Bone Density Distribution Pattern in the Lateral Wall of the Femoral Intercondylar Notch: Implications for the Direct Insertion of the Femoral ACL Attachment.

Background: The ideal position of the femoral bone tunnel in the anterior cruciate ligament (ACL) is controversial. The functional importance of the ACL fiber varies depending on where it is attached to the femur. Functionally important fibers can cause high mechanical stress on the bone, and the Wolff law predicts that bone mineral density will increase at high mechanical stress sites. Purpose/Hypothesis: The purpose of this study was to use computed tomography imaging to determine the distribution pattern of bone density in the lateral intercondylar wall. It was hypothesized that the high-density area (HDA) of the lateral intercondylar wall would reflect the functional insertion of the ACL as reported in previous anatomic studies. Study Design: Descriptive epidemiology study. Methods: Data from 39 knees without ACL injuries were retrospectively collected. The HDA of the lateral intercondylar wall was defined as the region containing the top 10% of the radiodensity values. The shape of the HDA was approximated as an ellipse, and the quadrant method was used to determine the center of the ellipse. The association between the ratio of the minor axis to the major axis of the ellipse and background characteristics was investigated. Results: According to the quadrant method, the center of the HDA ellipse was 33.6% in the deep-shallow direction and 23.4% in the high-low direction. The center of the ellipse was comparable to the anatomic center of the ACL footprint, as previously reported. The ratio of the minor axis to the major axis of the ellipse was 0.58 (95% CI, 0.54-0.62). There was a significant negative correlation between the ratio of the minor axis to the major axis of the HDA ellipse and the posterior tibial slope (r = -0.38, P = .02). Conclusion: The center of the HDA ellipse was found to be similar to the anatomic center of the ACL footprint. Considering the mechanical stress responses in bone, the HDA of the lateral intercondylar wall has the potential to represent the ACL insertion, especially functional insertion.

Vision transformer to differentiate between benign and malignant slices in 18F-FDG PET/CT.

Fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) is widely used for the detection, diagnosis, and clinical decision-making in oncological diseases. However, in daily medical practice, it is often difficult to make clinical decisions because of physiological FDG uptake or cancers with poor FDG uptake. False negative clinical diagnoses of malignant lesions are critical issues that require attention. In this study, Vision Transformer (ViT) was used to automatically classify 18F-FDG PET/CT slices as benign or malignant. This retrospective study included 18F-FDG PET/CT data of 207 (143 malignant and 64 benign) patients from a medical institute to train and test our models. The ViT model achieved an area under the receiver operating characteristic curve (AUC) of 0.90 [95% CI 0.89, 0.91], which was superior to the baseline Convolutional Neural Network (CNN) models (EfficientNet, 0.87 [95% CI 0.86, 0.88], P < 0.001; DenseNet, 0.87 [95% CI 0.86, 0.88], P < 0.001). Even when FDG uptake was low, ViT produced an AUC of 0.81 [95% CI 0.77, 0.85], which was higher than that of the CNN (DenseNet, 0.65 [95% CI 0.59, 0.70], P < 0.001). We demonstrated the clinical value of ViT by showing its sensitive analysis of easy-to-miss cases of oncological diseases.

Binding Mode-Based Physicochemical Screening Method Using d-Ala-d-Ala Silica Gel and Chemical Modification Approach to Facilitate Discovery of New Macrolactams, Banglactams A and B, from Nonomuraea bangladeshensis K18-0086.

Utilizing a binding mode-based physicochemical screening method using d-Ala-d-Ala silica gel, two new macrolactams, named banglactams A (1) and B (2), were discovered from the culture broth of Nonomuraea bangladeshensis K18-0086. In the course of our investigation, we found that d-Ala-d-Ala silica gel precisely differentiated the chemical structures of banglactams and separated them. However, we were not able to obtain enough of 1 to elucidate the structure due to its instability and insolubility. To overcome this challenge, we chemically modified 1 to improve solubility, enabling us to obtain a sufficient material supply for the indirect determination of the structure. Antibacterial activity evaluation of banglactams revealed that 1 binding to d-Ala-d-Ala silica gel exhibited antibacterial activity against Staphylococcus aureus; however, this was not the case with 2. This research indicates the utility of our original binding mode-based PC screening method, and the combination strategy of PC and chemical modifications led us to discover novel antibacterial compounds.

Automated entry of paper-based patient-reported outcomes: Applying deep learning to the Japanese orthopaedic association back pain evaluation questionnaire.

