Optimal Clinical Decisions Research Articles

Dynamic CT myocardial perfusion combined with coronary CT angiography for detecting hemodynamical significance of coronary artery stenosis: a comparative study

This study aimed to evaluate the diagnostic performance of combined dynamic stress CT myocardial perfusion imaging (CTP) and coronary CT angiography (CTA) alongside CT-derived fractional flow reserve (CT-FFR) in detecting hemodynamically significant coronary artery disease (CAD). A total of 33 patients (86 vessels) who underwent coronary CTA, dynamic stress CTP, and coronary angiography were included. Vessels exhibiting 30–90% stenosis were subjected to FFR analysis based on coronary angiography (Angio-FFR). Hemodynamic significance, determined by Angio-FFR ≤ 0.80, and imaging findings were evaluated. The evaluation involved a comparison between the combined use of coronary CTA, CTP and CT-FFR, versus the sole use of coronary CTA. Out of 86 coronary vessels, 17 (19.8%) exhibited hemodynamically significant stenosis. The sensitivity, specificity, and accuracy of coronary CTA for detecting ischemia were 94.12%, 34.78%, and 46.51%, respectively. Adding CTP to CTA improved specificity to 88.41%, and accuracy to 87.21%, respectively. The area under the curve (AUC) for the discrimination of functional significant stenosis was 0.798 when using CTA alone, and for CTA plus CTP, it reached 0.910. Furthermore, the combination of CTA, CTP and CT-FFR, showed accuracy of 88.37%, sensitivity of 88.24% and specificity of 88.41% with the AUC of 0.946. The integration of dynamic CTP with CTA significantly enhances the diagnostic accuracy for identifying patients with hemodynamically significant CAD, compared to the use of CTA alone. This study underscores the value of combining CTP, CT-FFR, and CTA in improving diagnostic precision for CAD. The combination of CTP, CT-FFR and CTA offers a multifaceted assessment for patients with CAD by simultaneously providing anatomical detail, functional analysis, and physiological quantification, which facilitating rapid, accurate, and optimal clinical decision-making and significantly enhances patient management.

Investigating the role of thrombosis and false lumen orbital orientation in the hemodynamics of Type B aortic dissection

While much about the fundamental mechanisms behind the initiation and progression of Type B aortic dissection (TBAD) is still unknown, predictive models based on patient-specific fluid-structure interaction (FSI) simulations can help in risk stratification and optimal clinical decision-making. Aiming at the development of personalized treatment, FSI models can be leveraged to investigate the interplay between complex aortic flow patterns and anatomical features, while considering the deformation of the arterial wall and the dissection flap. In this study, the hemodynamics of false lumen thrombosis, a large fenestration, and the orbital orientation of the false lumen is studied through image-based FSI simulations on three TBAD patient-specific geometries. A new pipeline is developed leveraging the open-source software SimVascular and ParaView to analyze multiple patients simultaneously and to achieve large-scale parallelization in FSI results based on patients’ computed tomography (CT) images. The results of this study suggest that the internal orbital orientation of the false lumen contributes to maintaining a positive luminal pressure difference ΔPTL-FL\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Delta P_{TL-FL}$$\\end{document} = PTL-PFL\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$P_{TL}-P_{FL}$$\\end{document} between the true lumen (TL) and the false lumen (FL), despite an impingement area in the false lumen near the entry tear. A positive and high luminal pressure difference is thought to promote TL expansion and FL compression. Moreover, it was also found that FL thrombosis at the entry tear region reduce the magnitude of the negative luminal pressure difference, which in turn may reduce FL expansion and the risk of unstable aortic growth. Finally, this FSI study suggests that the aortic wall and dissection flap stiffness determines the effects of a large fenestration in the descending thoracic aorta on the luminal pressure difference.

