accuracy (83.395%) and sensitivity (87.538%). Concurrently, this investigation delineates age, gender, serum gastrin-17, serum pepsinogen I, and the serum pepsinogen I to serum pepsinogen II ratio as parameters significantly associated with early-stage GC. These insights not only validate the efficacy of our proposed model in the early screening of GC but also contribute substantively to the corpus of knowledge facilitating early diagnosis.

Enhanced Runge-Kutta-driven feature selection model for early detection of gastroesophageal reflux disease.

Gastroesophageal reflux disease (GERD) profoundly compromises the quality of life, with prolonged untreated cases posing a heightened risk of severe complications such as esophageal injury and esophageal carcinoma. The imperative for early diagnosis is paramount in averting progressive pathological developments. This study introduces a wrapper-based feature selection model based on the enhanced Runge Kutta algorithm (SCCRUN) and fuzzy k-nearest neighbors (FKNN) for GERD prediction, named bSCCRUN-FKNN-FS. Runge Kutta algorithm (RUN) is a metaheuristic algorithm designed based on the Runge-Kutta method. However, RUN's effectiveness in local search capabilities is insufficient, and it exhibits insufficient convergence accuracy. To enhance the convergence accuracy of RUN, spiraling communication and collaboration (SCC) is introduced. By facilitating information exchange among population individuals, SCC expands the solution search space, thereby improving convergence accuracy. The optimization capabilities of SCCRUN are experimentally validated through comparisons with classical and state-of-the-art algorithms on the IEEE CEC 2017 benchmark. Subsequently, based on SCCRUN, the bSCCRUN-FKNN-FS model is proposed. During the period from 2019 to 2023, a dataset comprising 179 cases of GERD, including 110 GERD patients and 69 healthy individuals, was collected from Zhejiang Provincial People's Hospital. This dataset was utilized to compare our proposed model against similar algorithms in order to evaluate its performance. Concurrently, it was determined that features such as the internal diameter of the esophageal hiatus during distention, esophagogastric junction diameter during distention, and external diameter of the esophageal hiatus during non-distention play crucial roles in influencing GERD prediction. Experimental findings demonstrate the outstanding performance of the proposed model, with a predictive accuracy reaching as high as 93.824 %. These results underscore the significant advantage of the proposed model in both identifying and predicting GERD patients.

Assessment of laparoscopic intracorporeal intestinal anastomosis training using simulation-based 3D printed models: exploring surgical performance and learning curves.

BACKGROUND AND AIMS: Intestinal anastomosis is a clinical procedure widely used to reconstruct the digestive tract, but authentic laparoscopic intracorporeal intestinal anastomosis (LIIA) models are lacking. However, three-dimensional (3D) printing can enable authentic and reusable models. In this paper, a novel cost-effective 3D-printing training model of LIIA is designed and the authenticity and validity of the model are tested. METHODS: A fused deposition modeling 3D printing and an assembled lab model were built to test LIIA. Fifteen surgeons were required to perform LIIA, and their operation score and time were recorded and analyzed. Five experts were invited to assess the face and content validity of the models. A study was also performed to further evaluate and validate the learning curve of surgeons. RESULTS: The difference in modified anastomosis objective structured assessment of technical skills (MAOSATS) scores between the expert, intermediate, and novice groups were significant (64.1±1.8: 48.5±1.7: 29.5±3.1, P <0.001). In addition, the operation time of the procedure was statistically different for all three groups (21.5±1.9: 30.6±2.8:70.7±4.0, P<0.001 ). The five experts rated the face and content validity of the model very highly, with the median being four out of five. Surgeons who underwent repeated training programs showed improved surgical performance. After eight training sessions, the novices' performance was similar to that of the average level of untrained intermediates, while the operation scores of the intermediates were close to that of the average level of experts. CONCLUSIONS: In this study, it is found that the LIIA model exhibits excellent face, content, and construct validity. Repeated simulation training of the LIIA training program improved the surgeon's operative performance, so the model is considered one of the most effective methods for LIIA training and assessment of surgical quality in the future and for reducing healthcare costs.

