Machine learning to predict the early recurrence of intrahepatic cholangiocarcinoma: A systematic review and meta­analysis.

The prediction of early recurrent of intrahepatic cholangiocarcinoma (ICC) has been widely investigated; however, the predictive value is currently insufficient. To determine the effectiveness of machine learning (ML) for the diagnosis of early recurrent intrahepatic cholangiocarcinoma (ICC), particularly in comparison with clinical models, the present study aimed to determine which ML model had the best diagnostic performance for inpatients with recurrent ICC. In order to search for studies which could be included, three electronic databases were screened from inception to November 2023. A pairwise meta-analysis was performed to evaluate the diagnostic accuracy of the random effects model. A network meta-analysis was performed to identify the most effective ML-based diagnostic model based on the surface under the cumulative ranking curve score. A total of 5 studies of acceptable quality containing 1,247 patients with ICC were included in the present study. Following pairwise meta-analysis, it was found that the ML-based diagnostic accuracy was greater than that of clinical models (surface under the cumulative ranking curve score closer to 1, with significant differences), which initially proved that the ML-based diagnostic power was more optimal than that of clinical models. According to the network meta-analysis, the nomogram performed the best, indicating that this ML model achieved the best diagnostic accuracy for patients with recurrent ICC. In conclusion, the application of ML-based diagnostic models for patients with recurrent ICC was more optimal than the application of the clinical model. The nomogram model ranked first among the models and is therefore recommended for patients with recurrent ICC.

Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge.

Leveraging continuous glucose monitoring (CGM) systems, real-time blood glucose (BG) forecasting is essential for proactive interventions, playing a crucial role in enhancing the management of type 1 diabetes (T1D) and type 2 diabetes (T2D). However, developing a model generalized to a population and subsequently embedding it within a microchip of a wearable device presents significant technical challenges. Furthermore, the domain of BG prediction in T2D remains under-explored in the literature. In light of this, we propose a population-specific BG prediction model, leveraging the capabilities of the temporal fusion Transformer (TFT) to adjust predictions based on personal demographic data. Then the trained model is embedded within a system-on-chip, integral to our low-power and low-cost customized wearable device. This device seamlessly communicates with CGM systems through Bluetooth and provides timely BG predictions using edge computing. When evaluated on two publicly available clinical datasets with a total of 124 participants with T1D or T2D, the embedded TFT model consistently demonstrated superior performance, achieving the lowest prediction errors when compared with a range of machine learning baseline methods. Executing the TFT model on our wearable device requires minimal memory and power consumption, enabling continuous decision support for more than 51 days on a single Li-Poly battery charge. These findings demonstrate the significant potential of the proposed TFT model and wearable device in enhancing the quality of life for people with diabetes and effectively addressing real-world challenges.

[Application status of open-wedge high tibial osteotomy assisted by three-dimensional printing patient-specific cutting guides].

Objective: To review the application of three-dimensional (3D) printing patient-specific cutting guides (PSCG) in open-wedge high tibial osteotomy (OWHTO). Methods: The domestic and foreign literature about the use of 3D printing PSCG to assist the OWHTO in recent years was reviewed, and the effectiveness of different types of 3D printing PSCG to assist OWHTO was summarized. Results: Many scholars design and use different 3D printing PSCGs to confirm the precise positioning of the osteotomy site (the bone surface around the cutting line, the "H" point of the proximal tibia, the internal and external malleolus fixators, etc.) and the correction angle (the pre-drilled holes, the wedge-shaped filling blocks, the angle-guided connecting rod, etc.) during operation, and all of them achieve good effectiveness. Conclusion: Compared with conventional OWHTO, 3D printing PSCG assisted OWHTO has many obvious advantages, such as shortening the operation time, and the frequency of fluoroscopy, and being closer to the expected preoperative correction, etc. However, the effectiveness between different 3D printing PSCGs still need to be discussed in the follow-up studies.

Does Garden type I incomplete femoral neck fracture really exist in older adults? To evaluate the stability and consistency of Garden classification.

