Specific Patient Characteristics Research Articles

Discovering patient groups in sequential electronic healthcare data using unsupervised representation learning

IntroductionUnsupervised feature learning methods inspired by natural language processing (NLP) models are capable of constructing patient-specific features from longitudinal Electronic Health Records (EHR).DesignWe applied document embedding algorithms to real-world paediatric intensive care (PICU) EHR data to extract patient-specific features from 1853 patients’ PICU journeys using 647 unique lab tests and medication events. We evaluated the clinical utility of the patient features via a K-means clustering analysis.ResultsWe trained a document embedding model under a unique evaluation pipeline and obtained latent patient feature vectors for all 1853 patients. We performed unsupervised clustering to the patient vectors as a downstream analysis and obtained 5 distinct clusters via hyperparameter optimisation. Significant variations (p<0.0001) within both patient characteristics and surgery intervention and diagnostic profiles were detected.ConclusionThe K-means clustering results demonstrated the clinical utilities of the patient-specific features learned from the embedding algorithms. The latent patient features obtained via the embedding process enabled direct applications of other machine learning algorithms. Future work will focus on utilising the temporal information within EHR and extending EHR embedding algorithms to develop personalised patient journey predictions.

Regional anesthesia in the patient receiving antithrombotic or thrombolytic therapy: American Society of Regional Anesthesia and Pain Medicine Evidence-Based Guidelines (fifth edition)

Hemorrhagic complications associated with regional anesthesia are extremely rare. The fifth edition of the American Society of Regional Anesthesia and Pain Medicine’s Evidence-Based Guidelines on regional anesthesia in the patient...

Construction of feature selection and efficacy prediction model for transformation therapy of locally advanced pancreatic cancer based on CT, 18F-FDG PET/CT, DNA mutation, and CA199

BackgroundImmunotherapy and radiotherapy play crucial roles in the transformation therapy of locally advanced pancreatic cancer; however, the exploration of effective predictive biomarkers has been unsatisfactory. With the rapid development of radiomics, next-generation sequencing, and machine learning, there is hope to identify biomarkers that can predict the efficacy of transformative treatment for locally advanced pancreatic cancer through simple and non-invasive clinical methods. Our study focuses on using computed tomography (CT), positron emission tomography/computed tomography (PET/CT), gene mutations, and baseline carbohydrate antigen 199 (CA199) to identify biomarkers for predicting the efficacy of transformative treatment.MethodsWe retrospectively collected data from 70 patients with locally advanced pancreatic cancer who had undergone a biopsy for pathological diagnosis. These patients had complete baseline enhanced CT images and baseline CA199 results. Among them, 65 patients had efficacy evaluation results after 4 treatment cycles, 54 patients had complete baseline PET/CT images, 51 patients had complete DNA mutation detection results, and 34 patients had both complete PET/CT images and DNA mutation detection results. Additionally, 47 patients had complete available CT images at baseline, after 2 treatment cycles, and after 4 treatment cycles. We extracted radiomic features from the original lesion-enhanced CT images (including baseline and subsequent follow-up CT scans), radiomic features from baseline 18F-fluoro-2-deoxy-2-D-glucose (18F-FDG) PET, and patient-specific features related to abdominal and visceral fat. We used short-term and long-term treatment efficacy as the prediction outcomes and performed statistical and machine learning-based feature selection and COX regression analysis to identify potentially predictive features. Subsequently, we separately or in combination modeled the CT features, PET features, baseline CA199, and gene mutation data to construct efficacy prediction models. Finally, we investigated the mixed effects model of the dynamic changes in CT features at baseline, after 2 treatment cycles, and after 4 treatment cycles on the prediction of short-term treatment efficacy.ResultsWe found that a combination of CT radiomic features, including F1_ gray level co-occurrence matrix (GLCM), F2_gray level run length matrix (GLRLM), F5_neighboring gray tone difference matrix (NGTDM), and F6_Shape, PET radiomic features such as visceral adipose tissue (VAT), tumor-to-liver ratio (T/L), standardized uptake value mean (SUVmean), and GLCM, as well as baseline CA199, can be used to predict short-term treatment efficacy. Baseline CA199, GLCM, IntensityDirect, Shape, and PET/CT features are independent factors for long-term treatment efficacy. In constructing the short-term treatment efficacy prediction model, ensemble learning methods such as adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and RandomForest performed the best. However, in terms of model interpretability, decision tree methods provide the most intuitive display of the predictive details of the model. For the time series data of patients’ baseline CT, CT after 2 treatment cycles, and CT after 4 treatment cycles, long short-term memory (LSTM) modeling yielded better predictive models.ConclusionA multimodal combination of radiomics, DNA mutations, and baseline CA199 can predict the efficacy of transformative treatment in locally advanced pancreatic cancer. Various feature selection methods and multimodal fusion approaches contribute to guiding personalized and precise treatment for pancreatic cancer.

