Web-based artificial intelligence to predict cognitive impairment following stroke: A multicenter study.

BACKGROUND AND PURPOSE: Post-stroke cognitive impairment (PSCI) is highly prevalent in modern society. However, there is limited study implying an accurate and explainable machine learning model to predict PSCI. The aim of this study is to develop and validate a web-based artificial intelligence (AI) tool for predicting PSCI. METHODS: The retrospective cohort study design was conducted to develop and validate a web-based prediction model. Adults who experienced a stroke between January 1, 2004, and September 30, 2017, were enrolled, and patients with PSCI were followed up from the stroke index date until their last follow-up. The model's performance metrics, including accuracy, area under the curve (AUC), recall, precision, and F1 score, were compared. RESULTS: A total of 3209 stroke patients were included in the study. The model demonstrated an accuracy of 0.8793, AUC of 0.9200, recall of 0.6332, precision of 0.9664, and F1 score of 0.7651. In the external validation phase, the accuracy improved to 0.9039, AUC to 0.9094, recall to 0.7457, precision to 0.9168, and F1 score to 0.8224. The final model can be accessed at https://psci-calculator.my.id/. CONCLUSION: Our results are able to produce a user-friendly interface that is useful for health practitioners to perform early prediction on PSCI. These findings also suggest that the provided AI model is reliable and can serve as a roadmap for future studies using AI models in a clinical setting.

Robust construction of polyvinyl alcohol intercalated graphene oxide nanofiltration membrane for desalination via pervaporation.

The construction and modification of a Graphene Oxide (GO) membrane, incorporating polyvinyl alcohol (PVA) cross-linked with maleic acid (MA) and supported by a nylon membrane, have been successfully completed. Systematic variations in PVA and MA concentrations were conducted to achieve membranes with favorable characteristics, stability, and excellent desalination performance. Optimization studies utilizing the Central Composite Design (CCD) revealed that the most optimal desalination results were obtained with 10 mL of PVA (0.1 mg mL-1) and 0.9 M of MA (GO-MA0.9-PVA10/Nylon membrane). Experimental findings demonstrated that the inclusion of PVA and MA resulted in an increased interlayer distance of GO and enhanced membrane stability. The addition of PVA increases GO membrane hydrophilicity, while the addition of MA reduces membrane hydrophilicity. The GO-MA0.9-PVA10/Nylon membrane exhibited the highest desalination performance, boasting a rejection value exceeding >99.9% and a permeance of 18.76 kg m-2.h-1 under 1% NaCl feed at a temperature of 50 °C. This membrane demonstrated consistent desalination performance stability over an extended period of up to 70 h. Moreover, it exhibited durability through 8 cycles of 24-h usage with washing treatment. In conclusion, the GO-MA0.9-PVA10/Nylon membrane is strongly recommended for practical applications, outperforming other membrane options based on the comprehensive evaluation of its stability and desalination efficiency.

Evaluation of Clinical Success of the 3D-Printed Custom-Made Subperiosteal Implants.

OBJECTIVE: The authors aim to share their experiences in subperiosteal implant applications in atrophic jaws, which have been practiced in their clinic for about 2 years, and evaluate the complications and clinical success of the implants. MATERIAL AND METHOD: Clinical and radiologic data of 32 patients who underwent subperiosteal implantation for advanced alveolar bone loss were evaluated, but 1 patient was excluded as they smoked. Of the 31 patients included in the study, 27 were operated with the diagnosis of total tooth loss, 3 for maxillectomy and 1 for partial tooth loss. A total of 60 subperiosteal implants were placed in them. The mean follow-up period was 15 months. RESULTS: During the operation, implant-bone adaptation problems were encountered in 11 patients, implant skeletal fracture in 1 patient, and loss of primary stabilization during mini-screw fixation in 2. Although there were no complications in the early postoperative period, biological and prosthetic complications occurred in the late postoperative period. Soft tissue retraction at various levels in 12 patients (only keratinized tissue retraction in 6 and mucosal retraction exceeding keratinized tissue in 6), soft tissue infection in 5 and oroantral fistula development in 1, mini-screw loosening in 3 were the biological complications that occurred. CONCLUSIONS: Various complications may occur during or after the application of custom-made subperiosteal implants. However, these are manageable and can be reapplied in case of a possible implant loss, making it an important alternative, especially in atrophic jaws where endosseous dental implants cannot be applied.

[Analysis on personal protection in occupational population at high risk for brucellosis and influencing factor in China].

