Effectiveness and safety of augmentative plating technique in managing nonunion following intramedullary nailing of long bones in the lower extremity: A systematic review and meta-analysis.

PURPOSE: To methodically assess the effectiveness of augmentative plating (AP) and exchange nailing (EN) in managing nonunion following intramedullary nailing for long bone fractures of the lower extremity. METHODS: PubMed, EMBASE, Web of Science, and the Cochrane Library were searched to gather clinical studies regarding the use of AP and EN techniques in the treatment of nonunion following intramedullary nailing of lower extremity long bones. The search was conducted up until May 2023. The original studies underwent an independent assessment of their quality, a process conducted utilizing the Newcastle-Ottawa scale. Data were retrieved from these studies, and meta-analysis was executed utilizing Review Manager 5.3. RESULTS: This meta-analysis included 8 studies involving 661 participants, with 305 in the AP group and 356 in the EN group. The results of the meta-analysis demonstrated that the AP group exhibited a higher rate of union (odds ratio: 8.61, 95% confidence intervals (CI): 4.12 - 17.99, p < 0.001), shorter union time (standardized mean difference (SMD): -1.08, 95 % CI: -1.79 - -0.37, p = 0.003), reduced duration of the surgical procedure (SMD: -0.56, 95 % CI: -0.93 - -0.19, p = 0.003), less bleeding (SMD: -1.5, 95 % CI: -2.81 - -0.18), p = 0.03), and a lower incidence of complications (relative risk: -0.17, 95 % CI: -0.27 - -0.06, p = 0.001). In the subgroup analysis, the time for union in the AP group in nonisthmal and isthmal nonunion of lower extremity long bones was shorter compared to the EN group (nonisthmal SMD: -1.94, 95 % CI: -3.28 - -0.61, p < 0.001; isthmal SMD: -1.08, 95 % CI: -1.64 - -0.52, p = 0.002). CONCLUSION: In the treatment of nonunion in diaphyseal fractures of the long bones in the lower extremity, the AP approach is superior to EN, both intraoperatively (with reduced duration of the surgical procedure and diminished blood loss) and postoperatively (with an elevated union rate, shorter union time, and lower incidence of complications). Specifically, in the management of nonunion of lower extremity long bones with non-isthmal and isthmal intramedullary nails, AP demonstrated shorter union time in comparison to EN.

Efficacy comparison of antibiotic bone cement-coated implants and external fixations for treating infected bone defects.

PURPOSE: This study aimed to investigate the clinical efficacy of antibiotic bone cement-coated implants compared with external fixations for treating infected bone defects. METHODS: We retrospectively enrolled 119 patients with infected bone defects in our hospital from January 2010 to June 2021, of which 56 were treated with antibiotic bone cement-coated implants and 63 were with external fixation. RESULTS: The pre-operative and post-operative haematological indexes were tested to assess the infection control; the post-operative CRP level in the internal fixation group was lower than that in the external fixation group. No statistical significance was found in the rate of infection recurrence, loosening and rupture of the fixation, and amputation between the two groups. Twelve patients in the external fixation group had pin tract infection. In the evaluation of the Paley score scale, bone healing aspect revealed no significant difference between the two groups, while in the limb function aspect, antibiotic cement-coated implant group showed a much better score than the external fixation group (P = 0.002). The anxiety evaluation scale result also showed lower score in the antibiotic cement implant group (P < 0.001). CONCLUSIONS: Compared with external fixation, antibiotic bone cement-coated implant had the same effect on controlling infection and was more effective in recovering limb function and mental health in the first-stage treatment of infected bone defects after debridement.

A novel gene functional similarity calculation model by utilizing the specificity of terms and relationships in gene ontology.