Sources of information on surgical options for patients undergoing antireflux surgery: a single-center questionnaire-based survey.

BACKGROUND: To explore the sources of information on antireflux surgery for patients undergoing this surgery in China. METHODS: Patients who underwent antireflux surgery in the Gastroesophageal Reflux Center of the Zhejiang Provincial People's Hospital from January 2016 to June 2021 were selected as survey subjects, and a questionnaire survey was conducted by telephone. RESULTS: A total of 358 questionnaires were distributed, and 320 valid questionnaires were recovered, yielding a 89.4% completion rate. Among patients' sources of information about antireflux surgery, the media was the primary source (33.8%) followed by recommendations from relatives or friends (27.8%), referrals from physicians (23.4%) and other sources (15.0%). Patients of different ages and educational levels have different sources for obtaining information about the procedure. Most of the information on surgery for patients aged 20 to 49 years was derived from recommendations from friends or relatives, whereas most of the information on surgery for patients aged 50 to 80 years was obtained from the media. Most of the information on surgery for patients with a primary school education or less was derived from physicians' recommendations, whereas most of the information for patients with a junior secondary school education or higher was obtained from the media. The recommendation of patients for surgery varied among the different departments (X2 = 36.011, p < 0.001), and a two-to-two comparison found that the recommended rates for cardiology and gastroenterology differed from the rates of other groups (p < 0.001, Table 2). CONCLUSIONS: The results of this investigation show that a large number of patients who underwent antireflux surgery learned about the operation through the media and recommendations from relatives or friends rather than physicians at the hospital. Notably, physicians specializing in GERD need to increase their knowledge of the disease and surgical treatment options to provide correct medical information to patients and to conduct media campaigns.

Development and evaluation of a portable and soft 3D-printed cast for laparoscopic choledochojejunostomy model in surgical training.

BACKGROUND: Laparoscopic choledochojejunostomy (LCJ) is an essential basic skill for biliary surgeons. Therefore, we established a convenient and effective LCJ 3D printing model to evaluate whether the model could simulate the actual operation situation and determine its effectiveness and validity in surgical training. METHODS: A 3D printing dry laboratory model was established to simulate LCJ. The face and content validity of the model were evaluated by six experienced biliary surgeons based on 5-point Likert scale questionnaires. A total of 15 surgeons with different levels of experience performed LCJ on the model and evaluated the structural validity of the model using the objective structured assessment of technical skills (OSATS). Simultaneously, the operation time of each surgery was also recorded. A study was also performed to further evaluate the learning curve of residents. RESULTS: The operating space score of the model was 4.83 ± 0.41 points. The impression score of bile duct and intestinal canal was 4.33 ± 0.52 and 4.17 ± 0.41 points, respectively. The tactile sensation score of bile duct suture and intestinal canal suture was 4.00 ± 0.63 and 3.83 ± 0.41points, respectively. The OSATS score for model operation in the attending group was 29.20 ± 0.45 points, which was significantly higher than that in the fellow group (26.80 ± 1.10, P = 0.007) and the resident group (19.80 ± 1.30, P < 0.001). In addition, there was a statistical difference in operation time among surgeons of different experience levels (P < 0.05). Residents could significantly improve the surgical score and shorten the time of LCJ through repeated training. CONCLUSIONS: The 3D printing LCJ model can simulate the real operation scenes and distinguish surgeons with different levels of experience. The model is expected to be one of the training methods for biliary tract surgery in the future.

Validity of a Soft and Flexible 3D-Printed Nissen Fundoplication Model in Surgical Training.

Rapid development of three-dimensional (3D) printing technique has enabled the production of many new materials for medical applications but the dry laboratory surgical training model made of soft and flexible materials is still insufficient. We established a new 3D-printed Nissen fundoplication training model of which materials simulate the real mechanical properties. In this study, 16 participants were divided into two groups: Experimental group and control group. The validity of model was tested using Likert scale by the experts and the experimental group. To evaluate the efficacy, performances of the experimental group were scored at the first, fourth, and eighth training by OSATS system and the duration of procedure was compared through the use of recorded video. Meanwhile, an ex vivo model was used to compare the performance of the experiment group and control group after the training in the same way. Our results showed that the 3D-printed model can support the future surgical applications, help improve surgical skills, and shorten procedure time after training.