Objective: To understand the current status of personal protection in occupational population at high risk for brucellosis in China and provide evidence for the evaluation of implementation of National Brucellosis Prevention and Control Plan (2016-2020). Methods: Four counties in Shanxi Province and Xinjiang Uygur Autonomous Region were selected to conduct a questionnaire survey in occupational population at high risk for brucellosis from December 2019 to July 2020 by using cross-sectional survey methods. Results: A total of 2 384 persons at high risk for brucellosis were surveyed, and the standardized utilization rate of personal protective equipment (PPE) was 20.13% (480/2 384). The utilization rate of glove, mask, rubber shoe, and work cloth were 38.26% (912/2 384), 31.80% (758/2 384), 32.01% (763/2 384) and 30.87% (736/2 384),respectively. There were significant differences in the utilization rate and standardized utilization rate of the four types of PPE among populations in different age, occupation, educational level and area groups (all P<0.001). The utilization rate and standardized utilization rate of PPE were lower in people over 60 years old, women, farmers, and those with lower educational level. The results of multivariate analysis showed that occupation and area were the influencing factors for the standardized utilization of PPE, the standardized utilization rates of PPE were higher in herdsmen and veterinarians. The standardized utilization rate of PPE in Yanggao County and Huocheng County was significantly higher than that in Zuoyun County and Hunyuan County. Conclusions: The utilization rate of the four types of PPE in occupational population at high risk for brucellosis was not high in China, and the standardized utilization rate was low, lower than the requirement in National Brucellosis Prevention and Control Plan, and there were significant differences among different areas. It is urgent to distribute PPE to occupational population at high risk for brucellosis and carry out health education about PPE utilization. Meanwhile, it is necessary to strengthen information exchange or sharing among different areas.

Leukotriene B4 levels in CHD-associated paediatric pulmonary hypertension.

BACKGROUND: The aim of this study is to evaluate the role of leukotriene B4, an inflammatory mediator, in the development of pulmonary hypertension in paediatric patients with CHD with left-right shunt. METHODS: The study included forty patients with CHD with left-right shunts. Based on haemodynamic data obtained from cardiac diagnostic catheterisation, 25 patients who met the criteria for pulmonary arterial hypertension were included in the patient group. The control group comprised 15 patients who did not meet the criteria. The standard cardiac haemodynamic study was conducted. Leukotriene B4 levels were assessed in blood samples taken from both pulmonary arteries and peripheral veins. RESULTS: The median age of patients with pulmonary arterial hypertension was 10 months (range: 3-168), while the median age of the control group was 50 months (range: 3-194). In the pulmonary hypertension group, the median pulmonary artery systolic/diastolic/mean pressures were 38/18/24 mmHg, compared to 26/10/18 mmHg in the control group. Leukotriene B4 levels in pulmonary artery blood samples were significantly higher in the pulmonary arterial hypertension group compared to the controls (p < 0.05). Peripheral leukotriene B4 levels were also elevated in the pulmonary arterial hypertension group in comparison to the control group, though the difference was not statistically significant. CONCLUSION: The discovery of elevated leukotriene B4 levels in pulmonary artery samples from paediatric patients with pulmonary arterial hypertension secondary to CHD with left-to-right shunt suggests that local inflammation may have a pathological role in the development of pulmonary arterial hypertension.

Hierarchical Li electrochemistry using alloy-type anode for high-energy-density Li metal batteries.

Exploiting thin Li metal anode is essential for high-energy-density battery, but is severely plagued by the poor processability of Li, as well as the uncontrollable Li plating/stripping behaviors and Li/electrolyte interface. Herein, a thickness/capacity-adjustable thin alloy-type Li/LiZn@Cu anode is fabricated for high-energy-density Li metal batteries. The as-formed lithophilic LiZn alloy in Li/LiZn@Cu anode can effectively regulate Li plating/stripping and stabilize the Li/electrolyte interface to deliver the hierarchical Li electrochemistry. Upon charging, the Li/LiZn@Cu anode firstly acts as Li source for homogeneous Li extraction. At the end of charging, the de-alloy of LiZn nanostructures further supplements the Li extraction, actually playing the Li compensation role in battery cycling. While upon discharging, the LiZn alloy forms just at the beginning, thereby regulating the following Li homogeneous deposition. The reversibility of such an interesting process is undoubtedly verified from the electrochemistry and in-situ XRD characterization. This work sheds light on the facile fabrication of practical Li metal anodes and useful Li compensation materials for high-energy-density Li metal batteries.

Artificial Intelligence Approach for Severe Dengue Early Warning System.