BACKGROUND: Recently, with the foundation and development of gene ontology (GO) resources, numerous works have been proposed to compute functional similarity of genes and achieved series of successes in some research fields. Focusing on the calculation of the information content (IC) of terms is the main idea of these methods, which is essential for measuring functional similarity of genes. However, most approaches have some deficiencies, especially when measuring the IC of both GO terms and their corresponding annotated term sets. To this end, measuring functional similarity of genes accurately is still challenging. RESULTS: In this article, we proposed a novel gene functional similarity calculation method, which especially encapsulates the specificity of terms and edges (STE). The proposed method mainly contains three steps. Firstly, a novel computing model is put forward to compute the IC of terms. This model has the ability to exploit the specific structural information of GO terms. Secondly, the IC of term sets are computed by capturing the genetic structure between the terms contained in the set. Lastly, we measure the gene functional similarity according to the IC overlap ratio of the corresponding annotated genes sets. The proposed method accurately measures the IC of not only GO terms but also the annotated term sets by leveraging the specificity of edges in the GO graph. CONCLUSIONS: We conduct experiments on gene functional classification in biological pathways, gene expression datasets, and protein-protein interaction datasets. Extensive experimental results show the better performances of our proposed STE against several baseline methods.

Application of vancomycin-impregnated calcium sulfate hemihydrate/nanohydroxyapatite/carboxymethyl chitosan injectable hydrogels combined with BMSC sheets for the treatment of infected bone defects in a rabbit model.

BACKGROUND: The choice of bone substitutes for the treatment of infected bone defects (IBDs) has attracted the attention of surgeons for years. However, single-stage bioabsorbable materials that are used as carriers for antibiotic release, as well as scaffolds for BMSC sheets, need further exploration. Our study was designed to investigate the effect of vancomycin-loaded calcium sulfate hemihydrate/nanohydroxyapatite/carboxymethyl chitosan (CSH/n-HA/CMCS) hydrogels combined with BMSC sheets as bone substitutes for the treatment of IBDs. METHODS: BMSCs were harvested and cultured into cell sheets. After the successful establishment of an animal model with chronic osteomyelitis, 48 New Zealand white rabbits were randomly divided into 4 groups. Animals in Group A were treated with thorough debridement as a control. Group B was treated with BMSC sheets. CSH/n-HA/CMCS hydrogels were implanted in the treatment of Group C, and Group D was treated with CSH/n-HA/CMCS+BMSC sheets. Gross observation and micro-CT 3D reconstruction were performed to assess the osteogenic and infection elimination abilities of the treatment materials. Histological staining (haematoxylin and eosin and Van Gieson) was used to observe inflammatory cell infiltration and the formation of collagen fibres at 4, 8, and 12 weeks after implantation. RESULTS: The bone defects of the control group were not repaired at 12 weeks, as chronic osteomyelitis was still observed. HE staining showed a large amount of inflammatory cell infiltration around the tissue, and VG staining showed no new collagen fibres formation. In the BMSC sheet group, although new bone formation was observed by gross observation and micro-CT scanning, infection was not effectively controlled due to unfilled cavities. Some neutrophils and only a small amount of collagen fibres could be observed. Both the hydrogel and hydrogel/BMSCs groups achieved satisfactory repair effects and infection control. Micro-CT 3D reconstruction at 4 weeks showed that the hydrogel/BMSC sheet group had higher reconstruction efficiency and better bone modelling with normal morphology. HE staining showed little aggregation of inflammatory cells, and VG staining showed a large number of new collagen fibres. CONCLUSIONS: Our preliminary results suggested that compared to a single material, the novel antibiotic-impregnated hydrogels acted as superior scaffolds for BMSC sheets and excellent antibiotic vectors against infection, which provided a basis for applying tissue engineering technology to the treatment of chronic osteomyelitis.

Comparing the Population Pharmacokinetics of and Acute Kidney Injury Due to Polymyxin B in Chinese Patients with or without Renal Insufficiency.

Despite excellent bactericidal effect, dosing adjustment of polymyxin B for patients with renal insufficiency and polymyxin B-related nephrotoxicity is still a major concern to clinicians. The aim of this study was to compare the population pharmacokinetics (PK) properties of polymyxin B in Chinese patients with different renal functions and to investigate the relationship between PK parameters and polymyxin B-related acute kidney injury (AKI). A total of 37 patients with normal renal function (creatinine clearance ≥ 80 ml/min) and 33 with renal insufficiency (creatinine clearance < 80 ml/min) were included. In the two-compartment population PK models, the central compartment clearance (CL) (2.19 liters/h versus 1.58 liters/h; P < 0.001) and intercompartmental clearance (Q) (13.83 liters/h versus 10.28 liters/h; P < 0.001) values were significantly different between the two groups. The simulated values for AUC across 24 h at steady state (AUCss,24h) for patients with normal renal function were higher than those for patients with renal insufficiency. However, renal dosing adjustment of polymyxin B seemed not to be necessary. In addition, during the treatment, AKI occurred in 23 (32.86%) patients. The polymyxin B AUCss,24h in patients with AKI was significantly higher than that in patients without AKI (108.66 ± 70.10 mg · h/liter versus 66.18 ± 34.79 mg · h/liter; P = 0.001). Both the receiver operating characteristic (ROC) curve and logistic regression analysis showed that an AUCss,24h of >100 mg · h/liter was a good predictor for the probability of nephrotoxicity.

