-
Nature Communications Jun 2024Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients...
Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine learning-based algorithm to predict short-term survival in patients being initiated on CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieves an area under the receiver operating curve of 0.848 (CI = 0.822-0.870). Feature importance, error, and subgroup analyses provide insight into bias and relevant features for model prediction. Overall, we demonstrate the potential for predictive machine learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.
Topics: Humans; Continuous Renal Replacement Therapy; Machine Learning; Male; Female; Algorithms; Middle Aged; Electronic Health Records; Aged; ROC Curve; Renal Replacement Therapy
PubMed: 38937447
DOI: 10.1038/s41467-024-49763-3 -
JMIR Bioinformatics and Biotechnology May 2024The etiology of ischemic stroke is multifactorial. Several gene mutations have been identified as leading causes of cerebral autosomal dominant arteriopathy with...
BACKGROUND
The etiology of ischemic stroke is multifactorial. Several gene mutations have been identified as leading causes of cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL), a hereditary disease that causes stroke and other neurological symptoms.
OBJECTIVE
We aimed to identify the variants of NOTCH3 and thrombophilia genes, and their complex interactions with other factors.
METHODS
We conducted a hierarchical cluster analysis (HCA) on the data of 100 patients diagnosed with ischemic stroke. The variants of NOTCH3 and thrombophilia genes were identified by polymerase chain reaction with confronting 2-pair primers and real-time polymerase chain reaction. The overall preclinical characteristics, cumulative cutpoint values, and factors associated with these somatic mutations were analyzed in unidimensional and multidimensional scaling models.
RESULTS
We identified the following optimal cutpoints: creatinine, 83.67 (SD 9.19) µmol/L; age, 54 (SD 5) years; prothrombin (PT) time, 13.25 (SD 0.17) seconds; and international normalized ratio (INR), 1.02 (SD 0.03). Using the Nagelkerke method, cutpoint 50% values of the Glasgow Coma Scale score; modified Rankin scale score; and National Institutes of Health Stroke Scale scores at admission, after 24 hours, and at discharge were 12.77, 2.86 (SD 1.21), 9.83 (SD 2.85), 7.29 (SD 2.04), and 6.85 (SD 2.90), respectively.
CONCLUSIONS
The variants of MTHFR (C677T and A1298C) and NOTCH3 p.R544C may influence the stroke severity under specific conditions of PT, creatinine, INR, and BMI, with risk ratios of 4.8 (95% CI 1.53-15.04) and 3.13 (95% CI 1.60-6.11), respectively (P<.05). It is interesting that although there are many genes linked to increased atrial fibrillation risk, not all of them are associated with ischemic stroke risk. With the detection of stroke risk loci, more information can be gained on their impacts and interconnections, especially in young patients.
PubMed: 38935968
DOI: 10.2196/56884 -
JMIR Bioinformatics and Biotechnology Feb 2024Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by...
BACKGROUND
Current postpartum hemorrhage (PPH) risk stratification is based on traditional statistical models or expert opinion. Machine learning could optimize PPH prediction by allowing for more complex modeling.
OBJECTIVE
We sought to improve PPH prediction and compare machine learning and traditional statistical methods.
METHODS
We developed models using the Consortium for Safe Labor data set (2002-2008) from 12 US hospitals. The primary outcome was a transfusion of blood products or PPH (estimated blood loss of ≥1000 mL). The secondary outcome was a transfusion of any blood product. Fifty antepartum and intrapartum characteristics and hospital characteristics were included. Logistic regression, support vector machines, multilayer perceptron, random forest, and gradient boosting (GB) were used to generate prediction models. The area under the receiver operating characteristic curve (ROC-AUC) and area under the precision/recall curve (PR-AUC) were used to compare performance.
RESULTS
Among 228,438 births, 5760 (3.1%) women had a postpartum hemorrhage, 5170 (2.8%) had a transfusion, and 10,344 (5.6%) met the criteria for the transfusion-PPH composite. Models predicting the transfusion-PPH composite using antepartum and intrapartum features had the best positive predictive values, with the GB machine learning model performing best overall (ROC-AUC=0.833, 95% CI 0.828-0.838; PR-AUC=0.210, 95% CI 0.201-0.220). The most predictive features in the GB model predicting the transfusion-PPH composite were the mode of delivery, oxytocin incremental dose for labor (mU/minute), intrapartum tocolytic use, presence of anesthesia nurse, and hospital type.
CONCLUSIONS
Machine learning offers higher discriminability than logistic regression in predicting PPH. The Consortium for Safe Labor data set may not be optimal for analyzing risk due to strong subgroup effects, which decreases accuracy and limits generalizability.
PubMed: 38935950
DOI: 10.2196/52059 -
Journal of Medical Internet Research Jun 2024Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement. (Comparative Study)
Comparative Study
BACKGROUND
Artificial intelligence, particularly chatbot systems, is becoming an instrumental tool in health care, aiding clinical decision-making and patient engagement.
OBJECTIVE
This study aims to analyze the performance of ChatGPT-3.5 and ChatGPT-4 in addressing complex clinical and ethical dilemmas, and to illustrate their potential role in health care decision-making while comparing seniors' and residents' ratings, and specific question types.