BACKGROUND: Health-related patient-reported outcomes (HR-PROs) are crucial for assessing the quality of life among individuals experiencing low back pain. However, manual data entry from paper forms, while convenient for patients, imposes a considerable tallying burden on collectors. In this study, we developed a deep learning (DL) model capable of automatically reading these paper forms. METHODS: We employed the Japanese Orthopaedic Association Back Pain Evaluation Questionnaire, a globally recognized assessment tool for low back pain. The questionnaire comprised 25 low back pain-related multiple-choice questions and three pain-related visual analog scales (VASs). We collected 1305 forms from an academic medical center as the training set, and 483 forms from a community medical center as the test set. The performance of our DL model for multiple-choice questions was evaluated using accuracy as a categorical classification task. The performance for VASs was evaluated using the correlation coefficient and absolute error as regression tasks. RESULT: In external validation, the mean accuracy of the categorical questions was 0.997. When outputs for categorical questions with low probability (threshold: 0.9996) were excluded, the accuracy reached 1.000 for the remaining 65 % of questions. Regarding the VASs, the average of the correlation coefficients was 0.989, with the mean absolute error being 0.25. CONCLUSION: Our DL model demonstrated remarkable accuracy and correlation coefficients when automatic reading paper-based HR-PROs during external validation.

Comparison of natural language processing algorithms in assessing the importance of head computed tomography reports written in Japanese.

PURPOSE: To propose a five-point scale for radiology report importance called Report Importance Category (RIC) and to compare the performance of natural language processing (NLP) algorithms in assessing RIC using head computed tomography (CT) reports written in Japanese. MATERIALS AND METHODS: 3728 Japanese head CT reports performed at Osaka University Hospital in 2020 were included. RIC (category 0: no findings, category 1: minor findings, category 2: routine follow-up, category 3: careful follow-up, and category 4: examination or therapy) was established based not only on patient severity but also on the novelty of the information. The manual assessment of RIC for the reports was performed under the consensus of two out of four neuroradiologists. The performance of four NLP models for classifying RIC was compared using fivefold cross-validation: logistic regression, bidirectional long-short-term memory (BiLSTM), general bidirectional encoder representations of transformers (general BERT), and domain-specific BERT (BERT for medical domain). RESULTS: The proportion of each RIC in the whole data set was 15.0%, 26.7%, 44.2%, 7.7%, and 6.4%, respectively. Domain-specific BERT showed the highest accuracy (0.8434 ± 0.0063) in assessing RIC and significantly higher AUC in categories 1 (0.9813 ± 0.0011), 2 (0.9492 ± 0.0045), 3 (0.9637 ± 0.0050), and 4 (0.9548 ± 0.0074) than the other models (p < .05). Analysis using layer-integrated gradients showed that the domain-specific BERT model could detect important words, such as disease names in reports. CONCLUSIONS: Domain-specific BERT has superiority over the other models in assessing our newly proposed criteria called RIC of head CT radiology reports. The accumulation of similar and further studies of has a potential to contribute to medical safety by preventing missed important findings by clinicians.

Injury rate and characteristics in Japanese male professional ice hockey players: prospective study of 60 players over 10 seasons.

Objectives: We aimed to assess the injury rate and characteristics in Japanese male professional ice hockey players. Methods: This study involved an inclusive cohort of male ice hockey players from a Japanese professional team competing in the 2010-2011 through the 2019-2020 seasons. An injury was defined as the 'time-loss and medical attention' definition of the International Ice Hockey Federation. All injuries that occurred during games and practice sessions were recorded daily on injury charts by the team athletic trainers and/or physician. Game-related injury rates were analysed using both the athlete-at-risk (AAR) and time on ice (TOI) methods. Results: Sixty players were included in the study. A total of 479 injuries were recorded, with 307 (64%) occurring during 451 games and 172 (36%) occurring during the practice sessions. The game-related injury rates obtained using the AAR and TOI methods were not statistically different (p>0.05): 115.3 (95% CI 107.1 to 123.1) and 116.8 (95% CI 109.9 to 124.7) per 1000 player-game hours, respectively. Most injuries involved the upper extremities (39.9% game-related, 32.6% practice-related), followed by the lower extremities (23.5% game-related, 32.5% practice-related). The most frequent mechanism of game-related injury was body checking (45.4%). Conclusion: We observed a higher injury rate in a Japanese male professional team compared with rates reported in other leagues. The reported injury characteristics should help to improve injury prevention strategies that should target shoulder dislocations caused by body checking, and finger or wrist fractures resulting from contact with a hockey stick or puck impact.