Carbonic anhydrase 2 inhibits epithelial-mesenchymal transition and metastasis in hepatocellular carcinoma.

Carbonic anhydrase 2 (CA2) plays vital role in the regulation of ion transport and pH balance and is involved in many biological processes; however, its role in cancer remains obscure. In this study, we identified a novel function of CA2 in facilitating hepatocellular carcinoma (HCC) metastasis. CA2 expression was elevated in Na+-K+-ATPase α1 (ATP1A1)-downregulated HCC cells and was inversely correlated with that of ATP1A1 in HCC. ATP1A1 acted as an oncoprotein whereas CA2 overexpression inhibited cell migration and invasion by reversing epithelial-mesenchymal transition (EMT) in HCC. CA2 downregulation promoted HCC metastasis and invasion whereas ATP1A1 downregulation inhibited HCC metastasis. Because of the opposing effects of CA2 and ATP1A1 in HCC, we examined the role of their correlation in HCC metastasis. CA2 attenuated ATP1A1-triggered tumor growth in vivo and ATP1A1-induced metastasis in vitro. Taken together, the present results suggest that CA2 serves as a suppressor of HCC metastasis and EMT and is correlated with favorable overall survival (OS) in HCC patients.

miR-122 Targets X-Linked Inhibitor of Apoptosis Protein to Sensitize Oxaliplatin-Resistant Colorectal Cancer Cells to Oxaliplatin-Mediated Cytotoxicity.

BACKGROUND/AIMS: Although oxaliplatin is one of the most effective chemotherapeutic drugs used to treat colorectal cancer (CRC), long-term administration usually induces acquired drug resistance during the course of treatment. Thus, there is an urgent need to explore novel strategies to improve the efficiency of cancer therapy. The aim of this study was to explore the effect of microRNA-122 (miR-122) on reversing oxaliplatin resistance in CRC. METHODS: The expression of miR-122 in CRC cells was examined by quantitative reverse transcriptase real-time PCR. The cytotoxicity of oxaliplatin against CRC cells was evaluated by Cell Counting Kit-8 assays. Mitochondrial membrane potentials and cell apoptotic rates were measured by flow cytometry. Cellular protein expression and interactions were detected by western blot and co-immunoprecipitation. RESULTS: Established oxaliplatin-resistant SW480 and HT29 cells (SW480/OR and HT29/OR) expressed significantly higher levels of X-linked inhibitor of apoptosis protein (XIAP) and lower levels of miR-122 compared with normal SW480 and HT29 cells, respectively. Our results showed that the downregulation of miR-122 was responsible for the overexpression of XIAP in these oxaliplatin-resistant CRC cells. We then found that the recovery of miR-122 expression can sensitize SW480/OR and HT29/OR cells to oxaliplatin-mediated apoptosis through the inhibition of XIAP expression. CONCLUSION: Upregulation of XIAP in CRC cells is responsible for the acquired resistance to oxaliplatin. Furthermore, miR-122 reversed oxaliplatin resistance in CRC by targeting XIAP.

Pharmacokinetic Comparison of Two Mycophenolate Mofetil Formulations in Kidney Transplant Recipients.