Diagnostic Algorithm Using Multimodal Imaging for the Differential Diagnosis of Intra-Cardiac Masses.

Cardiac masses are complex clinical conditions that frequently pose diagnostic challenges in cardiology practice. These masses can form within heart chambers or near the pericardium and are generally categorized as either non-neoplastic or neoplastic. These latter are further classified into benign and malignant (primary and secondary or metastatic). Diagnosing these conditions often requires a multiparametric approach that includes both clinical features, such as the patient's and associated clinical conditions, and multimodality imaging. However, histological examination of the resected specimen is often necessary to ascertain the nature of the mass. Given their heterogeneity and the rarity of many cardiac masses, there are no guidelines or consensus on the best diagnostic approach. Modern imaging protocols must be tailored to the specific clinical issues and patient characteristics, given the rapid advancements in technology. Thus, it is imperative to use a multimodality approach, combining different imaging techniques and multidisciplinary teamwork. Hereby, we propose a practical algorithm for evaluating cardiac lesions using a step-by-step implementation of multimodal imaging. Ultimately, the goal is to tailor the most suitable imaging technique to the patient's needs.

Registry versus claims-based index dates for studies of cancer diagnosis in administrative data.

Studies of healthcare encounters leading to cancer diagnosis have increased over recent years. While some studies examine healthcare utilization before the cancer registry date of diagnosis, relevant pre-diagnosis interactions are not always immediately prior to this date due to date abstraction guidelines. We evaluated agreement of a registry date with a claims-based index and examined Emergency Department (ED) involvement in cancer diagnosis as an example of possible pre-diagnostic healthcare misclassification that could arise from improper date choice. We implemented an algorithm to define a claims-based index as the date of the earliest International Classification of Diseases code for the cancer in Medicare and estimated agreement with the date of diagnosis from a North Carolina registry for patients diagnosed aged 66 or older with 16 cancer types from 2008 to 2017 (n = 92,056). We then classified whether each cancer was initially diagnosed through care originating in the ED using each date. The index date was identical to the cancer registry date for 47% of patients and preceded the registry date for 28%, with extent of agreement varying by cancer- and patient-specific characteristics. Agreement in ED-involved diagnosis classification using each date varied by cancer site, with sensitivity of classifications using the registry date relative to the index having a minimum of 86% for prostate and kidney cancer. Studies assessing healthcare utilization proximal to cancer diagnosis should carefully consider the relevant assessment window and be aware that the use of cancer registry versus claims-based dates may impact variable classification.