Surgical Resection of Primary Tumor for Bone Metastatic Breast Cancer Patients at Initial Presentation.

BACKGROUND/AIM: The purpose of this study was to investigate whether primary tumor resection in patients with bone metastatic breast cancer has an impact on survival using the Surveillance, Epidemiology, and End Results database, considering subtype classification. PATIENTS AND METHODS: We included all female patients with bone metastatic breast cancer at initial presentation between 2010 and 2016 with known hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) statuses. Cases showing unknown cause of death or unknown HR/HER2 status were excluded. Survival analysis was performed using Cox proportional hazards modeling to calculate hazard ratios (HZR). RESULTS: Of the 13,450 patients included in this study, 2,073 patients were HR+/HER2+, 8,597 patients were HR+/HER2-, 797 patients were HR-/HER2+, and 1,182 patients were HR-/HER2- (triple-negative). Five-year overall survival (OS) rate was 34.5% in HR+/HER2+, 26.0% in HR+/HER2-, 29.2% in HR-/HER2+ and 8.0% in triple-negative. Triple-negative patients showed the worsen OS [HR+/HER2+: HZR=2.1, 95% confidence interval (CI)=1.9-2.3; HR+/HER2-: HZR= 2.4, 95%CI=2.2-2.6; HR-/HER2+: HZR=1.5, 95%CI=1.3-1.6]. After excluding patients who died within six months, primary tumor resection prolonged survival in each subtype classification except HR-/HER2+. CONCLUSION: Patients with triple-negative bone metastatic breast cancer showed unfavorable survival. Primary tumor resection prolonged survival in each subtype except for HR-/HER2+.

Prediction of solid and micropapillary components in lung invasive adenocarcinoma: radiomics analysis from high-spatial-resolution CT data with 1024 matrix.

PURPOSE: To predict solid and micropapillary components in lung invasive adenocarcinoma using radiomic analyses based on high-spatial-resolution CT (HSR-CT). MATERIALS AND METHODS: For this retrospective study, 64 patients with lung invasive adenocarcinoma were enrolled. All patients were scanned by HSR-CT with 1024 matrix. A pathologist evaluated subtypes (lepidic, acinar, solid, micropapillary, or others). Total 61 radiomic features in the CT images were calculated using our modified texture analysis software, then filtered and minimized by least absolute shrinkage and selection operator (LASSO) regression to select optimal radiomic features for predicting solid and micropapillary components in lung invasive adenocarcinoma. Final data were obtained by repeating tenfold cross-validation 10 times. Two independent radiologists visually predicted solid or micropapillary components on each image of the 64 nodules with and without using the radiomics results. The quantitative values were analyzed with logistic regression models. The receiver operating characteristic curves were generated to predict of solid and micropapillary components. P values < 0.05 were considered significant. RESULTS: Two features (Coefficient Variation and Entropy) were independent indicators associated with solid and micropapillary components (odds ratio, 30.5 and 11.4; 95% confidence interval, 5.1-180.5 and 1.9-66.6; and P = 0.0002 and 0.0071, respectively). The area under the curve for predicting solid and micropapillary components was 0.902 (95% confidence interval, 0.802 to 0.962). The radiomics results significantly improved the accuracy and specificity of the prediction of the two radiologists. CONCLUSION: Two texture features (Coefficient Variation and Entropy) were significant indicators to predict solid and micropapillary components in lung invasive adenocarcinoma.

Corticobasal degeneration with visual hallucination as an initial symptom: A case report.

Although the initial symptoms of corticobasal degeneration (CBD) are varied, psychiatric symptoms are uncommon. Here, we report the autopsy findings of a patient with early CBD who presented with hallucinations. A 68-year-old man developed memory loss and visions of bears and insects. Because of slow vertical eye movement, postural instability, and levodopa-unresponsive parkinsonism, the patient initially was clinically diagnosed with progressive supranuclear palsy. He died of a urinary tract infection 11 months after the onset of the disease. Histopathological examination revealed neuronal loss and gliosis, which were severe in the substantia nigra and moderate in the globus pallidus and subthalamic nucleus. Astrocytic plaques were scattered throughout the amygdala and premotor cortex. The superficial cortical layers lacked ballooned neurons and spongiosis, and tau deposition was greater in glia than in neurons. The amygdala contained a moderate number of argyrophilic grains and pretangles. Western blot analysis showed a 37-kDa band among the low-molecular-weight tau fragments. Because the CBD pathology was mild, we attributed the patient's visual hallucinations to the marked argyrophilic grain pathology. CBD can occur with psychiatric symptoms, including visual hallucinations, and argyrophilic grain pathology may be associated with psychiatric symptoms.