BACKGROUND: Accurate classification of femoral neck fracture (FNF) is crucial for treatment plan and therapeutic outcomes. Garden classification is commonly used in the clinic, but its stability and consistency remain controversial. The aim of this study was to evaluate the stability and consistency of Garden classification based on X and CT images, and to analyze whether it is valid for Garden I in the elderly. METHODS: X-ray and CT images from 886 elderly patients with FNF were collected, four orthopaedic surgeons and four radiologists evaluated these images independently, and determined the fracture type based on Garden classification. Three months later, The exercise was repeated and the results were compared based on 4 types Garden classification (I, II, III and IV) and 3 types Garden classification (I + II, III and IV). Kappa was used to measure inter- and intraobserver agreement. The patients with Garden I incomplete FNF confirmed by 8 observers together based on images combined with medical history were compared with the intraoperative results. RESULTS: Four types Garden classification, there was little consistency inter- and intraobservers (Kappa from 0.18 to 0.43) based on X-ray images, while professors consistency (0.56 to 0.76) was higher than residents (0.28 to 0.35) based on CT. 3 types Garden classification showed almost perfect agreement inter- and intraobservers, which ranged from 0.76 to 0.90. Totally 52 patients were diagnosed as Garden I, 38 of whom underwent arthroplasty. All surgical cases showed complete fracture during operation. CONCLUSIONS: There was low consistency and repeatability in 4 types Garden classification (I, II, III and IV), while 3 types Garden classification (I + II, III and IV) had high consistency among observers. In the elderly, all undisplaced femoral neck fracture may be Garden II, no Garden I.

The Effect of Video Game-Based Interventions on Performance and Cognitive Function in Older Adults: Bayesian Network Meta-analysis.

BACKGROUND: The decline in performance of older people includes balance function, physical function, and fear of falling and depression. General cognitive function decline is described in terms of processing speed, working memory, attention, and executive functioning, and video game interventions may be effective. OBJECTIVE: This study evaluates the effect of video game interventions on performance and cognitive function in older participants in terms of 6 indicators: balance function, executive function, general cognitive function, physical function, processing speed, and fear of falling and depression. METHODS: Electronic databases were searched for studies from inception to June 30, 2020. Randomized controlled trials and case-controlled trials comparing video game interventions versus nonvideo game control in terms of performance and cognitive function outcomes were incorporated into a Bayesian network meta-analysis. All data were continuous variables. RESULTS: In total, 47 studies (3244 participants) were included. In pairwise meta-analysis, compared with nonvideo game control, video game interventions improved processing speed, general cognitive function, and depression scores. In the Bayesian network meta-analysis, interventions with video games improved balance function time (standardized mean difference [SMD] -3.34, 95% credible interval [CrI] -5.54 to -2.56), the cognitive function score (SMD 1.23, 95% CrI 0.82-1.86), processing speed time (SMD -0.29, 95% CrI -0.49 to -0.08), and processing speed number (SMD 0.72, 95% CrI 0.36-1.09), similar to the pairwise meta-analysis. Interventions with video games with strong visual senses and good interactivity ranked first, and these might be more beneficial for the elderly. CONCLUSIONS: Our comprehensive Bayesian network meta-analysis provides evidence that video game interventions could be considered for the elderly for improving performance and cognitive function, especially general cognitive scores and processing speed. Games with better interactivity and visual stimulation have better curative effects. Based on the available evidence, we recommend video game interventions for the elderly. TRIAL REGISTRATION: PROSPERO CRD42020197158; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=197158.

Accuracy of CT for measuring femoral neck anteversion in children with developmental dislocation of the hip verified using 3D printing technology.

