Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer

Background Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. Methods We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. Results A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). Conclusion We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

Determinants affecting utilisation of health services and treatment for children under-5 in rural Nepali health centres: a retrospective cohort study

Background: Large inequalities in child health remain in Nepal, with caste, ethnicity and sex being major determinants of deprivation and negative outcomes. The purpose of this study was to explore whether key demographics on under 5s were associated with health seeking behaviours, utilisation of health care, and treatment received.Methods: Data came from Integrated Management of Neonatal & Childhood Illness (IMNCI) records of 23 health centres across five districts. After digitising the paper records, district, ethnicity, sex, age and temperature of the child were used to predict the number of days taken to seek medical care for Acute Respiratory Infection (ARI), diarrhoea and fever. In addition to this, correct diagnosis and subsequent treatment of pneumonia was assessed against IMNCI guidelines, again using the demographic factors of interest to predict these outcomes.Results: From 116 register books spanning 23 health centres, 33,860 child patient records were considered for analysis. The median age of attendance was 16 months (Inter-Quartile Range= 9, 30), while there were more male children that attended (55.8% vs. 44.2% for females). There were statistically significant differences for the time taken to attend a health centre between different districts for ARI, diarrhoea and fever, with children in the remote Humla and Mugu districts taking significantly longer to present at a health facility after the onset of symptoms (all p<0.012). Children from underprivileged ethnic groups, Madhesi and Dalit, were less likely to be given a correct diagnosis of pneumonia (p=0.001), while males were more likely to receive a correct diagnosis than females (73% vs. 67%, p=0.001). This sex difference remained in the adjusted regression models for diagnosis of pneumonia (p=0.011) but not for treatment of pneumonia (p=0.202).Conclusions: Significant demographic differences were found based on ethnicity, sex, and district when examining health seeking behaviours for ARI, diarrhoea, and fever. Significant associations were seen for these same factors when exploring accuracy of diagnoses of pneumonia, but not for treatment. This study has emphasised the importance of a digitalised healthcare system, where inequalities can be identified without the reliance on anecdotal evidence.

Research of Post-Treatment Effect on Structure of Alloys Manufactured Using Additive Technologies

The effect of cold isostatic pressing of EP648 alloy after selective laser sintering is researched. The effect of cold isostatic pressing on the porosity of the structure of a material manufactured by additive technologies (AT) has been established. It is proposed to consider cold isostatic pressing as a method of subsequent treatment of products ("post-treatment") made by selective laser sintering.

Early neonatal features of juvenile offenders

Objective: Identification of perinatal risk factors as differential predictors of violent and non-violent crimes among children and adolescents who come under the attention of juvenile departments of the internal affairs bodies of the Russian Federation.Methods: Study of the perinatal history data of 148 juvenile offenders of comparable age (13-16 years old), selected using continuous sampling method in the course of a clinical observational cohort retrospective study.Results: Children from the control group in half of the cases were “late premature” (48%), with protein-energy malnutrition (frequency of occurrence of FGRP 56.8% BMI 56.1 ± 13.65). The beginning of their life was accompanied by a low score according to Apgar scale (6.9 ± 1.81). From the first minutes of life, they required urgent therapy in the delivery room (35.9%) and subsequent treatment at the ICU (25.7%) due to the damage of the respiratory system (asphyxia 11.5%, RDS 19.6%, episodes of apnea 16.2 %) and increasing dysfunction of the central nervous system (IVH II-IV grade 24.3%). Subsequently, they demonstrated a disruption of early neonatal adaptation and a clinical picture of the realization of intrauterine fetal developmental disorders, which arose both as a result of improper metabolism and of a prolonged oxygen starvation (adrenal hypoplasia 27.7%, cardiomyopathy 29.7%, hypoxia 48.6%).Conclusions: The initial protein-energy deficiency revealed in the course of the study if accompanied by the course of both acute and chronic oxygen starvation could influence the formation of destructive behavior in the group of juvenile offenders.

Lessons learned from a fatal case of tuberculous meningitis with a rapid decline in an infant

Tuberculous meningitis is a highly lethal, often underrecognized disease with characteristic clinical and imaging features which can be cured if the diagnosis and subsequent treatment are begun at early stages. Frequently, there is a delayed diagnosis of this condition due to unfamiliarity of clinicians in non-endemic areas about its presentation and diagnostic workup. This article presents a case of rapid decline and fatality due to tuberculous meningitis in an 11-month-old child from a non-TB-endemic area and describes the characteristic clinical presentation, imaging findings, and diagnostic pitfalls associated with this condition.

Hemodynamic Analysis of Pipeline Embolization Device Stent for Treatment of Giant Intracranial Aneurysm under Unsupervised Learning Algorithm

To treat large intracranial aneurysms, pipeline embolization device (PED) stent with unsupervised learning algorithms was utilized. Unsupervised learning model algorithm was used to screen aneurysm health big data, find aneurysm blood flow and PED stent positioning characteristic parameters, and guide PED stent treatment of intracranial aneurysms. The research objects were 100 patients with intracranial large aneurysm admitted to X Hospital of X Province from June 2020 to June 2021, who were enrolled into two groups. One group used the prototype transfer generative adversarial network (PTGAN) model to measure mean blood flow and mean vascular pressure and guide the placement of PED stents (PTGAN group). The other group did not use the model to place PED (control group). The PTGAN model can learn feature information from horizontal and vertical directions, with smooth edges and prominent features, which can effectively extract the main morphological and texture features of aneurysms. Compared with the convolutional neural network (CNN) model, the accuracy of the PTGAN model increased by 8.449% (87.452%–79.003%), and the precision increased by 8.347% (91.23%–82.883%). The recall rate increased by 7.011% (87.231%–80.22%), and the F1 score increased by 8.09% (89.73%–81.64%). After the adoption of the PTGAN model, the average blood flow inside the aneurysm body was 0.22 (m/s). After the adoption of the CNN model, the average blood flow inside the aneurysm body was 0.21 (m/s), and the difference was 0.01 (m/s), which was considerable ( p < 0.05 ). Through this research, it was found that the PTGAN model was better than the CNN model in terms of accuracy, precision, recall, and F1 score values. The PTGAN model was better than the CNN model in detecting the average blood flow rate and average blood pressure after treatment, and the blood flowed smoothly. Postoperative complications and postoperative relief were also better than those of the control group. In summary, based on the unsupervised learning algorithm, the PED stent had a good adoption effect in the treatment of intracranial aneurysms and was suitable for subsequent treatment.

Camphor sulfonic acid incorporation on SnO2/polyaniline nanocomposites for improved thermoelectric energy conversion

To modulate carrier transport and hence thermoelectric properties a facile approach has been undertaken by incorporation of tin dioxide (SnO2) in polyaniline (PANI) and subsequent treatment with camphor sulfonic acid...