BACKGROUND: The aim of this study was to investigate and compare the pharmacokinetic (PK) characteristics of mycophenolate mofetil (MMF) capsule and MMF dispersible tablet by detecting the active metabolite of mycophenolic acid (MPA) in Chinese kidney transplant recipients. METHODS: In the prospective, randomized, open-label study, the renal transplant patients were given a multiple dose of either the MMF capsule or MMF dispersible tablet combination with tacrolimus (Tac). For each patient, 11 serial blood samples were collected over 12 hours (h). Parameters including predose concentration (C0), postdose minimum and maximum concentration (Cmin and Cmax), time to Cmax (Tmax), total body clearance (CL), and area under the concentration-time curve for the 12-hour exposure (AUC0-12h) were determined. Patient interviews were conducted to assess the occurrence of adverse events. RESULTS: Baseline characteristics were comparable between both groups. The C0, Cmin, Cmax, Tmax, CL, and AUC0-12h values were not significantly different after multiple doses of MMF capsule or MMF dispersible tablet (P > 0.05). The median values of AUC0-12h were 43.98 and 41.95 mcg·h/mL for MMF capsule and MMF dispersible tablet, respectively. Interindividual variability in Cmax, Cmin, and C0 were considerable in both groups. No serious adverse events were reported by patients or found on analysis of laboratory tests. CONCLUSIONS: PK parameters of the 2 MPA drugs were comparable in early renal transplant patients in this study. The 2 formulations were well tolerated in Chinese kidney transplant patients.

Population pharmacokinetics and pharmacodynamics of ticagrelor and AR-C124910XX in Chinese healthy male subjects.

BACKGROUND: Ticagrelor, the first reversible P2Y12 receptor antagonist, exhibits faster onset and offset of antiplatelet effects and more consistent platelet inhibition than clopidogrel in both healthy subjects and patients with stable coronary artery disease. OBJECTIVE: The objectives of this study were to establish a population pharmacokinetics (PK) and pharmacodynamics (PD) model of ticagrelor and to provide a theoretical basis for the optimization of ticagrelor treatment in clinic. METHODS: A single oral dose of 180 mg ticagrelor was administered to 14 healthy male subjects in a randomized study. Common single-nucleotide polymorphisms (SNPs) in biotransformation enzymes CYP3A4 and CYP3A5 (CYP3A4*1G and CYP3A5*3) were genotyped by PCR-direct sequencing. Blood samples were collected to measure plasma concentrations of ticagrelor and its active metabolite AR-C124910XX and maximal platelet inhibition. Various models were evaluated to characterize the pharmacokinetics of ticagrelor and AR-C124910XX as well as their PK-PD relationship. Covariates that may potentially affect PK or PD of ticagrelor and AR-C124910XX were included and assessed. Simulation for dosage regimen was performed based on the final PK-PD model. RESULTS: Ticagrelor and AR-C124910XX PK were best described by a two-compartment model with first-order transit absorption model. CYP3A4*1G increased clearance for AR-C124910XX, but had no significant effect on ticagrelor clearance. The relationship between concentration and platelet response of ticagrelor was best described by a turnover model. Simulation results indicated that a lower dosage regimen of 30 mg maintenance dose (MD) could produce an anticipated anti-platelet response in comparison to the routine clinical dosage regimen (180 mg loading dose (LD), 90 mg MD). CONCLUSION: Our study developed a population PK-PD model for ticagrelor and further simulation for dosage regimen was performed based on the final model. Compared to the current recommended dosage regimen (180 mg LD, 90 mg MD), our simulation result of a relatively lower dose (30 mg MD) could also obtain an acceptable anti-platelet response, which may provide a reference for further dosage regimen design in Chinese population.

Qualitative and quantitative determination of YiXinShu Tablet using ultra high performance liquid chromatography with Q Exactive hybrid quadrupole orbitrap high-resolution accurate mass spectrometry.

To clarify and quantify the chemical profile of YiXinShu Tablet rapidly, a feasible and accurate strategy was developed by applying ultra high performance liquid chromatography with Q Exactive hybrid quadrupole orbitrap high-resolution accurate mass spectrometry. A total of 105 components were identified, including 25 phenanthraquinones, 11 lactones, 19 lignans, 24 acids, and 26 other compounds. Among them, 26 major compounds were unambiguously detected by comparing with reference standards. And 19 of these compounds in three batches of YiXinShu Tablet were selected for quantitative determination. (Z)-Ligustilide, salvianic acid A, salvianolic acid A, salvianolic acid B, and rosmarinic acid were abundant in these three batches with contents over 1 mg/g. The established analysis methods were examined to be accurate and feasible. The results show that the ultra high performance liquid chromatography with Q Exactive hybrid quadrupole orbitrap high-resolution accurate mass spectrometry method has a powerful qualitative ability and promising quantitative application.