Performance optimization of support vector machine with oppositional grasshopper optimization for acute appendicitis diagnosis.

Preoperative differentiation of complicated and uncomplicated appendicitis is challenging. The research goal was to construct a new intelligent diagnostic rule that is accurate, fast, noninvasive, and cost-effective, distinguishing between complicated and uncomplicated appendicitis. Overall, 298 patients with acute appendicitis from the Wenzhou Central Hospital were recruited, and information on their demographic characteristics, clinical findings, and laboratory data was retrospectively reviewed and applied in this study. First, the most significant variables, including C-reactive protein (CRP), heart rate, body temperature, and neutrophils discriminating complicated from uncomplicated appendicitis, were identified using random forest analysis. Second, an improved grasshopper optimization algorithm-based support vector machine was used to construct the diagnostic model to discriminate complicated appendicitis (CAP) from uncomplicated appendicitis (UAP). The resultant optimal model can produce an average of 83.56% accuracy, 81.71% sensitivity, 85.33% specificity, and 0.6732 Matthews correlation coefficients. Based on existing routinely available markers, the proposed intelligent diagnosis model is highly reliable. Thus, the model can potentially be used to assist doctors in making correct clinical decisions.

Evolving kernel extreme learning machine for medical diagnosis via a disperse foraging sine cosine algorithm.

Kernel extreme learning machine (KELM) has been widely used in the fields of classification and identification since it was proposed. As the parameters in the KELM model have a crucial impact on performance, they must be optimized before the model can be applied in practical areas. In this study, to improve optimization performance, a new parameter optimization strategy is proposed, based on a disperse foraging sine cosine algorithm (DFSCA), which is utilized to force some portions of search agents to explore other potential regions. Meanwhile, DFSCA is integrated into KELM to establish a new machine learning model named DFSCA-KELM. Firstly, using the CEC2017 benchmark suite, the exploration and exploitation capabilities of DFSCA were demonstrated. Secondly, evaluation of the model DFSCA-KELM on six medical datasets extracted from the UCI machine learning repository for medical diagnosis proved the effectiveness of the proposed model. At last, the model DFSCA-KELM was applied to solve two real medical cases, and the results indicate that DFSCA-KELM can also deal with practical medical problems effectively. Taken together, these results show that the proposed technique can be regarded as a promising tool for medical diagnosis.

Evolving fuzzy k-nearest neighbors using an enhanced sine cosine algorithm: Case study of lupus nephritis.

Because of its simplicity and effectiveness, fuzzy K-nearest neighbors (FKNN) is widely used in literature. The parameters have an essential impact on the performance of FKNN. Hence, the parameters need to be attuned to suit different problems. Also, choosing more representative features can enhance the performance of FKNN. This research proposes an improved optimization technique based on the sine cosine algorithm (LSCA), which introduces a linear population size reduction mechanism for enhancing the original algorithm's performance. Moreover, we developed an FKNN model based on the LSCA, it simultaneously performs feature selection and parameter optimization. Firstly, the search performance of LSCA is verified on the IEEE CEC2017 benchmark test function compared to the classical and improved algorithms. Secondly, the validity of the LSCA-FKNN model is verified on three medical datasets. Finally, we used the proposed LSCA-FKNN to predict lupus nephritis classes, and the model showed competitive results. The paper will be supported by an online web service for any question at https://aliasgharheidari.com.

Long Noncoding RNA PCAT18 Upregulates SPRR3 to Promote Colorectal Cancer Progression by Binding to miR-759.