BACKGROUND: Accurate femoral neck anteversion angle (FNA) measurement is of great significance in the diagnosis and treatment of developmental dysplasia of the hip (DDH) in children. The FNA measurement still remains a controversy. We aimed to verify the accuracy of our CT method by 3D printing technology and to evaluate its clinical value. METHODS: Sixty-eight children with unilateral DDH were enrolled, and their FNA was measured using 2D-CT and 3D-CT, respectively, by three observers. This procedure was repeated 3 months later. The above measurement outcomes were then compared with the results in the 3D-printed femur (3D-PF) model. The FNA in the 3D-PF model was measured by three observers (two radiologists and one orthopedist; all were professors) collectively through electronic angle instrument. RESULTS: The primary measurement of FNA at the affected hips by 2D-CT was 44.0 ± 6.1, 49.5 ± 8.9, and 52.8 ± 7.9°, respectively. On the 3D-CT, it was 47.6 ± 5.4, 49.3 ± 6.8, and 48.6 ± 6.2°. Three months later, the FNA on 2D-CT was 49.3 ± 10.5, 42.8 ± 7.4, and 45.1 ± 9.3°, and it was 48.0 ± 6.5, 48.9 ± 7.2, and 49.0 ± 5.7° on 3D-CT, respectively. The FNA in the 3D-PF model at the affected and unaffected hips was 48.5 ± 6.6 and 36.9 ± 13.1°. There were significant differences between 2D-CT and 3D-PF measurements, but no significant difference was found between 3D-CT and 3D-PF measurements. The results by 2D-CT showed significant differences among groups and between the groups. However, the results by 3D-CT had no significant differences among groups or between the groups. CONCLUSION: The results of our study showed that 3D-CT is a more precise, and reproducible method for FNA measurement in DDH. The FNA at the affected hips is 11.6° larger than the unaffected in DDH children aged 3-8 years.

Bone cement leaking into iliac vein during artificial femoral head replacement: A case report.

RATIONALE: Leakage of bone cement from femoral medullary cavity is a rare complication after hip arthroplasty, and there is no report on the leaked bone cement entering into iliac vessels. PATIENT CONCERNS: An 89-year-old woman presented with a fracture in the right femoral neck. She had well-fixed right femoral head replacement after careful preoperative examinations, and no adverse reactions appeared. She was able to get off bed to walk at the 2nd day after surgery. DIAGNOSES: Postoperative radiograph showed leakage of bone cement into the joint through femoral medullary cavity entering into iliac vessels, but the patient complained no discomforts. She received a treatment with low-molecular weight heparin and rivaroxaban. OUTCOMES: The patient was able to walk with normal gait, without swelling in both lower extremities and discomfort in the hip. There was no other complication concerning intravascular foreign bodies. LESSONS: This case calls into the phenomenon of leakage of injected bone cement in femoral head replacement regardless of complete and nonfractured femur, which may be into the lower limb and pelvic veins, given that, dangerous consequences will not occur.

Topical application of honey in the management of chemo/radiotherapy-induced oral mucositis: A systematic review and network meta-analysis.

BACKGROUND: Mucositis is an inflammatory response of mucosal epithelial cells to the cytotoxic effects of chemotherapy and radiation therapy. To assess the comparative efficacy of honey for patients with cancer undergoing chemo/radiotherapy-induced oral mucositis through a systematic review and network meta-analysis. METHODS: A network meta-analysis was used to identify evidence from relevant randomized controlled trials (RCTs). We searched PubMed, Embase, and the Cochrane Library for publications up to November 2017. The prespecified primary efficacy outcome was the treatment effect of moderate-severe oral mucositis with honey. We performed subgroup analyses and meta-regressions according to the age group, cancer type, mucositis cause, honey type, control arm and type of assessment scale. Moreover, secondary efficacy outcomes were treatment completed, onset time of mucositis, swallowing diary, fungal colonization, bacterial colonisation and analgesic use. And, we did standardize meta-analyses using the random-effects model, later completing the random-effects network meta-analyses by different treatment/control arms. RESULTS: A total of 17 RCTs were eligible (22 analyses), involving 1265 patients and 13 arms. Honey treatment arm significantly increased the therapeutic effect of chemo/radiotherapy-induced moderate-severe oral mucositis (0.25, 0.14-0.46); significant efficacy was observed in a large proportion of subgroups. The meta-regression may have identified the causes of heterogeneity as the honey type (P = 0.038). Therefore, we need to perform further comparisons of difference in honey types and controls by network meta-analysis, and the results from network meta-analysis revealed that pure natural honey was superior in therapeutic effect (0.05, 0.01-0.46). For secondary outcomes, significant effect was found in decreasing onset time of mucositis (0.41, 0.08-0.73), while no increase in adverse effects was observed. The study is registered with PROSPERO (CRD42017070873). CONCLUSIONS: The adjuvant treatment honey is effective and safe for patients with cancer undergoing chemo/radiotherapy-induced oral mucositis, especially applied pure natural local honey can be invoked as a first-line adjuvant therapy agent.