Chemical profiling and quantification of ShenKang injection, a systematic quality control strategy using ultra high performance liquid chromatography with Q Exactive hybrid quadrupole orbitrap high-resolution accurate mass spectrometry.

ShenKang injection is traditional Chinese medicine used to treat chronic renal failure in China. It is a compound preparation that consists of four herbs: Rhubarb, Salvia miltiorrhiza, Safflower and Radix Astragali. We developed an ultra high pressure liquid chromatography coupled with Q Exactive hybrid quadrupole-orbitrap high resolution accurate mass spectrometry tandem mass spectrometry method to analyze its chemical compositions, and a total of 90 compounds were identified from ShenKang injection. Among them, 19 major compounds were unambiguously detected by comparing with reference standards. Meanwhile, 13 representative compounds selected as quality control markers were simultaneously quantified in ShenKang injection samples. Chromatographic separation was accomplished on a Waters ACQUITY HPLC® HSS C18 column using gradient elution. The method was validated with respect to linearity, sensitivity, accuracy and precision, reproducibility and stability. And the validated method was successfully applied for simultaneous determination of 13 bioactive compounds in ShenKang injection from ten batches of samples by liquid chromatography with mass spectrometry. The results were analyzed by principal components analysis method, and three compounds had a significant relationship with the quality control of ShenKang injection. This research established a rapid and reliable method for the integrating quality control, including qualitation and quantification of ShenKang injection.

Regulation of aerobic glycolysis by long non-coding RNAs in cancer.

As with miRNAs a decade ago, long non-coding RNAs (lncRNAs) are emerging as a new class of RNAs involved in physiological and pathological processes. Recent evidences have shown that lncRNAs play a role in cancer metabolism. The relationship between lncRNAs and aerobic glycolysis provides new strategies for the treatment of cancer. Here we discuss recent findings on the role of lncRNAs in aerobic glycolysis and provide insights into their mechanisms of action. In addition, we explore the potential challenges in using lncRNAs as targets for cancer therapy.

A Red to Near-IR Fluorogen: Aggregation-Induced Emission, Large Stokes Shift, High Solid Efficiency and Application in Cell-Imaging.

A tetraphenylethene (TPE) derivative modified with the strong electron acceptor 2-dicyano-methylene-3-cyano-4,5,5-trimethyl-2,5-dihydrofuran (TCF) was obtained in high yield by a simple two-step reaction. The resultant TPE-TCF showed evident aggregation-induced emission (AIE) features and pronounced solvatochromic behavior. Changing the solvent from apolar cyclohexane to highly polar acetonitrile, the emission peak shifted from 560 to 680 nm (120 nm redshift). In an acetonitrile solution and in the solid powder, the Stokes shifts are as large as 230 and 190 nm, respectively. The solid film emits red to near-IR (red-NIR) fluorescence with an emission peak at 670 nm and a quantum efficiency of 24.8 %. Taking the advantages of red-NIR emission and high efficiency, nanoparticles (NPs) of TPE-TCF were fabricated by using tat-modified 1,2-distearoylsn-glycero-3-phosphor-ethanol-amine-N-[methoxy-(polyethyl-eneglycol)-2000] as the encapsulation matrix. The obtained NPs showed perfect membrane penetrability and high fluorescent imaging quality of cell cytoplasm. Upon co-incubation with 4,6-diamidino-2-phenylindole (DAPI) in the presence of tritons, the capsulated TPE-TCF nanoparticles could enter into the nucleus and displayed similar staining properties to those of DAPI.

Low photobleaching and high emission depletion efficiency: the potential of AIE luminogen as fluorescent probe for STED microscopy.

We present a preliminary study which explores the potential of aggregation-induced emission (AIE) luminogen as a new fluorescent probe for STED microscopy. Compared with Coumarin 102, which is a commonly used organic fluorophore in STED microscopy, HPS, a typical AIE luminogen, is more resistant to photobleaching. In addition, HPS-doped nanoparticles have higher emission depletion efficiency than Coumarin 102 in organic solution. These two advantages of AIE luminogen can facilitate the improvement of spatial resolution, as well as long-term imaging, in STED microscopy. AIE luminogen will be a promising candidate for STED microscopy in the future.

