Computational and Mathematical Methods in Medicine

Purposes. This research explores the game-based intelligent test (GBIT), predicts the possibilities of Mini-Mental State Examination (MMSE) scores and the risk of cognitive impairment, and then verifies GBIT as one of the reliable and valid cognitive assessment tools. Methods. This study recruited 117 elderly subjects in Taiwan (average age is , average height is , average weight is , and average MMSE score is ). A multiple regression model was used to analyze the GBIT parameters of the elderly’s reaction, attention, coordination, and memory to predict their MMSE performance. The binary logistic regression was then utilized to predict their risk of cognitive impairment. The statistical significance level was set as . Results. Multiple regression analysis showed that gender, the correct number of reactions, and the correct number of memory have a significantly positive predictive power on MMSE of the elderly (, , and ). Binary logistic regression analysis noted that the correct average number of reactions falls by one question, and the ratio of cognitive dysfunction risk increases 1.09 times (); the correct average number of memory drops by one question, the ratio of cognitive dysfunction risk increases 3.76 times (), and the overall model predictive power is 88.20% (sensitivity: 84.00%; specificity: 92.30%). Conclusions. This study verifies that GBIT is reliable and can effectively predict the cognitive function and risk of cognitive impairment in the elderly. Therefore, GBIT can be used as one of the feasible tools for evaluating older people’s cognitive function.

Background. Modification of N⁶-methyladenosine (m⁶A) and RNA m⁶A regulatory factors is required in cancer advancement. The contribution of m⁶A and its alteration in esophageal squamous cell carcinoma (ESCC) is still unclear. Results. ALKBH5 was lowly expressed in ESCC tissues, which the total m⁶A level was increased in ESCC tissue than the presentation in normal healthy tissue. The pcDNA3.1-ALKBH5 recombinant plasmid was transfected into KYSE-150 and Eca-109 cells. The overexpression of ALKBH5 is responsible for a significant reduction of the total m⁶A levels in Eca-109 and KYSE150 cells, inhibiting the proliferation capability, migration, and cell invasion. Conclusions. ALKBH5 as a demethylase was lowly expressed in cancer progression of ESCC and acts as a crucial component in ESCC progression.

This study was to explore the CT image features based on intelligent algorithm to evaluate continuous blood purification in the treatment of severe sepsis caused by pulmonary infection and nursing. 50 patients in the hospital were selected as the research objects. Convolutional neural network algorithm was used to segment CT images of severe sepsis caused by pulmonary infection. They were randomly divided into 25 cases of experimental group and 25 cases of control group. The experimental group was given continuous blood purification treatment, combined with comprehensive nursing. The control group was given routine treatment and basic nursing. Fasting plasma glucose (FPG) and fasting insulin (FIN), interleukin-6 (IL-6), tumor necrosis factor (TNF-α), high-sensitivity c-reactive protein (hs-CRP) levels, CD₃⁺, CD₄⁺, CD₄^+/CD₈⁺ levels, ICU monitoring time, malnutrition inflammation score (MIS), and incidence of adverse events were compared between the two groups before and after treatment. There was no difference in FPG and FIN between the two groups before treatment. After treatment, the FPG and FIN of the experimental group were lower than those of the control group, and there was statistical significance (). There was no difference in IL-6, TNF-α, and hs-CRP between the two groups before treatment. After treatment, IL-6, TNF-α, and hs-CRP in the experimental group were lower than those in the control group. There was no difference in the percentage of CD₃⁺, CD₄⁺, and CD₄^+/CD₈⁺ between the two groups before treatment. After treatment, the CD₃⁺, CD₄⁺, and CD₄⁺/CD₈⁺ in the experimental group were higher than those in the control group. The ICU monitoring time, MIS, and incidence of adverse events in the experimental group were lower than those in the control group (). Convolutional neural network algorithm can accurately identify and segment CT images of patients with severe sepsis, which has high clinical application value. Continuous blood purification therapy can effectively control blood glucose level, improve immune function, and reduce the content of inflammatory factors in patients with severe sepsis caused by pulmonary infection. Effective nursing measures can improve the therapeutic effect.