Dengue fever is a viral infectious disease transmitted through mosquito bites, and has symptoms ranging from mild flu-like symptoms to deadly complications. Dengue fever is one of the global burden diseases which annually have 50-100 million cases with 500,000 cases of severe dengue fever, of which 22,000 deaths occur mostly in children. Despite the discovery of vaccines, vector control is still the main approach for prevention efforts. Early detection and accessibility to medical care can reduce severe Dengue mortality rate from 50% to 2%. In the previous study, both statistical and machine learning methods have the potential for predicting a Dengue outbreak, but the study is still fragmented and limited on implementing the generated model into an early warning system application. In this study, we developed an artificial intelligence model with spatiotemporal to predict Dengue outbreak and Dengue incidence case which is ready to be implemented into an early warning system application. Indonesia, especially Semarang City, has experienced an endemic Dengue. We used Semarang City spatiotemporal, meteorological, climatological, and Dengue surveillance epidemiology data from January 2014 to December 2021 in 16 districts of Semarang City. We reviewed 7208 samples from 16 districts and 1 city per week during 8 years. The entire dataset was divided into training (80%) and testing (20%) to develop a prediction model. We used machine learning and Long Short Term Memory (LSTM) to predict Dengue outbreak 1 week before the event for each district. and machine learning to predict Dengue incident cases 1 week before the event for each district. Accuracy, area under the receiver operating characteristic curve (AUROC), precision, recall, and F1 score were considered to evaluate the Dengue outbreak prediction model. The Dengue incidence cases prediction model will evaluate using Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-Squared (R2). Extra Trees Classifier model shown outperform in Dengue outbreak prediction, with accuracy 0.8925, AUROC 0. 9529, Recall 0.6117, precision 0.8880, and F1 score 0.7238. CatBoost Regressor model is shown to outperform in Dengue incidence cases prediction, with R2 0.5621, MAE 0.6304, MSE 1.1997, and RMSE 1.0891. The study proves that Artificial Intelligence (AI) with a spatiotemporal approach can give higher performance in Dengue outbreak and incidence cases prediction. Utilization of AI approaches that are sensitive with spatiotemporal feasibility to implement in Dengue early warning system application may contribute to increase the policy makers and community attention to do accurate community-based vector control.

Facial Mimicry and Doctor-Patient Satisfaction: The Feasibility of Artificial Empathy in a Clinical Video Data.

Good nonverbal communication between doctor and patient is essential for achieving a successful and therapeutic doctor-patient relationship. Increasing evidence has shown that nonverbal communication mimicry, particularly facial mimicry, where one mirrors another's facial expressions, is linked to empathy and emotion recognition. Empathy is also the key driver of patient satisfaction. This study explores how facial expressions and facial mimicry influence doctor-patient satisfaction during a clinical encounter. We used a facial emotion recognition-based artificial empathy model to analyze 315 recorded clinical video data of doctors and patients in a dermatology outpatient clinic. The results show a significant negative correlation between patients' emotions of sadness and neutral and doctor satisfaction, but no correlation between the duration of doctors mimicking patient emotions and patient satisfaction. These findings provide valuable insights into the future design of systems that can further enhance clinician awareness to maintain communication skills in the search for better doctor-patient satisfaction.

Spontaneous tendon or ligament ruptures in patients undergoing dialysis: First pediatric case report and literature review.

Spontaneous tendon or ligament ruptures are quite rare and mostly associated with chronic systemic diseases such as diabetes mellitus, systemic lupus erythematosus, rheumatoid arthritis, and chronic kidney disease (CKD). In this study, we present the first documented case of a spontaneous rupture of the medial patellofemoral ligament (MPFL) in a pediatric patient. The patient was undergoing long-term peritoneal dialysis (PD) and had a history of severe secondary hyperparathyroidism. Additionally, we discussed spontaneous tendon and ligament ruptures associated with CKD or dialysis through a comprehensive literature review. This case report highlights the importance of recognizing that spontaneous tendon or ligament injuries are not exclusive to adults; children with CKD can also be affected. Several factors including poor parathyroid hormone (PTH) and metabolic acidosis control, prolonged CKD duration and presence of malnutrition play role in the pathogenesis. Early diagnosis is crucial as it allows for timely surgical intervention and leads to a favorable functional recovery.

Aorto-left ventricular tunnel: the necessity of early surgical intervention.

Aorto-left ventricular tunnel, also known as aorto-left ventricular fistula, is a rare CHD characterised by an abnormal connection between the aorta and the left ventricle. This article presents a comprehensive case report on aorto-left ventricular tunnel, encompassing clinical presentation, diagnostic approaches, treatment options, and outcomes, with a specific focus on the necessity of early surgical intervention.

One-Year Follow-Up Results of MIS-C Patients with Coronary Artery Involvement: A Multi-center Study.