The Impact of Tibial Slope on Anterior Cruciate Ligament Reconstruction Outcomes – University Hospital Study

Anterior cruciate ligament (ACL) injuries are common knee injuries that often require surgical reconstruction to restore knee function and stability. Despite advances in surgical techniques, the failure rate for ACL reconstruction remains approximately 15%, emphasizing the need to understand factors contributing to suboptimal outcomes. One factor that has garnered attention is the tibial slope, particularly the posterior tibial slope (PTS), which may influence ACL injury and graft failure. Biomechanical studies suggest that an increased PTS can elevate anterior tibial translation, potentially increasing stress on the ACL and raising the risk of both primary ACL injury and graft failure. However, the clinical significance of tibial slope in ACL reconstruction outcomes remains debated. This retrospective study investigates whether an increased PTS is associated with a higher likelihood of revision surgery or poor surgical outcomes. A total of 152 patients who underwent primary ACL reconstruction or revision surgery between 2018 and 2022 with at least two years of follow-up were included. Tibial slope measurements were obtained from lateral tibial radiographs, and patients were categorized into three groups based on post-surgical outcomes: Group A (successful return to prior sport levels), Group B (stable knee without return to sport), and Group C (requiring revision surgery). The Mann-Whitney U test was used to compare tibial slope measurements across groups. No significant differences were found in tibial slope between the groups (p &gt; 0.05). Group A had a median tibial slope of 6.08°, Group B had 6.68°, and Group C had 5.85°. These findings suggest that tibial slope may not be a major factor influencing ACL reconstruction success or failure. Other factors, including surgical technique, rehabilitation, and patient-specific characteristics, may play more significant roles. Further research is needed to explore the relationship between tibial slope and ACL ...

Hepatocellular carcinoma: Revising the surgical approach in light of the concept of multiparametric therapeutic hierarchy.

The clinical management of hepatocellular carcinoma (HCC) is strongly influenced by several prognostic factors, mainly tumor stage, patient's health, liver function and specific characteristics of each intervention. The interplay between these factors should be carefully evaluated by a multidisciplinary tumor board. To support this, the novel "multiparametric therapeutic hierarchy" (MTH) concept has been recently proposed. This review will present the main features of available surgical treatments for HCC (liver transplantation, liver resection, ablation). Strengths and weaknesses are reported in the light of clinical decision making and of treatment allocation, with a special focus on the collocation of each treatment in the MTH framework and on how MTH may be useful in supporting clinical decision. Sequential treatments and their role to allow further surgical treatments will also be analyzed.

Positive signs from the history as an aid for early diagnosis in functional movement disorders: The prospective TASMAN study.

There has been a concerted move in recent times to shift from an exclusionary to a positive diagnosis of functional movement disorders (FMDs). To date, most of the focus has been on defining positive physical signs. Here the focus was on the diagnostic specificity of specific symptoms and patient characteristics. For this prospective cohort study, newly referred patients in the Netherlands and Australia were recruited before their first neurology appointment. Participants completed questionnaires within 2 months prior to their visit at one of the six different clinics. Directly following the first consultation, physicians received a questionnaire about their diagnostic process. Patients were excluded if the diagnosis was not a movement disorder. Univariate and multivariate regression analyses were conducted to identify predictors of FMDs. Subsequently, a predictive model was constructed and assessed using the area under the receiver operating curve. Between 1 March 2021 and 1 March 2023, 465 patients were eligible for inclusion, of whom 171 (37%) had an FMD and 294 (63%) a non-FMD. Distinguishing factors amongst these groups included age at onset, gender, history or family history of a functional and psychiatric disorder, sudden onset, specific triggers, fluctuation patterns throughout the day and over an extended period, pain, fatigue, depression, anxiety and dissociation. Using these, a predictive model was developed, yielding a discriminative accuracy of 88%. Specific symptoms and patient characteristics have high diagnostic discriminative value between FMDs and non-FMDs, providing an additional tool in positive diagnosis.

Improving Individualized Salbutamol Treatment: A Population Pharmacokinetic Model for Oral Salbutamol in Virtual Patients.