BACKGROUND: Long noncoding RNAs (lncRNAs) play essential functions in the development of several cancers, including colorectal cancer (CRC). Nevertheless, how PCAT18 regulates CRC tumorigenesis remains unclear. In this research, we aimed to investigate the roles of PCAT18 in CRC. MATERIALS AND METHODS: qRT-PCR and Western blot were used to analyze RNA and protein levels. CCK8, colony formation, transwell and wound healing assays were utilized to analyze proliferation, migration and invasion. Luciferase reporter assay was used to analyze RNA interactions. RESULTS: PCAT18 was found to be highly expressed in CRC tissues and cells. PCAT18 level was positively correlated with lymph node metastasis and TNM stage. Functionally, PCAT18 silencing induced impairment of CRC proliferation, migration and invasion. Besides, PCAT18 was identified to inhibit miR-759. PCAT18 promotes SPRR3 expression through binding to miR-759. Furthermore, miR-759 inhibitors or SPRR3 ectopic expression partially rescued the abilities of proliferation, migration and invasion in CRC cells transfected with sh-PCAT18. CONCLUSION: Therefore, our study demonstrated that PCAT18 contributes to CRC progression through regulating miR-759/SPRR3 axis, which provides a new theoretical basis of explaining CRC tumorigenesis.

Circular RNA hsa_circRNA_102958 promotes tumorigenesis of colorectal cancer via miR-585/CDC25B axis.

Purpose: Circular RNAs (circRNAs) are recently identified new noncoding RNAs and play an important role in tumorigenesis. Previous studies have indicated that hsa_circRNA_102958 is a potential diagnostic indicator in gastric cancer. However, its role in colorectal cancer (CRC) is poorly understood. Methods: qRT-PCR and ISH were used to test gene expression in tissues. Survival rate was analzyed by Kaplan-Meier curve. Luciferase reporter assay was used to determine the interaction between circRNA and miRNA or between miRNA and mRNA. Western blotting was used to test protein expression. CCK8 and colony formation assay was used to analyze proliferation. Transwell assay was used for migration and invasion determination. Results: In our research, we found that hsa_circRNA_102958 expression was significantly increased in CRC tissues, compared to adjacent normal controls. Increased hsa_circRNA_102958 levels in CRC patients indicated a poor prognosis. The effects of hsa_circRNA_102958 on CRC cell proliferation, migration and invasion were then determined by CCK8, colony formation and Transwell assays. We showed that hsa_circRNA_102958 silencing markedly suppressed CRC growth, migration and invasion. Furthermore, hsa_circRNA_102958 was identified as a sponge for miR-585. We demonstrated that hsa_circRNA_102958 promoted CDC25B expression through inhibiting miR-585 in CRC. Rescue assays illustrated that CDC25B overexpression reversed the suppressive effects of hsa_circRNA_102958 silencing on CRC. Conclusion: Taken together, our findings revealed the novel oncogenic roles of hsa_circRNA_102958 in CRC through miR-585/CDC25B axis.

KMT2A histone methyltransferase contributes to colorectal cancer development by promoting cathepsin Z transcriptional activation.

Accumulating evidence supports the notion that epigenetic modifiers are abnormal in carcinogenesis and have a fundamental role in cancer progression. Among these aberrant epigenetic modifiers, the function of histone methyltransferase KMT2A in somatic tumors is not well known. By analyzing KMT2A expression in patient tissues, we demonstrated that KMT2A was overexpressed in colorectal cancer tissues in comparison with adjacent normal tissues and its expression was positively correlated with cancer stages. In KMT2A-knockdown HCT116 and DLD1 cells, cell invasion and migration were consequently suppressed. In addition, KMT2A depletion effectively suppressed cancer metastasis in vivo. Mechanistically, cathepsin Z (CTSZ) was demonstrated to be an important downstream gene of KMT2A. Further studies showed that p65 could recruit KMT2A on the promoter region of the downstream gene CTSZ and knockdown of p65 could reduce the KMT2A on the promoter of CTSZ. Finally, our present study revealed that KMT2A epigenetically promotes cancer progression by targeting CTSZ, which has specific functions in cancer invasion and metastasis.

Long noncoding RNA lncBRM promotes proliferation and invasion of colorectal cancer by sponging miR-204-3p and upregulating TPT1.