METHODS
A total of 4 specialized physicians formulated 176 real-world clinical questions. A total of 8 senior physicians and residents assessed responses from GPT-3.5 and GPT-4 on a 1-5 scale across 5 categories: accuracy, relevance, clarity, utility, and comprehensiveness. Evaluations were conducted within internal medicine, emergency medicine, and ethics. Comparisons were made globally, between seniors and residents, and across classifications.
RESULTS
Both GPT models received high mean scores (4.4, SD 0.8 for GPT-4 and 4.1, SD 1.0 for GPT-3.5). GPT-4 outperformed GPT-3.5 across all rating dimensions, with seniors consistently rating responses higher than residents for both models. Specifically, seniors rated GPT-4 as more beneficial and complete (mean 4.6 vs 4.0 and 4.6 vs 4.1, respectively; P<.001), and GPT-3.5 similarly (mean 4.1 vs 3.7 and 3.9 vs 3.5, respectively; P<.001). Ethical queries received the highest ratings for both models, with mean scores reflecting consistency across accuracy and completeness criteria. Distinctions among question types were significant, particularly for the GPT-4 mean scores in completeness across emergency, internal, and ethical questions (4.2, SD 1.0; 4.3, SD 0.8; and 4.5, SD 0.7, respectively; P<.001), and for GPT-3.5's accuracy, beneficial, and completeness dimensions.
CONCLUSIONS
ChatGPT's potential to assist physicians with medical issues is promising, with prospects to enhance diagnostics, treatments, and ethics. While integration into clinical workflows may be valuable, it must complement, not replace, human expertise. Continued research is essential to ensure safe and effective implementation in clinical environments.
Topics: Humans; Clinical Decision-Making; Artificial Intelligence
PubMed: 38935937
DOI: 10.2196/54571 -
American Society of Clinical Oncology... Jun 2024The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen... (Review)
Review
The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen deprivation therapy to an era of advanced imaging, precision diagnostics, genomics, and targeted treatment options. Concurrently, the emergence of large language models (LLMs) has dramatically transformed the paradigm for artificial intelligence (AI). This convergence of advancements in prostate cancer management and AI provides a compelling rationale to comprehensively review the current state of AI applications in prostate cancer care. Here, we review the advancements in AI-driven applications across the continuum of the journey of a patient with prostate cancer from early interception to survivorship care. We subsequently discuss the role of AI in prostate cancer drug discovery, clinical trials, and clinical practice guidelines. In the localized disease setting, deep learning models demonstrated impressive performance in detecting and grading prostate cancer using imaging and pathology data. For biochemically recurrent diseases, machine learning approaches are being tested for improved risk stratification and treatment decisions. In advanced prostate cancer, deep learning can potentially improve prognostication and assist in clinical decision making. Furthermore, LLMs are poised to revolutionize information summarization and extraction, clinical trial design and operations, drug development, evidence synthesis, and clinical practice guidelines. Synergistic integration of multimodal data integration and human-AI integration are emerging as a key strategy to unlock the full potential of AI in prostate cancer care.
Topics: Humans; Male; Prostatic Neoplasms; Artificial Intelligence
PubMed: 38935882
DOI: 10.1200/EDBK_438516 -
PloS One 2024The Youth Risk Behavior Survey (YRBS) among high school students includes standard questions about sexual identity and sex of sexual contacts, but these questions are...
PURPOSE
The Youth Risk Behavior Survey (YRBS) among high school students includes standard questions about sexual identity and sex of sexual contacts, but these questions are not consistently included in every state that conducts the survey. This study aimed to develop and apply a method to predict state-level proportions of high school students identifying as lesbian, gay, or bisexual (LGB) or reporting any same-sex sexual contacts in those states that did not include these questions in their 2017 YRBS.
METHODS
We used state-level high school YRBS data from 2013, 2015, and 2017. We defined two primary outcomes relating to self-reported LGB identity and reported same-sex sexual contacts. We developed machine learning models to predict the two outcomes based on other YRBS variables, and comparing different modeling approaches. We used a leave-one-out cross-validation approach and report results from best-performing models.
RESULTS
Modern ensemble models outperformed traditional linear models at predicting state-level proportions for the two outcomes, and we identified prediction methods that performed well across different years and prediction tasks. Predicted proportions of respondents reporting LGB identity in states that did not include direct measurement ranged between 9.4% and 12.9%. Predicted proportions of respondents reporting any same-sex contacts, where not directly observed, ranged between 7.0% and 10.4%.
CONCLUSION
Comparable population estimates of sexual minority adolescents can raise awareness among state policy makers and the public about what proportion of youth may be exposed to disparate health risks and outcomes associated with sexual minority status. This information can help decision makers in public health and education agencies design, implement and evaluate community and school interventions to improve the health of LGB youth.