Salbutamol, a short-acting β2-agonist used in asthma treatment, is available in multiple formulations, including inhalers, nebulizers, oral tablets, and intravenous, intramuscular, and subcutaneous routes. Each formulation exhibits distinct pharmacokinetic (PK) and pharmacodynamic (PD) profiles, influencing therapeutic outcomes and adverse effects. Although asthma management predominantly relies on inhaled salbutamol, understanding how these formulations interact with patient-specific characteristics could improve personalized medicine approaches, potentially uncovering the therapeutic benefits of alternative formulations for an individual patient. Herein, this study aims to analyze how covariates-such as age, weight, gender, body surface area (BSA), cytochrome P450 (CYP) expression, race, and health status-affect the therapeutic regime of orally administered salbutamol using population PK (popPK) modeling. The final model is intended as a tool to support the selection of optimal formulation and dosage regimen based on individual patient profiles. A dataset of 40 virtual patients derived from a physiologically based PK (PBPK) model of oral salbutamol was included in the popPK model. A two-compartment model with first-order elimination and absorption, with a transit compartment, best described the plasma concentration-time profile following a 4 mg dose. Relationships were identified between gender and mean transit time (Mtt) and clearance (Cl), as well as the effects of weight and BSA on the volume of distribution of the central compartment (V1) and Cl, and a significant impact of health status on Cl. Despite current contraindications for oral salbutamol, our findings suggest that certain individuals, particularly children, may benefit from oral treatment over inhalation. We also identified individual characteristics associated with increased salbutamol toxicity risk, indicating the need for dose adjustment or alternative administration. This study further highlights the potential of popPK modeling in personalized therapy through a fully in silico approach.

A qualitative analysis of healthcare professionals’ experiences with an internet-based emotion regulation intervention added to acute psychiatric inpatient care

BackgroundHealthcare professionals play an important role in successfully implementing digital interventions in routine mental healthcare settings. While a larger body of research has focused on the experiences of mental healthcare professionals with the combination of digital interventions and face-to-face outpatient treatment, comparatively little is known about their experiences with digital interventions combined with inpatient treatment. This is especially true for acute psychiatric inpatient care, where studies on the implementation of digital interventions are more rare. The current study aimed to investigate healthcare professionals’ experiences with an internet-based emotion regulation intervention added to acute psychiatric inpatient treatment.MethodsPhysicians, nurses, psychologists, social workers, and occupational therapists from three acute inpatient wards (n = 20) were interviewed regarding their experiences. A thematic analysis approach was used to analyze the interview data.ResultsThe following themes and corresponding subthemes were identified: lack of experience (few or no previous experiences, no expectations, few points of contact), the intervention as a contemporary complement (positive expectations, necessary and contemporary, positive effects on therapeutic work and patients, characteristics of the internet-based program), concerns about fit for acute psychiatric inpatient care (fit for acute psychiatric inpatients, doubts about implementation), the human factor as essential for implementation (the team makes or breaks it, guidance is key, patient characteristics), and requirements for implementation beyond the human factor (integration into existing treatment structure, resources, changes to the internet-based program, timing).ConclusionsWhile healthcare professionals reported few points of contact with the intervention, they saw it as a contemporary complement to acute psychiatric inpatient care with benefits for therapeutic work and patients. The findings further suggest that specific concerns regarding the fit for acute psychiatric inpatient care remain and that human factors such as support from the ward team, human guidance during the intervention and being mindful of specific patient characteristics are considered important for implementation. Moreover, factors such as integration of the intervention into the ward program, resource availability and the timing of the intervention during a patient’s individual stay should be considered for successful implementation.Trial registrationClinicaltrials.gov, NCT04990674, 04/08/2021.

Personalized Vascularized Tumor Organoid-on-a-Chip for Tumor Metastasis and Therapeutic Targeting Assessment.

While tumor organoids have revolutionized cancer research by recapitulating the cellular architecture and behaviors of real tumors in vitro, their lack of functional vasculature hinders their attainment of full physiological capabilities. Current efforts to vascularize organoids are struggling to achieve well-defined vascular networks, mimicking the intricate hierarchy observed in vivo, which restricts the physiological relevance particularly for studying tumor progression and response to therapies targeting the tumor vasculature. An innovative vascularized patient-derived tumor organoids (PDTOs)-on-a-chip with hierarchical, tumor-specific microvasculature is presented, providing a versatile platform to explore tumor-vascular dynamics and antivascular drug efficacy. It is found that highly metastatic tumor cells induced vessel angiogenesis and simultaneously migrated toward blood vessels via the Notch pathway. The evident association between the angiogenic and migratory capacities of PDTOs and their clinical metastatic outcomes underscores the potential of the innovative platform for evaluating tumor metastasis, thus offering valuable insights for clinical decision-making. Ultimately, the system represents a promising avenue for advancing the understanding of tumor metastasis and developing personalized treatment strategies based on patient-specific tumor characteristics.