Duplex-ultrasound as a single imaging test for Global Limb Anatomic Staging System (GLASS) assignment stage and comparison with intraoperative arteriography

Obtaining a prognostic and predictive classification based on the risk of amputation is crucial in ischemic pathology of the lower limbs. Accurate anatomical characterization of arterial lesions is essential for optimal clinical decision-making. The Global Limb Anatomic Staging System (GLASS) provides a comprehensive anatomy assessment of the femoropopliteal and infrapopliteal arterial system. GLASS introduces concepts such as the target arterial path (TAP) and estimated limb-based patency (LBP), crucial for determining the best arterial route to restore blood flow. A prospective study conducted from May to December 2022 involved 66 patients undergoing revascularization surgery for Critical Limb-Threatening Ischemia (CLTI). Preoperative arterial mapping (PAM) using duplex ultrasonography was the sole imaging modality. The TAP was defined in each patient, and GLASS staging was determined. Intraoperative arteriography (IA) was used on the day of surgery for comparison. Agreement between PAM and IA was assessed using Cohen's kappa coefficient, and diagnostic metrics were compared using ROC curves. Doppler ultrasound demonstrated a sensitivity of 98%, specificity and PPV of 100%, and NPV of 94.7% in the femoropopliteal sector, with a Kappa coefficient of 0.98. For the infrapopliteal sector, sensitivity was 95%, specificity 96.5%, PPV 97.3%, and NPV 93.3%, with a Kappa coefficient of 0.89. Combining both sectors, the overall GLASS stage showed a 93.9% concordance with a Kappa coefficient of 0.91. ROC curves revealed no significant differences between ultrasound and arteriography in terms of staging. This study demonstrates that Doppler Ultrasound can serve as the exclusive imaging modality for determining the preoperative GLASS stage.

The prevalence of non-sentinel lymph node metastasis among breast cancer patients with sentinel lymph node involvement and its impact on clinical decision-making: a single-centred retrospective study.

Sentinel lymph node biopsy (SLNB) has become standard procedure for early breast cancer patients with clinically node negative disease. The patients with SLN metastasis normally underwent axillary lymph node dissection (ALND). However, the metastatic status of non-sentinel Lymph nodes (non-SLNs) varied significantly in different reports. Here, we evaluated the prevalence of non-SLNs metastasis among breast cancer patients with sentinel lymph node metastasis and its impact on clinical decision-making. We identified 892 female patients with operable cT1-3N0 invasive breast cancer who underwent ALND in our center due to SLN metastasis from 2017 to 2023, retrospectively. The prevalence of non-SLN metastasis among different clinicopathological traits and its correlation with the number of positive SLNs were analyzed. The optimal clinical decision-making was generalized. The median number of SLN+, SLN, non-SLN+ and non-SLN was 2, 4, 1 and 14 among the enrolled 892 female patients, respectively. 504 (56.50%) patients with SLN + had at least one metastatic lymph node in the harvested non-SLNs. Among the enrolled 892 female patients, 435 (48.77%) patients with 1 positive SLN, of which 180 (41.38%) had at least one additional metastatic non-SLNs. 242 (27.13%) patients with 2 positive SLNs, of which 146 (60.33%) had at least one metastatic non-SLNs. For the rest 215 (24.10%) patients with at least 3 metastatic SLNs, 178 (82.79%) had at least one metastatic non-SLNs. In the univariate analysis, the non-SLNs metastatic status was correlated with the number of SLNs+, tumor size, tumor grade, lymphovascular invasion (LVI) and molecular subtypes, but not histopathologic type. In the multivariate analysis, the risk of additional non-SLNs metastasis correlated with the number of SLNs+, SLNs, non-SLNs and LVI. Omiting ALND in patients with higher non-SLNs + rate outside the American College of Surgeons Oncology Group (ACSOG) Z0011 and the European Organization for Research and Treatment of Cancer (EORTC) 10,981-22023 AMAROS criteria should be considered with caution in clinical decision-making. To evaluate whether axillary radiotherapy and ALND provides equivalent regional control in breast cancer patients with obvious residual metastatic lymph nodes undesected in the axilla, a well-matched prospective randomized controlled trial is an urgent need.

Cross-modal similar clinical case retrieval using a modular model based on contrastive learning and k-nearest neighbor search