Topics: Humans; Adolescent; Sexual and Gender Minorities; Male; Female; United States; Sexual Behavior; Surveys and Questionnaires; Machine Learning; Risk-Taking; Students
PubMed: 38935807
DOI: 10.1371/journal.pone.0304175 -
PLoS Computational Biology Jun 2024Spatial transcriptomics has gained popularity over the past decade due to its ability to evaluate transcriptome data while preserving spatial information. Cell...
Spatial transcriptomics has gained popularity over the past decade due to its ability to evaluate transcriptome data while preserving spatial information. Cell segmentation is a crucial step in spatial transcriptomic analysis, as it enables the avoidance of unpredictable tissue disentanglement steps. Although high-quality cell segmentation algorithms can aid in the extraction of valuable data, traditional methods are frequently non-spatial, do not account for spatial information efficiently, and perform poorly when confronted with the problem of spatial transcriptome cell segmentation with varying shapes. In this study, we propose ST-CellSeg, an image-based machine learning method for spatial transcriptomics that uses manifold for cell segmentation and is novel in its consideration of multi-scale information. We first construct a fully connected graph which acts as a spatial transcriptomic manifold. Using multi-scale data, we then determine the low-dimensional spatial probability distribution representation for cell segmentation. Using the adjusted Rand index (ARI), normalized mutual information (NMI), and Silhouette coefficient (SC) as model performance measures, the proposed algorithm significantly outperforms baseline models in selected datasets and is efficient in computational complexity.
PubMed: 38935799
DOI: 10.1371/journal.pcbi.1012254 -
PloS One 2024[This corrects the article DOI: 10.1371/journal.pone.0300195.].
[This corrects the article DOI: 10.1371/journal.pone.0300195.].
PubMed: 38935750
DOI: 10.1371/journal.pone.0306364 -
PloS One 2024Fertility-sparing treatment (FST) might be considered an option for reproductive patients with low-risk endometrial cancer (EC). On the other hand, the matching rates...
Prediction of final pathology depending on preoperative myometrial invasion and grade assessment in low-risk endometrial cancer patients: A Korean Gynecologic Oncology Group ancillary study.
OBJECTIVES
Fertility-sparing treatment (FST) might be considered an option for reproductive patients with low-risk endometrial cancer (EC). On the other hand, the matching rates between preoperative assessment and postoperative pathology in low-risk EC patients are not high enough. We aimed to predict the postoperative pathology depending on preoperative myometrial invasion (MI) and grade in low-risk EC patients to help extend the current criteria for FST.
METHODS/MATERIALS
This ancillary study (KGOG 2015S) of Korean Gynecologic Oncology Group 2015, a prospective, multicenter study included patients with no MI or MI <1/2 on preoperative MRI and endometrioid adenocarcinoma and grade 1 or 2 on endometrial biopsy. Among the eligible patients, Groups 1-4 were defined with no MI and grade 1, no MI and grade 2, MI <1/2 and grade 1, and MI <1/2 and grade 2, respectively. New prediction models using machine learning were developed.
RESULTS
Among 251 eligible patients, Groups 1-4 included 106, 41, 74, and 30 patients, respectively. The new prediction models showed superior prediction values to those from conventional analysis. In the new prediction models, the best NPV, sensitivity, and AUC of preoperative each group to predict postoperative each group were as follows: 87.2%, 71.6%, and 0.732 (Group 1); 97.6%, 78.6%, and 0.656 (Group 2); 71.3%, 78.6% and 0.588 (Group 3); 91.8%, 64.9%, and 0.676% (Group 4).
CONCLUSIONS
In low-risk EC patients, the prediction of postoperative pathology was ineffective, but the new prediction models provided a better prediction.
Topics: Humans; Female; Endometrial Neoplasms; Myometrium; Middle Aged; Adult; Republic of Korea; Neoplasm Invasiveness; Neoplasm Grading; Prospective Studies; Aged; Preoperative Period; Magnetic Resonance Imaging; Carcinoma, Endometrioid
PubMed: 38935680
DOI: 10.1371/journal.pone.0305360 -
PloS One 2024In recent years, with the development of the Internet, the attribution classification of APT malware remains an important issue in society. Existing methods have yet to...
In recent years, with the development of the Internet, the attribution classification of APT malware remains an important issue in society. Existing methods have yet to consider the DLL link library and hidden file address during the execution process, and there are shortcomings in capturing the local and global correlation of event behaviors. Compared to the structural features of binary code, opcode features reflect the runtime instructions and do not consider the issue of multiple reuse of local operation behaviors within the same APT organization. Obfuscation techniques more easily influence attribution classification based on single features. To address the above issues, (1) an event behavior graph based on API instructions and related operations is constructed to capture the execution traces on the host using the GNNs model. (2) ImageCNTM captures the local spatial correlation and continuous long-term dependency of opcode images. (3) The word frequency and behavior features are concatenated and fused, proposing a multi-feature, multi-input deep learning model. We collected a publicly available dataset of APT malware to evaluate our method. The attribution classification results of the model based on a single feature reached 89.24% and 91.91%. Finally, compared to single-feature classifiers, the multi-feature fusion model achieves better classification performance.
Topics: Software; Internet; Algorithms; Humans; Deep Learning
PubMed: 38935673
DOI: 10.1371/journal.pone.0304066