Influence of Breast Density and Menopausal Status on Background Parenchymal Enhancement in Contrast-Enhanced Mammography: Insights from a Retrospective Analysis.

Background: Contrast-enhanced mammography (CEM) has recently gained recognition as an effective alternative to breast magnetic resonance imaging (MRI) for assessing breast lesions, offering both morphological and functional imaging capabilities. However, the phenomenon of background parenchymal enhancement (BPE) remains a critical consideration, as it can affect the interpretation of images by obscuring or mimicking lesions. While the impact of BPE has been well-documented in MRI, limited data are available regarding the factors influencing BPE in CEM and its relationship with breast cancer (BC) characteristics. Materials: This retrospective study included 116 patients with confirmed invasive BC who underwent CEM prior to biopsy and surgery. Data collected included patient age, breast density, receptor status, tumor grading, and the Ki-67 proliferation index. BPE was evaluated by two radiologists using the 2022 ACR BI-RADS lexicon for CEM. Statistical analyses were conducted to assess the relationship between BPE, patient demographics, and tumor characteristics. Results: The study found a significant association between higher levels of BPE and specific patient characteristics. In particular, increased BPE was more commonly observed in patients with higher breast density (p < 0.001) and those who were pre-menopausal (p = 0.029). Among patients categorized under density level B, the majority exhibited minimal BPE, while those in categories C and D showed progressively higher levels of BPE, indicating a clear trend correlating higher breast density with increased enhancement. Additionally, pre-menopausal patients demonstrated a higher likelihood of moderate to marked BPE compared to post-menopausal patients. Despite these significant associations, the analysis did not reveal a meaningful correlation between BPE intensity and tumor subtypes (p = 0.77) or tumor grade (p = 0.73). The inter-reader agreement for BPE assessment was substantial, as indicated by a weighted kappa of 0.78 (95% CI: 0.68-0.89), demonstrating consistent evaluation between radiologists. Conclusions: These findings suggest that BPE in CEM is influenced by factors like breast density and age, aligning with patterns observed in MRI studies. However, BPE intensity was not associated with tumor subtypes or grades, indicating a poorer prognosis. These insights highlight the potential of BPE as a risk biomarker in preventive follow-up, particularly for patients with high breast density and pre-menopausal status. Further multicentric and prospective studies are needed to validate these results and deepen the understanding of BPE's role in CEM diagnostics.

Optimizing Individualized Antimicrobial Dosing in Pediatric Patients: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