ObjectiveElectronic health record systems have made it possible for clinicians to use previously encountered similar cases to support clinical decision-making. However, most studies for similar case retrieval were based on single-modal data. The existing studies on cross-modal clinical case retrieval were limited. We aimed to develop a CRoss-Modal Retrieval (CRMR) model to retrieve similar clinical cases recorded in different data modalities. Materials and methodsThe publically available Medical Information Mart for Intensive Care-Chest X-ray (MIMIC-CXR) dataset was used for model development and testing. The CRMR model was designed as a modular model containing two feature extraction models, two feature transformation models, one feature transformation optimization model, and one case retrieval model. The ability to retrieve similar clinical cases recorded in different data modalities was facilitated by the use of contrastive deep learning and k-nearest neighbor search. ResultsThe average retrieval precision, denoted as AP@k, of the developed CRMR model, were 76.9 %@5, 76.7 %@10, 76.5 %@20, 76.3 %@50, and 77.9 %@100, respectively. Here k is the number of similar cases returned after retrieval. The average retrieval time varied from 0.013 ms to 0.016 ms with k varying from 5 to 100. Moreover, the model can retrieve similar cases with the same multiple radiographic manifestations as the query case. DiscussionThe CRMR model has shown promising cross-modal retrieval performance in clinical case analysis, with the potential for future scalability and improvement in handling diverse disease types and data modalities. The CRMR model has promising potential to aid clinicians in making optimal and explainable clinical decisions.

Immune-related adverse events in a nationwide cohort of real-world melanoma patients treated with adjuvant anti-PD1 – Seasonal variation and association with outcome

IntroductionImmune checkpoint inhibitors (ICIs) carry the risk of immune-related adverse events (irAEs), a significant concern as therapy has transitioned to the adjuvant setting. Balancing therapeutic benefits against potential risks is crucial, necessitating real-world data from an unselected patient population in addition to clinical trial data to ensure optimal clinical decision-making. MethodsThis nationwide real-world study assessed irAEs in patients receiving adjuvant anti-PD1 therapy, primarily nivolumab, for resected stage III-IV melanoma between 2018–2022. Data were retrieved from two national databases: the IMMUNOTOX database and the Danish Metastatic Melanoma Database (DAMMED). IrAEs were sub-grouped according to organ systems graded using CTCAE ver. 5.0 ranging from mild toxicities (grade 1–2) to severe (grade 3–4) and fatal (grade 5). ResultsAmong 792 included patients, (55 % male, median age 62 years (range 16–88)), 697 patients (88 %) experienced an irAE. Severe irAEs occurred in 116 patients (15 %) and five (0.6 %) died due to toxicity. A landmark analysis showed that patients who experienced at least one irAE before the 1st evaluation at 90 days had an increased progression free survival (PFS) (p = 0.032) and overall survival (OS) (p = 0.0071). Additionally, a seasonal pattern was noted with higher incidence of irAEs during summer. ConclusionThe prevalence of irAEs in real-world patients is comparable to the observed risk in clinical trials. Patients experiencing irAEs demonstrate a lower risk of melanoma relapse. Further, gender, age and seasonal variation may impact the incidence of irAEs.

Advances of Treatment of Pulmonary Large Cell Neuroendocrine Carcinoma

Large cell neuroendocrine carcinoma (LCNEC) of lung is a rare neuroendocrine carcinoma subtype with difficulty in early diagnosis and poor prognosis which is treated with standard strategies of small cell lung cancer and non-small cell lung cancer. In recent years, the precise types of LCNEC and its response to therapy have been identified by next-generation sequencing. Some researches have also found the correlation between different subtypes of LCNEC and the efficacy of chemotherapy regimens. However, there is no consensual agreement of its therapy. Recently, immune checkpoint inhibitors (ICIs) has provided a new option for LCNEC patients based on some retrospective research data and case reports. In this review, we aimed to summarize the epidemiological characteristics, standard therapy, the advances of molecular subtypes and clinical applications of ICIs of LCNEC, so as to provide optimal systemic clinical decision-making for LCNEC patients. .

Development and validation of novel interpretable survival prediction models based on drug exposures for severe heart failure during vulnerable period

