Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Radiology Radiology

Can automated CT body composition analysis predict high-grade Clavien-Dindo complications in patients with RCC undergoing partial and radical nephrectomy?

In Scottish medical journal

INTRODUCTION : This study investigated the relationship between body tissue composition analysis and complications according to the Clavien-Dindo classification in patients with renal cell carcinoma (RCC) who underwent partial (PN) or radical nephrectomies (RN).

METHODS : We obtained all data of 210 patients with RCC from the 2019 Kidney and Kidney Tumor Segmentation Challenge (C4KC-KiTS) dataset and obtained radiological images from the cancer image archive. Body composition was assessed with automated artificial intelligence software using the convolutional network segmentation technique from abdominal computed tomography images. We included 125 PN and 63 RN in the study. The relationship between body fat and muscle tissue distribution and complications according to the Clavien-Dindo classification was evaluated between these two groups.

RESULTS : Clavien-Dindo 3A and higher (high grade) complications were developed in 9 of 125 patients who underwent PN and 7 of 63 patients who underwent RN. There was no significant difference between all body composition values between patients with and without high-grade complications.

CONCLUSION : This study showed that body muscle-fat tissue distribution did not affect patients with 3A and above complications according to the Clavien-Dindo classification in patients who underwent nephrectomy due to RCC.

Demirel Emin, Dilek Okan

2023-Mar-22

Clavien–Dindo classification, Nephrectomy, adipose, muscle, renal cell cancer, surgical complication

General General

[Construction and evaluation of an artificial intelligence-based risk prediction model for death in patients with nasopharyngeal cancer].

In Nan fang yi ke da xue xue bao = Journal of Southern Medical University

OBJECTIVE : To screen the risk factors for death in patients with nasopharyngeal carcinoma (NPC) using artificial intelligence (AI) technology and establish a risk prediction model.

METHODS : The clinical data of NPC patients obtained from SEER database (1973-2015). The patients were randomly divided into model building and verification group at a 7∶3 ratio. Based on the data in the model building group, R software was used to identify the risk factors for death in NPC patients using 4 AI algorithms, namely eXtreme Gradient Boosting (XGBoost), Decision Tree (DT), Least absolute shrinkage and selection operator (LASSO) and random forest (RF), and a risk prediction model was constructed based on the risk factor identified. The C-Index, decision curve analysis (DCA), receiver operating characteristic (ROC) curve and calibration curve (CC) were used for internal validation of the model; the data in the validation group and clinical data of 96 NPC patients (collected from First Affiliated Hospital of Bengbu Medical College) were used for internal and external validation of the model.

RESULTS : The clinical data of a total of 2116 NPC patients were included (1484 in model building group and 632 in verification group). Risk factor screening showed that age, race, gender, stage M, stage T, and stage N were all risk factors of death in NPC patients. The risk prediction model for NPC-related death constructed based on these factors had a C-index of 0.76 for internal evaluation, an AUC of 0.74 and a net benefit rate of DCA of 9%-93%. The C-index of the model in internal verification was 0.740 with an AUC of 0.749 and a net benefit rate of DCA of 3%-89%, suggesting a high consistency of the two calibration curves. In external verification, the C-index of this model was 0.943 with a net benefit rate of DCA of 3%-97% and an AUC of 0.851, and the predicted value was consistent with the actual value.

CONCLUSIONS : Gender, age, race and TNM stage are risk factors of death of NPC patients, and the risk prediction model based on these factors can accurately predict the risks of death in NPC patients.

Zhang H, Lu J, Jiang C, Fang M

2023-Feb-20

artificial intelligence, nasopharyngeal carcinoma, nomogram, predictive model, risk factors

General General

Accelerating network layouts using graph neural networks.

In Nature communications ; h5-index 260.0

Graph layout algorithms used in network visualization represent the first and the most widely used tool to unveil the inner structure and the behavior of complex networks. Current network visualization software relies on the force-directed layout (FDL) algorithm, whose high computational complexity makes the visualization of large real networks computationally prohibitive and traps large graphs into high energy configurations, resulting in hard-to-interpret "hairball" layouts. Here we use Graph Neural Networks (GNN) to accelerate FDL, showing that deep learning can address both limitations of FDL: it offers a 10 to 100 fold improvement in speed while also yielding layouts which are more informative. We analytically derive the speedup offered by GNN, relating it to the number of outliers in the eigenspectrum of the adjacency matrix, predicting that GNNs are particularly effective for networks with communities and local regularities. Finally, we use GNN to generate a three-dimensional layout of the Internet, and introduce additional measures to assess the layout quality and its interpretability, exploring the algorithm's ability to separate communities and the link-length distribution. The novel use of deep neural networks can help accelerate other network-based optimization problems as well, with applications from reaction-diffusion systems to epidemics.

Both Csaba, Dehmamy Nima, Yu Rose, Barabási Albert-László

2023-Mar-21

General General

Risk Factors and Predictive Modeling for Post-Acute Sequelae of SARS-CoV-2 Infection: Findings from EHR Cohorts of the RECOVER Initiative.