SGT++: Improved Scene Graph-Guided Transformer for Surgical Report Generation.

Automatically recording surgical procedures and generating surgical reports are crucial for alleviating surgeons' workload and enabling them to concentrate more on the operations. Despite some achievements, there still exist several issues for the previous works: 1) failure to model the interactive relationship between surgical instruments and tissue; and 2) neglect of fine-grained differences within different surgical images in the same surgery. To address these two issues, we propose an improved scene graph-guided Transformer, also named by SGT++, to generate more accurate surgical report, in which the complex interactions between surgical instruments and tissue are learnt from both explicit and implicit perspectives. Specifically, to facilitate the understanding of the surgical scene graph under a graph learning framework, a simple yet effective approach is proposed for homogenizing the input heterogeneous scene graph. For the homogeneous scene graph that contains explicit structured and fine-grained semantic relationships, we design an attention-induced graph transformer for node aggregation via an explicit relation-aware encoder. In addition, to characterize the implicit relationships about the instrument, tissue, and the interaction between them, the implicit relational attention is proposed to take full advantage of the prior knowledge from the interactional prototype memory. With the learnt explicit and implicit relation-aware representations, they are then coalesced to obtain the fused relation-aware representations contributing to generating reports. Some comprehensive experiments on two surgical datasets show that the proposed STG++ model achieves state-of-the-art results.

RedCDR: Dual Relation Distillation for Cancer Drug Response Prediction.

Based on multi-omics data and drug information, predicting the response of cancer cell lines to drugs is a crucial area of research in modern oncology, as it can promote the development of personalized treatments. Despite the promising performance achieved by existing models, most of them overlook the variations among different omics and lack effective integration of multi-omics data. Moreover, the explicit modeling of cell line/drug attribute and cell line-drug association has not been thoroughly investigated in existing approaches. To address these issues, we propose RedCDR, a dual relation distillation model for cancer drug response (CDR) prediction. Specifically, a parallel dual-branch architecture is designed to enable both the independent learning and interactive fusion feasible for cell line/drug attribute and cell line-drug association information. To facilitate the adaptive interacting integration of multi-omics data, the proposed multi-omics encoder introduces the multiple similarity relations between cell lines and takes the importance of different omics data into account. To accomplish knowledge transfer from the two independent attribute and association branches to their fusion, a dual relation distillation mechanism consisting of representation distillation and prediction distillation is presented. Experiments conducted on the GDSC and CCLE datasets show that RedCDR outperforms previous state-of-the-art approaches in CDR prediction. The source code is available at https://github.com/mhxu1998/RedCDR.

Case report: A lung squamous cell carcinoma patient with a rare EGFR G719X mutation and high PD-L1 expression showed a good response to anti-PD1 therapy.

Lung cancer treatment has transitioned fully into the era of immunotherapy, yielding substantial improvements in survival rate for patients with advanced non-small cell lung cancer (NSCLC). In this report, we present a case featuring a rare epidermal growth factor receptor (EGFR) mutation accompanied by high programmed death-ligand 1 (PD-L1) expression, demonstrating remarkable therapeutic efficacy through a combination of immunotherapy and chemotherapy. A 77-year-old male with no family history of cancer suffered from upper abdominal pain for more than half months in August 2020 and was diagnosed with stage IV (cT3N3M1c) lung squamous cell carcinoma (LUSC) harboring both a rare EGFR p.G719C mutation and high expression of PD-L1 (tumor proportion score [TPS] = 90%). Treatment with the second-generation targeted therapy drug Afatinib was initiated on September 25, 2020. However, resistance ensued after 1.5 months of treatment. On November 17, 2020, immunotherapy was combined with chemotherapy (Sintilimab + Albumin-bound paclitaxel + Cisplatin), and a CT scan conducted three months later revealed significant tumor regression with a favorable therapeutic effect. Subsequently, the patient received one year of maintenance therapy with Sintilimab, with follow-up CT scans demonstrating subtle tumor shrinkage (stable disease). This case provides evidence for the feasibility and efficacy of immunotherapy combined with chemotherapy in the treatment of EGFR-mutated and PD-L1 highly expressed LUSC.

CED: A case-level explainable paramedical diagnosis via AdaGBDT.