Amputation surgery associated with shortened survival in patients with localized soft tissue sarcoma.

BACKGROUND: The objectives of this study were to clarify whether localized extremity soft tissue sarcoma (STS) patients who underwent amputation surgery experienced worsened survival and to identify those patients for whom amputation surgery worsened survival. METHODS: Using the Surveillance, Epidemiology, and End Results database, we identified 8897 patients with localized extremity STS between 1983 and 2016. Of these 6431 patients, 733 patients underwent amputation surgery (Amputation group), and 5698 underwent limb-sparing surgery (Limb-sparing group). RESULTS: After adjusting for patient background by propensity score matching, a total of 1346 patients were included. Patients in the Amputation group showed worsened survival (cancer-specific survival (CSS): hazard ratio (HR) = 1.42, 95% confidence interval (CI) 1.15-1.75, overall survival (OS): HR = 1.41, 95%CI 1.20-1.65). In subclass analysis, patients with high-grade STS, spindle cell sarcoma and liposarcoma in the Amputation group showed shortened survival (high-grade-CSS: HR = 1.44, 95%CI 1.16-1.77, OS: HR = 1.38, 95%CI 1.18-1.62; spindle cell sarcoma-CSS: HR = 4.75, 95%CI 1.56-14.4, OS: HR = 2.32, 95%CI 1.45-3.70; liposarcoma-CSS: HR = 2.91, 95%CI 1.54-5.50, OS: HR = 2.32, 95%CI 1.45-3.70). CONCLUSIONS: Survival was shortened in localized extremity STS patients who received amputation surgery.

Bone metastatic cancer of unknown primary at initial presentation.

INTRODUCTION: Cancer of unknown primary (CUP) is a challenging malignancy. The purpose of this study was to investigate the clinical characteristics and prognosis of bone metastatic CUP using the population-based Surveillance, Epidemiology, and End Results (SEER) database. METHODS: From the SEER database, we identified 1908 patients with bone metastatic CUP at initial presentation between 2010 and 2018. Histology was subdivided following International Classification of Diseases for Oncology codes as Adenocarcinoma, Squamous cell, Neuroendocrine, or Carcinoma not otherwise specified (NOS). Cox proportional hazard modeling was applied using factors of age, sex, ethnicity, histological subtype, and therapeutic intervention. RESULTS: Among the 1908 patients, histology was Neuroendocrine in 240 patients, Squamous cell in 201 patients, Adenocarcinoma in 810 patients and NOS in 657 patients. In each subtype, patients tended to be predominantly male and white. Chemotherapy was introduced for 28% of patients and radiation for 34% in the entire cohort. Survival in patients with bone metastatic CUP was unfavorable, with a median survival of 2 months. Among the histological subtypes, Adenocarcinoma showed shorter survival than the other groups. In addition, treatment interventions such as chemotherapy and radiation therapy prolonged survival, particularly for Squamous cell, Adenocarcinoma and NOS, but not for Neuroendocrine. DISCUSSION: Bone metastatic CUP showed extremely poor prognosis, but treatment interventions such as chemotherapy and radiation generally offered survival benefits. Further randomized clinical research is needed to confirm the present results.

Atypical TDP-43 proteinopathy clinically presenting with progressive nonfluent aphasia: A case report.

Progressive nonfluent aphasia (PNFA) is a form of frontotemporal lobar degeneration (FTLD) caused by tau and transactive response DNA-binding protein of 43 kDa (TDP-43) accumulation. Here we report the autopsy findings of a 64-year-old right-handed man with an atypical TDP-43 proteinopathy who presented with difficulties with speech, verbal paraphasia, and dysphagia that progressed over the 36 months prior to his death. He did not show pyramidal tract signs until his death. At autopsy, macroscopic brain examination revealed atrophy of the left dominant precentral, superior, and middle frontal gyri and discoloration of the putamen. Spongiform change and neuronal loss were severe on the cortical surfaces of the precentral, superior frontal, and middle frontal gyri and the temporal tip. Immunostaining with anti-phosphorylated TDP-43 revealed neuronal cytoplasmic inclusions and long and short dystrophic neurites in the frontal cortex, predominantly in layers II, V, and VI of the temporal tip, amygdala, and transentorhinal cortex. Immunoblot analysis of the sarkosyl-insoluble fractions showed hyperphosphorylated TDP-43 bands at 45 kDa and phosphorylated C-terminal fragments at approximately 25 kDa. The pathological distribution and immunoblot band pattern differ from the major TDP-43 subtype and therefore may represent a new FTLD-TDP phenotype.