Therapeutic drug monitoring (TDM) and target concentration intervention (TCI) represent significant advancements in individualized medicine, aiming to tailor dosages based on patient-specific characteristics. These approaches account for intra- and inter-individual physiological and clinical variability, with the goal of improving target attainment and clinical remission while reducing treatment failure and adverse effects. The objective is to assess and enhance the current body of randomized controlled trials (RCTs) that have investigated alternative personalized dosing strategies, such as TDM and TCI, in terms of their efficacy and safety for individualized antimicrobial dosing in pediatric populations. Only studies that compared different dosing regimens and reported plasma concentrations were included in the analysis. Databases such as MEDLINE, Embase, Web of Science, and the Cochrane Central Register of Controlled Trials were searched until January 3rd, 2024. Only published, peer-reviewed RCTs were considered for inclusion. The study focused on human subjects aged < 18 years who were receiving an antimicrobial drug. The interventions compared experimental dosing versus standard dosing with TDM or TCI. The risk of bias was assessed using version 2 of the Cochrane risk-of-bias tool for randomized trials. The primary outcome was the attainment of target concentrations, while secondary outcomes included adverse effects, clinical remission, and treatment failure. Data synthesis was performed using the restricted maximum likelihood method, and the risk ratio (RR) was used as the measure of effect size. Only 11 TDM-based RCTs were included in the study [experimental vs standard doses: 592 (51.3%) patients vs 563 (48.7%) patients]. Experimental dose was significantly associated with improvement in target attainment (RR 1.2587, OR 1.0717-1.4786; p=0.0051). However, experimental antimicrobial dose optimization was non-significantly associated with a numerical decrease in treatment failure (RR 0.8966, OR 0.7749-1.0374; p=0.1424). In addition, it was not significant associated with higher adverse effects [RR 1.3408, odds ratio (OR) 0.1783-10.0825; p=0.7757] and clinical remission rates (RR 4.0589, OR 0.2494-66.0558; p=0.3250). This meta-analysis showed that only target attainment using TDM was significantly improved in pediatric patients treated with experimental doses of antimicrobials compared to standard doses. Larger TCI-focused RCTs are needed to significantly improve treatment failure, adverse effects, and clinical remission.

Emergency Department Use Within 90 Days After Single-Level Posterior Cervical Foraminotomy.

This study sought to characterize the incidence of, timing of, predictive factors for, and reasons for emergency department (ED) visits within 90 days of single-level posterior cervical foraminotomy (PCF). These visits, after PCF, have received limited attention. The 2010-2022 M161 PearlDiver database was queried for elective single-level PCFs, excluding multilevel procedures, midline laminectomies, fusions, or other posterior/anterior procedures, as well as indications of trauma, infection, or neoplasm. Patient age, sex, Elixhauser Comorbidity Index (ECI), insurance, and region were extracted. Weekly ED use after PCF was calculated. Multivariate analyses were used to identify predictive factors for ED use, and primary ED diagnoses were categorized. Of 10,588 PCF patients, 9.09% (n=962) visited the ED within 90 days after surgery, mostly in the first 4 weeks. Multivariate analysis identified that predictors included younger age (odds ratio [OR], 1.02 per decade decrease), female sex (OR, 1.19), higher ECI (OR, 1.28 for ECI 1-2; OR, 1.41 for ECI 3-4; OR, 1.51 for ECI ≥5), Midwest (OR, 1.16) or Northeast (OR, 1.19) region, and Medicare (OR, 1.09) or Medicaid (OR, 1.57) coverage. In the first 4 weeks, 69.9% of ED visits were related to the surgical site; this decreased to 27.1% thereafter. Almost one-tenth of PCF patients visited the ED within 90 days after surgery. Specific patient characteristics were associated with ED visits, with surgical site-related diagnoses predominating in the acute postoperative period. Tailoring health care interventions based on timing of, risk factors for, and causes of ED visits may enhance outcomes and reduce costs. [Orthopedics. 202x;4x(x):xx-xx.].

Anterior communicating artery aneurysm microsurgery resulted in a proximal pseudoaneurysm

Intracranial pseudoaneurysms (IPAs), characterized by compromised vessel wall layers, represent &lt;1% of all intracranial aneurysms. They often materialize along the vessel wall and are vulnerable to rupture, resulting in a mortality rate of up to 50%. Treatment is complex due to the fragility of pseudoaneurysms, the absence of a suitable surgical neck, and frequently associated intracranial atherosclerosis and calcification. This study reports a rare instance of an IPA following a microsurgical clipping of an intracranial aneurysm. A 48-year-old male with severe headache, vomiting, and brief unconsciousness was diagnosed with a ruptured anterior communicating artery aneurysm. After successful microsurgical clipping, a follow-up computed tomography angiogram revealed a new aneurysmal dilation on the anterior aspect of the pre-bifurcation segment of the right internal carotid artery (ICA). A subsequent craniotomy was performed to address the ICA pseudoaneurysm. Owing to the calcification surrounding the pseudoaneurysm, it was safeguarded with crushed muscle and cellulose fabric. Follow-ups showed no pseudoaneurysm enlargement, and the patient recovered with no neurological deficits. Iatrogenic IPAs post-aneurysmal clipping are exceptionally rare yet dangerous entities necessitating rapid intervention to minimize morbidity and mortality. Tailoring treatment modalities based on patient-specific characteristics, lesion attributes, and surgical expertise is fundamental. A cautious follow-up regimen is also suggested to monitor the pseudoaneurysm’s dimensions effectively.