BackgroundSevere heart failure (HF) has a higher mortality during vulnerable period while targeted predictive tools, especially based on drug exposures, to accurately assess its prognoses remain largely unexplored. Therefore, this study aimed to utilize drug information as the main predictor to develop and validate survival models for severe HF patients during this period.MethodsWe extracted severe HF patients from the MIMIC-IV database (as training and internal validation cohorts) as well as from the MIMIC-III database and local hospital (as external validation cohorts). Three algorithms, including Cox proportional hazards model (CoxPH), random survival forest (RSF), and deep learning survival prediction (DeepSurv), were applied to incorporate the parameters (partial hospitalization information and exposure durations of drugs) for constructing survival prediction models. The model performance was assessed mainly using area under the receiver operator characteristic curve (AUC), brier score (BS), and decision curve analysis (DCA). The model interpretability was determined by the permutation importance and Shapley additive explanations values.ResultsA total of 11,590 patients were included in this study. Among the 3 models, the CoxPH model ultimately included 10 variables, while RSF and DeepSurv models incorporated 24 variables, respectively. All of the 3 models achieved respectable performance metrics while the DeepSurv model exhibited the highest AUC values and relatively lower BS among these models. The DCA also verified that the DeepSurv model had the best clinical practicality.ConclusionsThe survival prediction tools established in this study can be applied to severe HF patients during vulnerable period by mainly inputting drug treatment duration, thus contributing to optimal clinical decisions prospectively.

Cost‑effectiveness analysis of tislelizumab plus chemotherapy in Chinese patients with advanced or metastatic oesophageal squamous cell carcinoma

The RATIONALE-306 study revealed that patients with advanced or metastatic oesophageal squamous cell carcinoma (OSCC) could benefit from treatment with tislelizumab plus chemotherapy. This study aimed to evaluate the cost-effectiveness of tislelizumab plus chemotherapy for treating OSCC from the perspective of the Chinese healthcare system. Partitioned survival model estimated the cost-effectiveness of tislelizumab plus chemotherapy compared with chemotherapy alone for treating OSCC using RATIONALE-306 data. Costs and utilities were obtained from local databases and published studies. Costs, quality-adjusted life-years (QALYs), life-years, incremental cost-effectiveness ratios (ICER), incremental net health benefits (INHB), and incremental net monetary benefits (INMB) were outcomes. Price simulation were conducted at the willingness-to-pay (WTP) threshold. Sensitivity and subgroup analyses were performed to assess model robustness. Compared with chemotherapy alone, tislelizumab plus chemotherapy yielded an ICER of USD 27,896/QALY, gained an additional 0.414 QALYs and 0.751 life-years, and increased the cost by USD 11,560. Probabilistic sensitivity analysis revealed that tislelizumab plus chemotherapy was cost-effective at the WTP of USD 38,258/QALY with probability of 94.43%. When the price in China was less than USD 3.714 per mg, the price simulation results indicated that tislelizumab plus chemotherapy was cost-effective at a WTP threshold of USD 38,258. Tislelizumab plus chemotherapy yielded an INHB of 0.112 QALYs and an INMB of USD 4,279 compared with chemotherapy alone at a WTP threshold of USD 38,258. Based on the sensitivity analyses, the above results were stable. A general trend was observed for subgroups with better survival benefits related to a higher probability of cost-effectiveness. From the Chinese healthcare perspective, tislelizumab plus chemotherapy is more cost-effective than chemotherapy alone as a first-line therapy for OSCC. These findings can help clinicians make optimal clinical decisions and assist decision-makers in evaluating the cost-effectiveness of tislelizumab in clinical practice.

Mitotic catastrophe heterogeneity: implications for prognosis and immunotherapy in hepatocellular carcinoma.

The mitotic catastrophe (MC) pathway plays an important role in hepatocellular carcinoma (HCC) progression and tumor microenvironment (TME) regulation. However, the mechanisms linking MC heterogeneity to immune evasion and treatment response remain unclear. Based on 94 previously published highly correlated genes for MC, HCC patients' data from the Cancer Genome Atlas (TCGA) and changes in immune signatures and prognostic stratification were studied. Time and spatial-specific differences for MCGs were assessed by single-cell RNA sequencing and spatial transcriptome (ST) analysis. Multiple external databases (GEO, ICGC) were employed to construct an MC-related riskscore model. Identification of two MC-related subtypes in HCC patients from TCGA, with clear differences in immune signatures and prognostic risk stratification. Spatial mapping further associates low MC tumor regions with significant immune escape-related signaling. Nomogram combining MC riskscore and traditional indicators was validated great effect for early prediction of HCC patient outcomes. MC heterogeneity enables immune escape and therapy resistance in HCC. The MC gene signature serves as a reliable prognostic indicator for liver cancer. By revealing clear immune and spatial heterogeneity of HCC, our integrated approach provides contextual therapeutic strategies for optimal clinical decision-making.