Multisystem inflammatory syndrome (MIS-C) in children is a rare complication of SARS-CoV-2 infection. Knowing the course of the affected or unaffected coronary arteries in the patients under follow-up is important in terms of defining the long-term prognosis of the disease and determining the follow-up plan. This is a multicenter and retrospective study. The data were obtained from nine different centers. Between May 2020 and August 2022, 68 of 790 patients had coronary artery involvement. One-year echocardiographic data of 67 of 789 MIS-C patients with coronary artery involvement were analyzed. Existing pathologies of the coronary arteries were grouped as increased echogenicity, dilatation and aneurysm according to Z scores, and their changes over a 1-year period were determined. The data of all three groups are defined as frequency. SPSS Statistics version 22 was used to evaluate the data. In our study, aneurysm was observed in 16.4%, dilatation in 68.7% and increased echogenicity in 13.4% of the patients. All of the patients with involvement in the form of increased echogenicity recovered without sequelae by the end of the first month. No progression to aneurysm was observed in any of the patients with dilatation. No new-onset involvement was observed in patients with previously healthy coronary arteries during the convalescent period. In addition, from the sixth month follow-up period, there was no worsening in the amount of dilatation in any of the patients. At least 94% of the patients who completed the 12th month control period returned to normal.

Lessons learned from COVID-19 vaccination implementation: How psychological antecedents of vaccinations mediate the relationship between vaccine literacy and vaccine hesitancy.

BACKGROUND: Enhancing the public's vaccine literacy is critical for curbing vaccine hesitancy and enhancing society's pandemic preparedness, particularly in an era of infodemic. Evidence on vaccine literacy as an influencing factor of hesitancy is scarce. Lessons could be learned from COVID-19 vaccination implementation. Taking the COVID-19 vaccines as an example, the current study aimed to examine the relationship between vaccine literacy and hesitancy and the mediating role of psychological antecedents of vaccination on the relationship. METHODS: A baseline online questionnaire survey among the general public in China based on quota sampling was conducted in April 2021 to measure participants' vaccine literacy, psychological antecedents of vaccination, COVID-19 vaccination status, and vaccine hesitancy. A follow-up online survey tracked the updated COVID-19 vaccination status among those who hadn't taken COVID-19 vaccines at the baseline survey. Structural equation modeling has been applied to examine the direct and indirect effect of vaccine literacy on vaccine hesitancy. Time-to-event analysis was used to explore the effect of vaccine hesitancy on vaccination behavior. RESULTS: Lower vaccine hesitancy was associated with higher vaccine literacy. The "3Cs" psychological antecedents were important mediators between vaccine literacy and vaccine hesitancy. The pathway between critical/interactive vaccine literacy and vaccine hesitancy through the "3Cs" psychological antecedents played a more important role. Time-to-event analysis showed participants with a higher vaccine hesitancy were prone to have a longer delay in vaccination. CONCLUSIONS: Improving the public's ability to obtain and evaluate vaccination information can fix the public's psychological determinants of vaccination, reducing vaccine hesitancy and promoting vaccination. Governments need to put more effort into guiding and regulating the media to disseminate evidence-based information, rectifying misinformation, and improving the public's vaccine literacy through education, especially the public's capability to critically discern mixed information.

P-V-T equation of state of boron carbide.

We report the P-V-T equation of state measurements of B4C to 50 GPa and approximately 2500 K in laser-heated diamond anvil cells. We obtain an ambient temperature, third-order Birch-Murnaghan fit to the P-V data that yields a bulk modulus K0 of 221(2) GPa and derivative, (dK/dP)0 of 3.3(1). These were used in fits with both a Mie-Grüneisen-Debye model and a temperature-dependent, Birch-Murnaghan equation of state that includes thermal pressure estimated by thermal expansion (α) and a temperature-dependent bulk modulus (dK0/dT). The ambient pressure thermal expansion coefficient (α0 + α1T), Grüneisen γ(V) = γ0(V/V0)q and volume-dependent Debye temperature, were used as input parameters for these fits and found to be sufficient to describe the data in the whole P-T range of this study. This article is part of the theme issue 'Exploring the length scales, timescales and chemistry of challenging materials (Part 1)'.

The effect of long-haul COVID-19 toward domains of the health-related quality of life among recovered hospitalized patients.