Long noncoding RNAs (lncRNAs) are characterized as a type of noncoding RNAs over 200 nucleotides with little or none protein-coding potential. In the past years, lncRNAs have been proved to participant in many physiological and pathological processes. However, the role of lncRNAs in colorectal cancer (CRC) still needs more attentions. In our study, we found that lncBRM was highly expressed in CRC samples and the expression level of lncBRM was correlated with metastasis and advanced stage in CRC patients. And also, we showed that high expression of lncBRM predicted poor prognosis. Furthermore, we found that knockdown of lncBRM impaired the proliferation, migration and invasion of CRC cells while overexpressing of lncBRM promotes the proliferation, migration and invasion of CRC cells. Mechanically, we found that lncBRM served as a sponge of miR-204-3p that targeted TPT1. Highly expressed TPT1 can promote the proliferation, migration and invasion of CRC cells. In conclusion, we found that lncBRM was highly expressed in CRC and sponged miR-204-3p to modulate the expression of TPT1.

miR­3666 suppresses cellular proliferation and invasion in colorectal cancer by targeting SATB2.

MicroRNA­3666 (miR­3666) acts as a tumor suppressor in cervical cancer, non­small cell lung cancer and thyroid carcinoma; however, the function of miR­3666 in colorectal cancer (CRC) remains largely unknown. In the present study, was demonstrated that miR­3666 was significantly downregulated in CRC tissues compared with in adjacent normal tissues by reverse transcription­quantitative polymerase chain reaction. Additionally, miR­3666 may serve as a prognostic biomarker for patients with CRC. Via functional experiments, the present study reported that miR­3666 overexpression significantly inhibited the proliferation, migration and invasion of CRC cells as determined by Cell Counting Kit­8 and Transwell assays, and vice versa. In addition, miR­3666 was reported to directly target special AT­rich sequence binding protein 2 (SATB2) in CRC cells; overexpression of miR­3666 significantly suppressed the expression of SATB2 in CRC cells as determined by western blotting. Furthermore, an inverse correlation was observed between the expression levels of miR­3666 and SATB2 in CRC tissues. Restoration of SATB1 expression significantly reversed the effects of miR­3666 mimic on CRC cells. In summary, the results of the present study indicated that miR­3666 may serve as a tumor suppressor in CRC by targeting SATB2.

Ultrasound-based differentiation of malignant and benign thyroid Nodules: An extreme learning machine approach.

BACKGROUND AND OBJECTIVES: It is important to be able to accurately distinguish between benign and malignant thyroid nodules in order to make appropriate clinical decisions. The purpose of this study was to improve the effectiveness and efficiency for discriminating the malignant from benign thyroid cancers based on the Ultrasonography (US) features. METHODS: There were 114 benign nodules in 106 patients (82 women and 24 men) and 89 malignant nodules in 81 patients (69 women and 12 men) included in this study. The potential of extreme learning machine (ELM) has been explored for the first time to discriminate malignant and benign thyroid nodules based on the sonographic features in ultrasound images. The influence of two key parameters (the number of hidden neurons and type of activation function) on the performance of ELM was investigated. The relationship between feature subsets obtained by the feature selection method and the classification performance of ELM was also examined. A real-life dataset was used to evaluate the effectiveness of the proposed method in terms of classification accuracy, sensitivity, specificity, and area under the ROC (receiver operating characteristic) curve (AUC). RESULTS: The results demonstrate that there are significant differences between the malignant and benign thyroid nodules (p-value<0.01), the most discriminative features are echogenicity, calcification, margin, composition and shape. Compared with other methods, the proposed method not only has achieved very promising classification accuracy via 10-fold cross-validation (CV) scheme, but also greatly reduced the computational cost compared to other counterparts. The proposed ELM-based approach achieves 87.72% ACC, 0.8672 AUC, 78.89% sensitivity, and 94.55% specificity. CONCLUSIONS: Based on the empirical analysis, the proposed ELM-based approach for thyroid cancer detection has promising potential in clinical use, and it can be of assistance as an optional tool for the clinicians.