Compare deep learning model and conventional logistic regression model for the identification of unstable saccular intracranial aneurysms in computed tomography angiography.

It is crucial to distinguish unstable from stable intracranial aneurysms (IAs) as early as possible to derive optimal clinical decision-making for further treatment or follow-up. The aim of this study was to investigate the value of a deep learning model (DLM) in identifying unstable IAs from computed tomography angiography (CTA) images and to compare its discriminatory ability with that of a conventional logistic regression model (LRM). From August 2011 to May 2021, a total of 1,049 patients with 681 unstable IAs and 556 stable IAs were retrospectively analyzed. IAs were randomly divided into training (64%), internal validation (16%), and test sets (20%). Convolutional neural network (CNN) analysis and conventional logistic regression (LR) were used to predict which IAs were unstable. The area under the curve (AUC), sensitivity, specificity and accuracy were calculated to evaluate the discriminating ability of the models. One hundred and ninety-seven patients with 229 IAs from Banan Hospital were used for external validation sets. The conventional LRM showed 11 unstable risk factors, including clinical and IA characteristics. The LRM had an AUC of 0.963 [95% confidence interval (CI): 0.941-0.986], a sensitivity, specificity and accuracy on the external validation set of 0.922, 0.906, and 0.913, respectively, in predicting unstable IAs. In predicting unstable IAs, the DLM had an AUC of 0.771 (95% CI: 0.582-0.960), a sensitivity, specificity and accuracy on the external validation set of 0.694, 0.929, and 0.782, respectively. The CNN-based DLM applied to CTA images did not outperform the conventional LRM in predicting unstable IAs. The patient clinical and IA morphological parameters remain critical factors for ensuring IA stability. Further studies are needed to enhance the diagnostic accuracy.

Prognostic nomogram in patients with right-sided colon cancer after colectomy: a surveillance, epidemiology, and end results-based study.

This study aimed to develop and validate a nomogram for predicting overall survival (OS) in patients undergoing surgery for right-sided colon cancer (RCC). We collected 25,203 patients with RCC from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided them into 7:3 training and internal validation set. Utilizing the Cox proportional hazards regression model, we constructed a nomogram based on prognostic risk factors. Furthermore, for external validation, we retrospectively followed up with 228 patients from Jiaxing First Hospital and assessed and calibrated the nomogram using the C-index and calibration curves. After identifying independent prognostic factors through univariate and multivariate analyses, a nomogram was developed. The c-index values of this nomogram differed as follows: 0.851 (95% CI: 0.845-0.857) in the training set, 0.860 (95% CI: 0.850-0.870) in the internal validation set, and 0.834 (95% CI: 0.780-0.888) in the external validation set, indicating the model's strong discriminative ability. Calibration curves for 1-year, 3-year, and 5-year overall survival (OS) probabilities exhibited a high level of consistency between predicted and actual survival rates. Furthermore, Decision Curve Analysis (DCA) demonstrated that the new model consistently outperformed the TNM staging system in terms of net benefit. We developed and validated a survival prediction model for patients with RCC. This novel nomogram outperforms the traditional TNM staging system and can guide clinical practitioners in making optimal clinical decisions.

Consciously Choosing Unconsciousness

Consciously Choosing Unconsciousness

Toward Informed Selection and Interpretation of Clinical Genomic Tests in Prostate Cancer.

Clinical genomic testing of patient germline, tumor tissue, or plasma cell-free DNA can enable a personalized approach to cancer management and treatment. In prostate cancer (PCa), broad genotyping tests are now widely used to identify germline and/or somatic alterations in BRCA2 and other DNA damage repair genes. Alterations in these genes can confer cancer sensitivity to poly (ADP-ribose) polymerase inhibitors, are linked with poor prognosis, and can have potential hereditary cancer implications for family members. However, there is huge variability in genomic tests and reporting standards, meaning that for successful implementation of testing in clinical practice, end users must carefully select the most appropriate test for a given patient and critically interpret the results. In this white paper, we outline key pre- and post-test considerations for choosing a genomic test and evaluating reported variants, specifically for patients with advanced PCa. Test choice must be based on clinical context and disease state, availability and suitability of tumor tissue, and the genes and regions that are covered by the test. We describe strategies to recognize false positives or negatives in test results, including frameworks to assess low tumor fraction, subclonal alterations, clonal hematopoiesis, and pathogenic versus nonpathogenic variants. We assume that improved understanding among health care professionals and researchers of the nuances associated with genomic testing will ultimately lead to optimal patient care and clinical decision making.