Background: People with long-haul COVID-19 could experience various health problems, from mild to severe. This research aimed to identify the effect of long-haul COVID-19, specifically on the Quality-of-Life domains experienced by COVID-19 patients who have been discharged. Methods: Data collection was done online, using data from DKI Jakarta hospitalized patients confirmed with and recovered from SARS-CoV-2 infections. We selected patients who have a minimum of 28 days after being hospitalized for COVID-19 positive. The Logistic regression technique was used to analyze the data. The questionnaire used in this research contained questions regarding long-haul COVID-19 symptoms and domains of Quality of Life, which WHOQOL-BREF measured. Before collecting data, we tested the questionnaire with 30 recovered patients hospitalized outside DKI Jakarta. Results: 172 recovered inpatients who filled out the questionnaire correctly and were aged 18 years and above were randomly selected. Almost one-third (30.2%) of the recovered inpatients had long-haul COVID-19, with 23.8% experiencing one long-haul symptom and 6.4% experiencing more than one symptom. This research also showed that the long-haul effects of COVID-19 affected almost all domains of Quality of Life except the environmental one. Age, gender, and marital status were covariates for the association between long-haul COVID-19 and The Quality of Life. Conclusion: Continuing health services after the patient is discharged from the hospital is an important program for COVID-19 survivors because it can prevent a decline in the Quality of Life among patients due to the long-haul COVID-19.

Acoustic properties, elasticity, and equation of state of glycerol under pressure.

We employed high-pressure Brillouin scattering to study the pressure dependencies of acoustic modes of glycerol up to 14 GPa at 300 K. We observed longitudinal acoustic velocities and transverse acoustic velocities for the first time from 5 to 14 GPa. The results allow the determination of a complete set of elastic properties and an accurate determination of the pressure-volume (P-V) equation of state (EOS). EOS parameters, K0 = 14.9 ± 1.8 GPa and K'0 = 5.6 ± 0.5, were determined from fits to the data from ambient pressure to 14 GPa. Direct volume measurements of the P-V EOS are consistent with those determined by Brillouin scattering. A deviation from a Cauchy-like relationship for elastic properties was observed, and the pressure dependencies of the photoelastic constants and relaxation times were documented from 5 to 14 GPa. These results have broad implications for glass-forming liquids, viscoelastic theory, and mode coupling theory.

Machine Learning Approaches for Predicting Psoriatic Arthritis Risk Using Electronic Medical Records: Population-Based Study.

BACKGROUND: Psoriasis (PsO) is a chronic, systemic, immune-mediated disease with multiorgan involvement. Psoriatic arthritis (PsA) is an inflammatory arthritis that is present in 6%-42% of patients with PsO. Approximately 15% of patients with PsO have undiagnosed PsA. Predicting patients with a risk of PsA is crucial for providing them with early examination and treatment that can prevent irreversible disease progression and function loss. OBJECTIVE: The aim of this study was to develop and validate a prediction model for PsA based on chronological large-scale and multidimensional electronic medical records using a machine learning algorithm. METHODS: This case-control study used Taiwan's National Health Insurance Research Database from January 1, 1999, to December 31, 2013. The original data set was split into training and holdout data sets in an 80:20 ratio. A convolutional neural network was used to develop a prediction model. This model used 2.5-year diagnostic and medical records (inpatient and outpatient) with temporal-sequential information to predict the risk of PsA for a given patient within the next 6 months. The model was developed and cross-validated using the training data and was tested using the holdout data. An occlusion sensitivity analysis was performed to identify the important features of the model. RESULTS: The prediction model included a total of 443 patients with PsA with earlier diagnosis of PsO and 1772 patients with PsO without PsA for the control group. The 6-month PsA risk prediction model that uses sequential diagnostic and drug prescription information as a temporal phenomic map yielded an area under the receiver operating characteristic curve of 0.70 (95% CI 0.559-0.833), a mean sensitivity of 0.80 (SD 0.11), a mean specificity of 0.60 (SD 0.04), and a mean negative predictive value of 0.93 (SD 0.04). CONCLUSIONS: The findings of this study suggest that the risk prediction model can identify patients with PsO at a high risk of PsA. This model may help health care professionals to prioritize treatment for target high-risk populations and prevent irreversible disease progression and functional loss.

Sound Velocity and Equation of State of Ballistic Gelatin by Brillouin Scattering.

Brillouin scattering spectroscopy with diamond anvil cells was used by measuring the pressure dependence of the sound-relevant polymer material, glass-forming liquid, and H2O (water and ice VII) velocities of the material from ambient pressure to 12 GPa at room temperature. Measurements of 20%, 10%, and 4% gelatin solutions were performed. For comparison purposes, we also measured the pressure dependence of the sound velocity of animal tissue up to 10 GPa. We analyzed the Brillouin data using the Tait and Vinet equations of state. We discussed the possible influence of frequency dispersion on bulk modulus at low pressure. We compared the elastic moduli obtained for gelatin to those of several other polymers.