In Research square

Background Patients who were SARS-CoV-2 infected could suffer from newly incidental conditions in their post-acute infection period. These conditions, denoted as the post-acute sequelae of SARS-CoV-2 infection (PASC), are highly heterogeneous and involve a diverse set of organ systems. Limited studies have investigated the predictability of these conditions and their associated risk factors. Method In this retrospective cohort study, we investigated two large-scale PCORnet clinical research networks, INSIGHT and OneFlorida+, including 11 million patients in the New York City area and 16.8 million patients from Florida, to develop machine learning prediction models for those who are at risk for newly incident PASC and to identify factors associated with newly incident PASC conditions. Adult patients aged 20 with SARS-CoV-2 infection and without recorded infection between March 1 st , 2020, and November 30 th , 2021, were used for identifying associated factors with incident PASC after removing background associations. The predictive models were developed on infected adults. Results We find several incident PASC, e.g., malnutrition, COPD, dementia, and acute kidney failure, were associated with severe acute SARS-CoV-2 infection, defined by hospitalization and ICU stay. Older age and extremes of weight were also associated with these incident conditions. These conditions were better predicted (C-index >0.8). Moderately predictable conditions included diabetes and thromboembolic disease (C-index 0.7-0.8). These were associated with a wider variety of baseline conditions. Less predictable conditions included fatigue, anxiety, sleep disorders, and depression (C-index around 0.6). Conclusions This observational study suggests that a set of likely risk factors for different PASC conditions were identifiable from EHRs, predictability of different PASC conditions was heterogeneous, and using machine learning-based predictive models might help in identifying patients who were at risk of developing incident PASC.

Zang Chengxi, Hou Yu, Schenck Edward, Xu Zhenxing, Zhang Yongkang, Xu Jie, Bian Jiang, Morozyuk Dmitry, Khullar Dhruv, Nordvig Anna, Shenkman Elizabeth, Rothman Russel, Block Jason, Lyman Kristin, Zhang Yiye, Varma Jay, Weiner Mark, Carton Thomas, Wang Fei, Kaushal Rainu, Consortium The Recover

2023-Mar-08

General General

SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes Summarization

ArXiv Preprint

Electronic health records (EHRs) store an extensive array of patient information, encompassing medical histories, diagnoses, treatments, and test outcomes. These records are crucial for enabling healthcare providers to make well-informed decisions regarding patient care. Summarizing clinical notes further assists healthcare professionals in pinpointing potential health risks and making better-informed decisions. This process contributes to reducing errors and enhancing patient outcomes by ensuring providers have access to the most pertinent and current patient data. Recent research has shown that incorporating prompts with large language models (LLMs) substantially boosts the efficacy of summarization tasks. However, we show that this approach also leads to increased output variance, resulting in notably divergent outputs even when prompts share similar meanings. To tackle this challenge, we introduce a model-agnostic Soft Prompt-Based Calibration (SPeC) pipeline that employs soft prompts to diminish variance while preserving the advantages of prompt-based summarization. Experimental findings on multiple clinical note tasks and LLMs indicate that our method not only bolsters performance but also effectively curbs variance for various LLMs, providing a more uniform and dependable solution for summarizing vital medical information.

Yu-Neng Chuang, Ruixiang Tang, Xiaoqian Jiang, Xia Hu

2023-03-23

General General

Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma.

In Clinical and molecular hepatology

BACKGROUND & AIMS : Patients with cirrhosis and hepatocellular carcinoma (HCC) require extensive and personalized care to improve outcomes. ChatGPT (Generative Pre-trained Transformer), a large language model, holds the potential to provide professional yet patient-friendly support. We aimed to examine the accuracy and reproducibility of ChatGPT in answering questions regarding knowledge, management, and emotional support for cirrhosis and HCC.

METHODS : ChatGPT's responses to 164 questions were independently graded by two transplant hepatologists and resolved by a third reviewer. The performance of ChatGPT was also assessed using two published questionnaires and 26 questions formulated from the quality measures of cirrhosis management. Finally, its emotional support capacity was tested.

RESULTS : We showed that ChatGPT regurgitated extensive knowledge of cirrhosis (79.1% correct) and HCC (74.0% correct), but only small proportions (47.3% in cirrhosis, 41.1% in HCC) were labeled as comprehensive. The performance was better in basic knowledge, lifestyle, and treatment than in the domains of diagnosis and preventive medicine. For the quality measures, the model answered 76.9% of questions correctly but failed to specify decision-making cut-offs and treatment durations. ChatGPT lacked knowledge of regional guidelines variations, such as HCC screening criteria. However, it provided practical and multifaceted advice to patients and caregivers regarding the next steps and adjusting to a new diagnosis.

CONCLUSIONS : We analyzed the areas of robustness and limitations of ChatGPT's responses on the management of cirrhosis and HCC and relevant emotional support. ChatGPT may have a role as an adjunct informational tool for patients and physicians to improve outcomes.

Yeo Yee Hui, Samaan Jamil S, Ng Wee Han, Ting Peng-Sheng, Trivedi Hirsh, Vipani Aarshi, Ayoub Walid, Yang Ju Dong, Liran Omer, Spiegel Brennan, Kuo Alexander

2023-Mar-22

accuracy, artificial intelligence, health literacy, patient knowledge, reproducibility