Real-time monitoring of the amyloid ß1-42 monomer-to-oligomer channel transition using a lipid bilayer system.

This study describes the observation of the transformation of monomeric amyloid ß1-42 (Aß42) into oligomers in a lipid membrane utilizing a lipid bilayer system for electrophysiological measurement. The relevance of oligomers and protofibrils in Alzheimer's disease (AD) is underscored given their significant neurotoxicity. By closely monitoring the shift of Aß42 from its monomeric state to forming oligomeric channels in phospholipid membranes, we noted that this transformation transpired within a 2-h frame. We manipulated the lipid membrane's constitution with components such as glycerophospholipid, porcine brain total lipid extract, sphingomyelin (SM), and cholesterol (Chol.) to effectively imitate nerve cell membranes. Interesting findings showcased Chol.'s ability to foster stable oligomeric channel formation in the lipid membrane, with SM and GM1 lipids potentially enhancing channel formation as well. Additionally, the study identified the potential of a catechin derivative, epigallocatechin gallate (EGCG), in obstructing oligomerization. With EGCG present in the outer solution of the Aß42-infused membrane, a noteworthy reduction in channel current was observed, suggesting the successful inhibition of oligomerization. This conclusion held true in both, prior and subsequent, stages of oligomerization. Our findings shed light on the toxicity of oligomers, promising invaluable information for future advancements in AD treatment strategies.

Impact of Multiplex Polymerase Chain Reaction Test in Patients With Meningitis or Encephalitis.

Background: The objective of this study was to evaluate the impact of the FilmArray meningitis/encephalitis panel (FAME) on length of stay (LOS) and duration of antimicrobial treatment in children and adults in a Japanese community hospital. Methods: This retrospective cohort study was conducted in Japan between January 2016 and December 2022. We included hospitalized patients with cerebrospinal fluid (CSF) samples and those aged <2 months or who had 5 or more white blood cells/µL in the CSF. To compare the days of therapy (DOT) and LOS between the pre-FAME and FAME periods, multivariate Poisson regression analyses were conducted without an offset term. Results: The number of cases undergoing pathogen-specific polymerase chain reaction increased from 3.7% in the pre-FAME period to 57.5% in the FAME period (P < .001). The pathogen identification rate also increased during the FAME period, from 0.4% to 18.7% (P < .001). While the antibacterial DOT was not statistically different between the 2 periods (adjusted rate ratio [aRR], 1.06 [95% confidence interval {CI}, 1.00-1.13]; P = .063]), the antiviral DOT was significantly shorter in the FAME period (aRR, 0.80 [95% CI, .71-.89]; P < .001). Conclusions: This study revealed a significant reduction in antiviral use during the FAME period, whereas LOS and antibacterial use did not decrease. Given the possibility of factors (eg, the COVID-19 pandemic) affecting the epidemiology of meningitis and encephalitis, the indications and impact of the FAME test should be evaluated with continuous monitoring of the epidemiology of meningitis and encephalitis and its clinical impact.

Assessing knee joint biomechanics and trunk posture according to medial osteoarthritis severity.

During progression of knee osteoarthritis (OA), gait biomechanics changes three-dimensionally; however, its characteristics and trunk posture according to OA severity remain unknown. The present study investigated three-dimensional knee joint biomechanics and trunk posture according to knee OA severity. Overall, 75 patients (93 knees) with medial knee OA [Kellgren-Lawrence grade ≥ 2, grade 2: 20 patients with 24 knees (mean 60.0 years old); grade 3: 25 with 28 knees (mean 62.0 years old); grade 4: 30 with 41 knees (mean 67.9 years old)] and 14 healthy controls (23 knees, mean 63.6 years old) underwent gait analysis using an optical motion capture system and point cluster technique. In grade 2 knee OA, the relative contribution of the knee adduction moment (KAM) increased significantly (P < 0.05), and that of the knee flexion moment decreased (P < 0.05) prior to significant progression of varus knee deformity. Grade 3 knee OA showed significant exacerbation of varus knee deformity (P < 0.01) and KAM increase (P < 0.001). The maximum knee extension angle decreased (P < 0.05) and trunk flexion increased during gait in grade 4 knee OA (P < 0.001). Our study clarified the kinematics and kinetics of medial knee OA with trunk flexion according to severity. Kinetic conversion occurred in grade 2 knees prior to progression of varus deformities, knee flexion contractures, and sagittal imbalance during gait in patients with severe knee OA.