Referral patterns for common surgical procedures in Ontario: a cross-sectional population-level study.

Little is known about the existing structure and function of referral networks in the prevalent referral system for specialized surgical care in Canada, which is based on direct physician referral to specialists in a largely unmanaged referral marketplace. Our objective was to describe and analyze the referral networks of referring physicians and surgeons for common surgical procedures in Ontario, to better understand potential barriers to single-entry models. We analyzed referral networks for patients between referring physicians and surgeons for 9 common scheduled surgical procedures from 2016 to 2019 using administrative data sources in Ontario. We described the connectedness of referring physician-surgeon pairs using descriptive measures and graphical social network analysis. The median number of surgeons connected to a referring physician for patients having a particular surgical procedure ranged from 1 (interquartile range [IQR] 1-3) for spine surgery to 3 (IQR 1-4) for knee arthroplasty and 3 (IQR 2-5) for noncancer uterine procedures. Referral network structure varied according to the procedure studied. Spine surgery was highly clustered with a small number of larger groups; gallbladder, inguinal hernia, and noncancer uterine surgery were highly distributed with many small groups within the referral network. Breast cancer surgery occurred in a largely distributed network, but with a skewed distribution reflecting a few small groups with large numbers of patients. Improving surgical wait times by coordinating surgical referrals will require approaches that address the structure of existing referral networks. Most physicians refer their patients to a very small number of surgeons, suggesting that referring physicians largely do not individualize referrals to multiple different surgeons based on specific patient characteristics.

Personalized bone organoid using iPSC-derived cells for clinically relevant applications.

Patient-specific induced pluripotent stem cells (iPSCs)-based modeling potentially recapitulates the pathology and mechanisms more faithfully than cell line models and general animal models. Utilizing iPSC-derived cells for personalized bone formation research offers a powerful tool to better understand the role of individual differences in bone health and disease and provide more precise information for personalized bone regeneration therapies. Here we generated iPSC-derived mesenchymal progenitor cells (iMPCs), endothelial cells (iECs), and macrophages (iMØ), from different donors. Cellular markers, pluripotency properties, and immune regulatory properties were investigated. To replicate bone regeneration, we utilize different iPSC models and co-cultured three distinct cell types (iMPCs, iECs, and iMØ) in a 3D in vitro model derived from the same donor. Cells from different donors exhibited patient-specific characteristics and different regenerative capacities. Our study suggests that cells differentiated from iPSCs can be used to anticipate the effectiveness of cell-based therapies for personalized tissue regeneration.

Utilizing deep learning-based causal inference to explore vancomycin's impact on continuous kidney replacement therapy necessity in blood culture-positive intensive care unit patients.