OBJECTIVE: The rapid growth of medical data has greatly promoted the wide exploitation of machine learning for paramedical diagnosis. Inversely proportional to their performance, most machine learning models generally suffer from the lack of explainability, especially the local explainability of the model, that is, the case-specific explainability. MATERIALS AND METHODS: In this paper, we proposed a GBDT (Gradient Boosting Decision Tree)-based explainable model for case-specific paramedical diagnostics, and mainly make the following contributions: (1) an adaptive gradient boosting decision tree (AdaGBDT) model is proposed to boost the path-mining for decision effectively; (2) to learn a case-specific feature importance embedding for a specific patient, the bi-side mutual information is applied to characterize the backtracking on the decision path; (3) through the collaborative decision-making by globally explainable AdaGBDT with case-based reasoning (CBR) in the case-specific metric space, some hard cases can be identified by the means of visualized interpretation. The performance of our model is evaluated on the Wisconsin diagnostic breast cancer dataset and the UCI heart disease dataset. RESULTS: Experiments conducted on two datasets show that our AdaGBDT achieves the best performance, with the F1-value of 0.9647 and 0.8405 respectively. Moreover, a series of experimental analyses and case studies further illustrate the excellent performance of feature importance embedding. CONCLUSION: The proposed case-specific explainable paramedical diagnosis via AdaGBDT has excellent predictive performance, with both promising case-level and consistent global explainability.

Cooperative dual medical ontology representation learning for clinical assisted decision-making.

OBJECTIVE: Predicting clinical events and providing assisted decision-making using Electronic Health Records (EHRs) play a central role in personalized healthcare. Despite the promising performance achieved for diagnosis and procedure predictions, most of the existing predictive models regard different medical codes as the same type and generally ignore the dependence between diagnoses and procedures in patients' admission history. To address these issues, we propose an end-to-end cooperative dual medical ontology representation learning framework for clinical assisted decision-making. MATERIALS AND METHODS: The framework consists of two primary modules: (1) dual medical ontology representation learning to facilitate the learning of medical concepts and (2) task dependent multi-task prediction to capture the correlation between diagnoses and procedures in patients' admission history. We evaluate our method with EHRs from the MIMIC-III Clinical Database, covering 6321 patients and 16335 visits. RESULTS: Experiments conducted on the MIMIC-III dataset show that the proposed model achieves the best performance, with a top-20 accuracy of 58.20% for diagnosis prediction and a top-20 accuracy of 75.85% for procedure prediction. In addition, a series of experimental analyses and case studies further illustrate the excellent performance of our model. CONCLUSION: We propose an end-to-end cooperative dual medical ontology representation learning framework, which achieves superior performance on multi-task diagnosis and procedure predictions. The source code is available at https://github.com/mhxu1998/CoDMO.

A case report of membrane induction combined with RIA technique for the repair of distal humerus segmentary bone defect.

Bone nonunion and bone defect are common postoperative complications in clinic. Membrane induction or Ilizarov technique is often used to repair bone defect. Autologous bone is often used for bone defect repair and reconstruction, and the anterior superior iliac spine, posterior superior iliac spine or fibula bone is used as the donor area for bone extraction, but there are problems of donor area complications. In recent years, the development of bone marrow aspiration (RIA) has provided a new alternative way for the source of autogenous bone. We report a 48-year-old female patient with a comminuted supracondylar intercondylar fracture of the left humerus due to a car accident. After 8 months of emergency debridement and suture with Kirschner wire internal fixation, the fracture was found to be unhealed with extensive bone defects. We used membrane induction combined with RIA technology to repair and reconstruct the patients, and found good osteogenesis through late follow-up. In theory, membrane induction technique can realize the reconstruction of large segmental bone defects, but the scope of repair is often limited by the lack of autologous bone source. The emergence and development of RIA technology provides us with a new autologous bone donor area for bone repair and reconstruction surgery. It can provide a large amount of high-quality cancellar bone mud through minimally invasive means. Meanwhile, it can reduce patients' pain, infection, fracture, aesthetics and other problems caused by iliac bone extraction, and shorten patients' bed time. Maximize the preservation of the patient's autologous bone source. For the first time in the world, we reported the combination of membrane induction technology and RIA technology in the treatment of segmental bone defects, providing a new idea for the treatment of bone defects.