Predicting osteoporotic fractures post-vertebroplasty: a machine learning approach with a web-based calculator.

PURPOSE: The aim of this study was to develop and validate a machine learning (ML) model for predicting the risk of new osteoporotic vertebral compression fracture (OVCF) in patients who underwent percutaneous vertebroplasty (PVP) and to create a user-friendly web-based calculator for clinical use. METHODS: A retrospective analysis of patients undergoing percutaneous vertebroplasty: A retrospective analysis of patients treated with PVP between June 2016 and June 2018 at Liuzhou People's Hospital was performed. The independent variables of the model were screened using Boruta and modelled using 9 algorithms. Model performance was assessed using the area under the receiver operating characteristic curve (ROC_AUC), and clinical utility was assessed by clinical decision curve analysis (DCA). The best models were analysed for interpretability using SHapley Additive exPlanations (SHAP) and the models were deployed visually using a web calculator. RESULTS: Training and test groups were split using time. The SVM model performed best in both the training group tenfold cross-validation (CV) and validation group AUC, with an AUC of 0.77. DCA showed that the model was beneficial to patients in both the training and test sets. A network calculator developed based on the SHAP-based SVM model can be used for clinical risk assessment ( https://nicolazhang.shinyapps.io/refracture_shap/ ). CONCLUSIONS: The SVM-based ML model was effective in predicting the risk of new-onset OVCF after PVP, and the network calculator provides a practical tool for clinical decision-making. This study contributes to personalised care in spinal surgery.

Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study.

PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management. METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction. RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability. CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic. CLINICALTRIALS: gov/ct2/show/NCT05867732 .

Identification of sensory dysfunction and nervous structure changes in Fam134b knockout mice.

OBJECTIVES: Mutation in human FAM134B gene has been implicated in hereditary sensory and autonomic neuropathy type IIB. We aimed to knock out Fam134b in mice and explored its phenotypes to determine whether the genetic impairments and behavioral changes can mirror manifestations noted in humans. METHODS: We used CRISPR/Cas9 technology to knockout the Fam134b gene in the C57BL/6 J mouse. After confirming the knockout was successful by Sanger sequencing and Western blot, sensory function was measured using the hot plate test and the 50% paw withdrawal threshold test. In addition, standard microscopy and transmission electron microscopy were performed to observe the structural changes of the dorsal root ganglion sensory neuron and the sciatic nerve. RESULTS: DNA sequencing and Western blot analysis confirmed the mutation in the Fam134b mutation gene and the loss of expression of its products. Fam134b knockout mice exhibited heat pain insensitivity and mechanical hyperalgesia. Interestingly, limb damage was found in some homozygotes. Demyelination in the sciatic nerve was common. Golgi bodies were turgid in dorsal root ganglion neuron. CONCLUSIONS: These findings indicate that peripheral neuropathy is common in Fam134b KO mice. We believe this novel animal model is likely to have significant future potential as a reliable model for the evaluation of peripheral neuropathy and its complications.

Lrpap1 deficiency leads to myopia through TGF-ß-induced apoptosis in zebrafish.

BACKGROUND: Frameshift mutations in LRPAP1 are responsible for autosomal recessive high myopia in human beings but its underlying mechanism remains elusive. This study aims to investigate the effect of LRPAP1 defect on ocular refractive development and its involved mechanism. METHODS: A lrpap1 mutant zebrafish line with homozygous frameshift mutation was generated by CRISPR/Cas9 technology and confirmed by Sanger sequencing. The ocular refractive phenotype was analyzed by calculating the relative refractive error (RRE) with vivo photography and histological analysis at different development stages, together with examining ocular structure change via transmission electron microscopy. Further, RNA sequencing and bioinformatics analysis were performed. The potentially involved signaling pathway as well as the interacted protein were investigated in vivo. RESULTS: The lrpap1 homozygous mutant zebrafish line showed myopic phenotype. Specifically, the mutant lines showed larger eye axial length-to-body length in one-month old individuals and a myopic shift with an RRE that changed after two months. Collagen fibers became thinning and disordered in the sclera. Further, RNA sequencing and bioinformatics analysis indicated that apoptosis signaling was activated in mutant line; this was further confirmed by acridine orange and TUNEL staining. Moreover, the expression of TGF-ß protein was elevated in the mutant lines. Finally, the treatment of wild-type embryos with a TGF-ß agonist aggravated the degree of eyeball apoptosis; conversely, the use of a TGF-ß inhibitor mitigated apoptosis in mutant embryos. CONCLUSION: The study provides functional evidence of a link between lrpap1 and myopia, suggesting that lrpap1 deficiency could lead to myopia through TGF-ß-induced apoptosis signaling. Video abstract.

Research on the Influence of Cosolvent on the Determination of the Contamination Degree of Jet Fuel.

The effect of cosolvent on trace free water in the determination of the contamination degree of jet fuel was investigated. The interference of trace free water on the automatic particle counter can be eliminated by adding isopropanol as a cosolvent to the measured oil sample. Isopropanol can dissolve trace free water in oil. Addition of isopropanol could stabilize the pollution grade of particles with size ≥30 µm (c) at the same level, which is most obviously affected by free water without isopropanol. The standard uncertainty u(X 1) is slightly reduced with the addition of isopropanol, and the repeatability and accuracy of the automatic particle counting method are obviously improved. The results show that isopropanol should be added as a cosolvent to eliminate the interference of free water when the contamination degree of jet fuel oil samples with obvious free water is determined by the automatic particle counting method.

Posteromedial Ankle Impingement Caused by Hypertrophy of Talocalcaneal Coalition: A Report of Five Cases and Introduction of a Novel Index System.

Ankle impingement syndromes are common disorders that can be attributed to many factors. To the best of our knowledge, posteromedial ankle impingement syndromes caused by talocalcaneal coalition have never been previously reported. The present report describes 5 patients with posteromedial ankle pain and inversion limitation. The physical examination, radiographic, and magnetic resonance imaging findings suggested posteromedial ankle impingement syndrome and talocalcaneal coalition. The 5 patients underwent surgery after conservative treatment had failed. A novel index system, namely the angle and thickness of the medial talocalcaneal facet, was introduced. The talocalcaneal coalitions protruded medially and impinged on the malleolus medialis. The medial facet of the talus and calcaneum had a wider angle and thickness than normal. Pain relief was noted, and good long-term outcomes were achieved after resection of the medial prominence and coalition in all 5 patients. Talocalcaneal coalition can cause posteromedial ankle impingement syndrome when the coalition is hypertrophic. The angle and thickness of the medial talus facet could be a simple index to diagnose this disorder.