Patients with positive blood cultures in the intensive care unit (ICU) are at high risk for septic acute kidney injury requiring continuous kidney replacement therapy (CKRT), especially when treated with vancomycin. This study developed a machine learning model to predict CKRT and examined vancomycin's impact using deep learning-based causal inference. We analyzed ICU patients with positive blood cultures, utilizing the Medical Information Mart for Intensive Care III data set. The primary outcome was defined as the initiation of CKRT during the ICU stay. The machine learning models were developed to predict the outcome. The deep learning-based causal inference model was utilized to quantitatively demonstrate the impact of vancomycin on the probability of CKRT initiation. Logistic regression was performed to analyze the relationship between the variables and the susceptibility of vancomycin. A total of 1,318 patients were included in the analysis, with 41 requiring CKRT. The Random Forest and Light Gradient Boosting Machine exhibited the best performance, with Area Under Curve of Receiver Operating Characteristic Curve values of 0.905 and 0.886, respectively. The deep learning-based causal inference model demonstrated an average 7.7% increase in the probability of CKRT occurrence when administrating vancomycin in total data set. Additionally, that younger age, lower diastolic blood pressure, higher heart rate, higher baseline creatinine, and lower bicarbonate levels sensitized the probability of CKRT application in response to vancomycin treatment. Deep learning-based causal inference models showed that vancomycin administration increases CKRT risk, identifying specific patient characteristics associated with higher susceptibility.IMPORTANCEThis study assesses the impact of vancomycin on the risk of continuous kidney replacement therapy (CKRT) in intensive care unit (ICU) patients with blood culture-positive infections. Utilizing deep learning-based causal inference and machine learning models, the research quantifies how vancomycin administration increases CKRT risk by an average of 7.7%. Key variables influencing susceptibility include baseline creatinine, diastolic blood pressure, heart rate, and bicarbonate levels. These findings offer insights into managing vancomycin-induced kidney risk and may inform patient-specific treatment strategies in ICU settings.

The Impact of Clinical Parameters on LSTM-based Blood Glucose Estimate in Type 1 Diabetes

Accurate forecasting of blood sugar levels is essential for managing diabetes, especially Type-1 reducing incidences, and diminishing care, costs in patients. In this study, a Long Short-Term Memory Recurrent Neural Network (LSTM) model has been employed to predict blood glucose levels using clinical data. The research focuses on identifying and analyzing several key parameters that play a significant role in determining future blood glucose levels, ensuring a robust and reliable prediction framework. We have considered patient-specific features: Insulin-Sensitivity-Factor (ISF), total daily dose (TDD) of insulin, HbA1C levels, height and weight of a patient, and age and gender while analyzing the prediction performance for Blood Glucose. We thought training LSTM models on a large dataset and studying the most important predictors with their predictive power would be beneficial. The results indicate that including these clinical parameters improves the accuracy of blood glucose prediction and provides valuable information for individuals to control diabetes. This analysis highlights the efficiency of LSTM networks in making use of patient data to improve prediction models, eventually aiding more effective and individualized treatment strategies for Type 1 diabetic patients (T1D). This work also examines the extent to which each parameter influences the prediction of future blood glucose levels, providing deeper insights into their relative impact and significance in the predictive model.

Non-Operative Ttreatment of patients with Chondrosarcoma: An analysis of patients who refused cancer-directed surgery or patients contraindicated to surgery.

Chondrosarcomas are the second most common primary bone sarcoma. Due to chondrosarcomas relative resistance to chemotherapy and radiation, surgical treatment has become the mainstay treatment option. The purpose of our study was to understand the proportion of patients in this population who undergo non-operative treatment options secondary to various reasons and analyze the difference in survival as well as patient and cancer specific characteristics between the two groups. We retrospectively reviewed the Surveillance, Epidemiology, and End Results (SEER) database for patients diagnosed with primary chondrosarcoma from 1973 to 2015. We evaluated the patients for both descriptive characteristics as well as cancer specific characteristics. We then performed a propensity matched analysis and other analyses to compare difference in cancer characteristics as well as survival. There were 3048 patients with chondrosarcoma of the bone during our study period of which 188(6.2%) patients did not undergo operative treatment either due to refusal of cancer directed surgery or contraindicated to surgery. A one unit increase in age was significantly associated with increased odds of not undergoing surgery(Odds Ratio 1.04;95% CI, 1.03- 1.05). No statistically significant difference(P = 0.9) in survival was noted between patients with long bone, grade 1 chondrosarcomas regardless of if they did or did not undergo operative treatment. This study provides data to inform the patient on their decisions for or against surgery and may assist the surgeons in counseling patients regarding the surgical treatment of chondrosarcomas. Patients not undergoing operative treatment for chondrosarcomas are at statistically significantly increased risk of mortality.