Synovial Fluid C-reactive Protein Clinical Decision Limit and Diagnostic Accuracy for Periprosthetic Joint Infection.

Introduction C-reactive protein (CRP) has long served as a prototypical biomarker for periprosthetic joint infection (PJI). Recently, synovial fluid (SF)-CRP has garnered interest as a diagnostic tool, with several studies demonstrating its diagnostic superiority over serum CRP for the diagnosis of PJI. Although previous studies have identified diagnostic thresholds for SF-CRP, they have been limited in scope and employed various CRP assays without formal validation for PJI diagnosis. This study aimed to conduct a formal single clinical laboratory validation to determine the optimal clinical decision limit of SF-CRP for the diagnosis of PJI. Methods A retrospective analysis of prospectively collected data was performed using receiver operating characteristic (ROC) and area under the curve (AUC) analyses. Synovial fluid samples from hip and knee arthroplasties, received from over 2,600 institutions,underwent clinical testing for PJI at a single clinical laboratory (CD Laboratories, Zimmer Biomet, Towson, MD) between 2017 and 2022. Samples were assayed for SF-CRP, alpha-defensin, white blood cell count, neutrophil percentage, and microbiological culture. After applying selection criteria, the samples were classified with the 2018 ICM PJI scoring system as "infected," "not infected," or "inconclusive." Data were divided into training and validation sets. The Youden Index was employed to optimize the clinical decision limit. Results A total of 96,061 samples formed the training (n = 67,242) and validation (n = 28,819) datasets. Analysis of the biomarker median values, culture positivity, anatomic distribution, and days from aspiration to testing revealed nearly identical specimen characteristics in both the training set and validation set. SF-CRP demonstrated an AUC of 0.929 (95% confidence interval (CI): 0.926-0.932) in the training set, with an optimal SF-CRP clinical decision limit for PJI diagnosis of 4.45 mg/L. Applying this cutoff to the validation dataset yielded a sensitivity of 86.1% (95% CI: 85.0-87.1%) and specificity of 87.1% (95% CI: 86.7-87.5%). No statistically significant difference in diagnostic performance was observed between the validation and training sets. Conclusion This study represents the largest single clinical laboratory evaluation of an SF-CRP assay for PJI diagnosis. The optimal CRP cutoff (4.45 mg/L) for PJI, which yielded a sensitivity of 86.1% and a specificity of 87.1%, is specific to the assay methodology and laboratory performing the assay. We propose that an SF-CRP test with a laboratory-validated optimal clinical decision limit for PJI may be preferable, in a clinical diagnostic setting, to serum CRP tests that do not have laboratory-validated clinical decision limits for PJI.

Deep learning-based prediction of in-hospital mortality for sepsis

As a serious blood infection disease, sepsis is characterized by a high mortality risk and many complications. Accurate assessment of mortality risk of patients with sepsis can help physicians in Intensive Care Unit make optimal clinical decisions, which in turn can effectively save patients’ lives. However, most of the current clinical models used for assessing mortality risk in sepsis patients are based on conventional indicators. Unfortunately, some of the conventional indicators have been shown to be inapplicable in the accurate clinical diagnosis nowadays. Meanwhile, traditional evaluation models only focus on a small amount of personal data, causing misdiagnosis of sepsis patients. We refine the core indicators for mortality risk assessment of sepsis from massive clinical electronic medical records with machine learning, and propose a new mortality risk assessment model, DGFSD, for sepsis patients based on deep learning. The DGFSD model can not only learn individual clinical information about unassessed patients, but also obtain information about the structure of the similarity graph between diagnosed patients and patients to be assessed. Numerous experiments have shown that the accuracy of the DGFSD model is superior to baseline methods, and can significantly improve the efficiency of clinical auxiliary diagnosis.

Patients with Obesity Should be Recognised as a Special Patient Population During Drug Development of Antibacterial and Antifungal Agents; A Call to Action.