Introduction. The carotid region is encountered in vascular and neurological surgery and carries a potential for vascular and cranial nerve trauma. The carotid bifurcation is an especially important landmark and difficult to predict based on currently established landmarks. This study is a detailed analysis of the carotid region and proposes a novel methodology to predict the height of the bifurcation. Materials and Methods. Superficial and deep dissections were performed on the anterior triangle of the neck to expose the carotid region in twenty-one formalin-fixed donor cadavers. Musculoskeletal and neurovascular structures were assessed in relation to the carotid bifurcation and the medial border of the clavicle (MBC). Results. The carotid bifurcation occurred, on average, 11.4 mm higher on the left (; 95% CI: 9.28, 13.54). The superior thyroid artery (), facial vein (), and cranial nerve XII () were all more distal on the left side when measured from the MBC while the angle of the mandible and stylohyoid muscle remained symmetric. Left- and right-sided vascular structures were symmetric when measured from the carotid bifurcation. Conclusions. Neurovascular structures within the carotid region are likely to be anatomically superior on the left side while vessels are likely to remain symmetric in relation to the carotid bifurcation. When measured from the MBC, the bifurcation height can be predicted by multiplying the distance between the MBC and mastoid process by 0.65 (right side) or 0.74 (left side). This novel methodological estimation may be easily learned and directly implemented in clinical practice.

The chronic pain of knee osteoarthritis in the elderly is investigated in detail in this paper, as well as the complexity of chronic pain utilising neuroimaging recognition techniques. Chronic pain in knee osteoarthritis (KOA) has a major effect on patients’ quality of life and functional activities; therefore, understanding the causes of KOA pain and the analgesic advantages of different therapies is important. In recent years, neuroimaging techniques have become increasingly important in basic and clinical pain research. Thanks to the application and development of neuroimaging techniques in the study of chronic pain in KOA, researchers have found that chronic pain in KOA contains both injury-receptive and neuropathic pain components. The neuropathic pain mechanism that causes KOA pain is complicated, and it may be produced by peripheral or central sensitization, but it has not gotten enough attention in clinical practice, and there is no agreement on how to treat combination neuropathic pain KOA. As a result, using neuroimaging techniques such as magnetic resonance imaging (MRI), electroencephalography (EEG), magnetoencephalography (MEG), and near-infrared spectroscopy (NIRS), this review examines the changes in brain pathophysiology-related regions caused by KOA pain, compares the latest results in pain assessment and prediction, and clarifies the central brain analgesic mechanistic. The capsule network model is introduced in this paper from the perspective of deep learning network structure to construct an information-complete and reversible image low-level feature bridge using isotropic representation, predict the corresponding capsule features from MRI voxel responses, and then, complete the accurate reconstruction of simple images using inverse transformation. The proposed model improves the structural similarity index by about 10%, improves the reconstruction performance of low-level feature content in simple images by about 10%, and achieves feature interpretation and analysis of low-level visual cortical fMRI voxels by visualising capsule features, according to the experimental results.

Background. Studies focusing on prediction models are widespread in medicine. There is a trend in applying machine learning (ML) by medical researchers and clinicians. Over the years, multiple ML algorithms have been adapted to censored data. However, the choice of methodology should be motivated by the real-life data and their complexity. Here, the predictive performance of ML techniques is compared with statistical models in a simple clinical setting (small/moderate sample size and small number of predictors) with Monte-Carlo simulations. Methods. Synthetic data (250 or 1000 patients) were generated that closely resembled 5 prognostic factors preselected based on a European Osteosarcoma Intergroup study (MRC BO06/EORTC 80931). Comparison was performed between 2 partial logistic artificial neural networks (PLANNs) and Cox models for 20, 40, 61, and 80% censoring. Survival times were generated from a log-normal distribution. Models were contrasted in terms of the C-index, Brier score at 0-5 years, integrated Brier score (IBS) at 5 years, and miscalibration at 2 and 5 years (usually neglected). The endpoint of interest was overall survival. Results. PLANNs original/extended were tuned based on the IBS at 5 years and the C-index, achieving a slightly better performance with the IBS. Comparison with Cox models showed that PLANNs can reach similar predictive performance on simulated data for most scenarios with respect to the C-index, Brier score, or IBS. However, Cox models were frequently less miscalibrated. Performance was robust in scenario data where censored patients were removed before 2 years or curtailing at 5 years was performed (on training data). Conclusion. Survival neural networks reached a comparable predictive performance with Cox models but were generally less well calibrated. All in all, researchers should be aware of burdensome aspects of ML techniques such as data preprocessing, tuning of hyperparameters, and computational intensity that render them disadvantageous against conventional regression models in a simple clinical setting.