Chemo-mechanical forces modulate the topology dynamics of mesoscale DNA assemblies.

The intrinsic complexity of many mesoscale (10-100 nm) cellular machineries makes it challenging to elucidate their topological arrangement and transition dynamics. Here, we exploit DNA origami nanospring as a model system to demonstrate that tens of piconewton linear force can modulate higher-order conformation dynamics of mesoscale molecular assemblies. By switching between two chemical structures (i.e., duplex and tetraplex DNA) in the junctions of adjacent origami modules, the corresponding stretching or compressing chemo-mechanical stress reversibly flips the backbone orientations of the DNA nanosprings. Both coarse-grained molecular dynamics simulations and atomic force microscopy measurements reveal that such a backbone conformational switch does not alter the right-handed chirality of the nanospring helix. This result suggests that mesoscale helical handedness may be governed by the torque, rather than the achiral orientation, of nanospring backbones. It offers a topology-based caging/uncaging concept to present chemicals in response to environmental cues in solution.

The study of the efficiency of in vitro maturation of ovarian tissue oocytes in pediatric patients.

PURPOSE: Although recent in vitro maturation (IVM) studies in pediatric patients have demonstrated successful retrieval and maturation of oocytes, the studies included only a small number of premenarchal patients. In the present study, we examined the potential use of oocyte retrieval and maturation for pediatric patients who undergo ovarian tissue cryopreservation (OTC). METHODS: We retrospectively examined the clinical records of pediatric patients who underwent OTC at our institution between October 2015 and December 2022. Data on the age, primary disease, menstrual history, pre-procedure chemotherapy, anti-Müllerian hormone (AMH) level, number of oocytes collected ex vivo from ovarian tissue, and number of mature oocytes from IVM were examined. RESULTS: Data of 60 pediatric patients (aged 1 to 17 years) were included for analysis. Oocytes were retrieved from 36 patients; the oocytes of 18 of these patients could be cryopreserved. The IVM rate was significantly lower in the premenarchal patients than in the postmenarchal patients. The number of mature oocytes retrieved from IVM was higher in the no-chemotherapy group than in the chemotherapy group. A significant positive correlation was observed between the AMH level and the IVM outcomes. CONCLUSION: Oocyte retrieval and maturation in pediatric patients undergoing OTC is particularly useful in those not receiving chemotherapy. In patients receiving chemotherapy, the AMH level may be useful for predicting the IVM outcome. Activation of the oocyte maturation process in vivo in pediatric patients and better understanding of the major regulators of oocyte maturation are necessary to improve the utility of the IVM procedure.

Design and Synthesis of d-Ala-d-Ala Silica Gel for a Binding Mode-Based Physicochemical Screening Method.

Vancomycin is a potent and broad-spectrum antibiotic that binds to the d-Ala-d-Ala moiety of the growing bacterial cell wall and kills bacteria. This fascinating binding model prompted us to design and synthesize d-Ala-d-Ala silica gels for the establishment of a new physicochemical (PC) screening method. In this report, we confirmed that vancomycin binds to d-Ala-d-Ala silica gel and can be eluted with MeOH containing 50 mM TFA. Finally, d-Ala-d-Ala silica gel enables to purify vancomycin from the culture broth of a vancomycin-producing strain, Amycolatopsis orientalis.

Bimodal artificial intelligence using TabNet for differentiating spinal cord tumors-Integration of patient background information and images.

We proposed a bimodal artificial intelligence that integrates patient information with images to diagnose spinal cord tumors. Our model combines TabNet, a state-of-the-art deep learning model for tabular data for patient information, and a convolutional neural network for images. As training data, we collected 259 spinal tumor patients (158 for schwannoma and 101 for meningioma). We compared the performance of the image-only unimodal model, table-only unimodal model, bimodal model using a gradient-boosting decision tree, and bimodal model using TabNet. Our proposed bimodal model using TabNet performed best (area under the receiver-operating characteristic curve [AUROC]: 0.91) in the training data and significantly outperformed the physicians' performance. In the external validation using 62 cases from the other two facilities, our bimodal model showed an AUROC of 0.92, proving the robustness of the model. The bimodal analysis using TabNet was effective for differentiating spinal tumors.