Individuals with obesity are at increased risk of developing infectious diseases. Timely administration of an effective dose of an antimicrobial agent is paramount to safeguard optimal therapy. For this purpose, special patient populations at risk for altered exposure such as renal or hepatic impairment are studied during drug development. Strikingly, there is no such evaluation in individuals with obesity despite a potential influence on exposure and a global obesity prevalence of 13 %. Optimal clinical decision making in patients with obesity is impossible without prior study of the drug of interest in this population. This statement is strengthened by an evaluation of 19 antimicrobial agents that showed tremendous variability in the influence of weight on clearance. In contrast to patient with renal or hepatic impairment who are mainly at risk of overexposure, individuals with obesity can be at risk of both under- and overexposure. Gaining knowledge on the influence of body weight on clearance during early phases of drug development may allow for optimisation of other phases of research, potentially increasing success rate of the drug, and can provide clinicians with vital information as soon as the drug reaches the market. Antimicrobial therapy should be tailored to obesity-related (patho)physiological changes and to reach this goal, obese individuals should be studied during drug development.

The treatment and outcome prediction analysis of pediatric acquired severe aplastic anemia.

Pediatric acquired severe aplastic anemia (SAA), a prevalent non-malignant hematological disorder, presents significant therapeutic challenges and carries considerable risks. Despite substantial progress in immunosuppressive therapy (IST) and allogeneic hematopoietic stem cell transplantation (allo-HSCT) in recent years, the protracted treatment duration, substantial costs, and significant disparities in long-term survival outcomes among patients remain problematic. Identifying predictors of treatment response before therapy initiation is crucial for optimal clinical decision-making and complication prevention. Recent studies has pinpointed predictive factors for IST and haploidentical hematopoietic stem cell transplantation (haplo-HSCT) efficacy in SAA, fostering the development and utilization of transplantation-based scoring systems for prognosis evaluation. This review summarizes advancements in treating pediatric SAA and discusses key elements that influence the outcomes of IST and haplo-HSCT, aiming to support clinical decision-making in diverse clinical scenarios.

Diagnosing adjustment disorder in patients with cancer: evaluation of the adherence, interrater agreement, and content of a guideline-based interview

Abstract Background: The aim of this study was to evaluate the adherence, interrater agreement, and content of a guideline-based semistructured interview for adjustment disorder (AD) in patients with cancer. Methods: In total, 120 AD interviews with patients with cancer were performed by 9 trained psychologists. The interview contained topics related to stressors, resilience, and symptoms and complaints. Audiotaped interviews of 72 patients were available. Adherence to the interview manual was scored by two researchers independently, and the average adherence was calculated per topic. Interrater agreement was calculated using Cohen's Kappa. The content of the interviews was evaluated using thematic analysis of the transcribed interviews of patients with an AD diagnosis. Results: In the interviews, 97% of the topics were covered at least briefly and 78% of all topics were addressed at least adequately. Interviewers asked questions regarding stressors and symptoms and complaints more thoroughly compared with resilience. The interrater agreement regarding the AD diagnosis was moderate (Kappa 0.55). The content analysis showed that stressors and resilience can be additionally specified into physical, psychological, spiritual, and social themes, which are relevant to explore in the context of an AD diagnosis after cancer. Conclusion: The guideline-based interview for AD identifies problems and protective factors with adequate adherence and moderate agreement. A balanced investigation of stressors, resilience, and symptoms is important for optimal clinical decision-making regarding AD in the context of cancer.

Recommendations for the treatment and management of adult B-Cell acute lymphoblastic leukemia in Asia-Pacific: Outcomes from a pilot initiative.

The outcomes of adult B-cell acute lymphoblastic leukemia (ALL) remain poor. Recent advancements in the field of leukemia research show potential for improved patient care. However, the adoption of research findings into clinical practice is fraught with practice- and country-specific challenges. The continued addition of new findings warrants critical evaluation for the feasibility of incorporation into clinical practice. A uniform set of evidence-based guidelines can favorably assist physicians in making optimal clinical decisions. Such a resource may also serve as a reference point for strategic planning of initiatives aimed at addressing critical barriers in the optimal management of B-cell ALL. This initiative was undertaken to seek a collaborative perspective and understand the existing challenges. Concordance-based recommendations were outlined through a systematic discussion on various aspects of treatment and management of adult B-cell ALL. The outcomes and experiences gained from this exercise will serve as a foundation for future efforts encompassing the more granular aspects of the management of B-cell ALL across the Asia-Pacific region.