Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

/pdf/artificial-intelligence-assisted-diagnostic-cytology-and-3gluro6c.pdf

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

ABSTRACT Background Preeclampsia (PE) is one of the leading factors in maternal and perinatal mortality and morbidity worldwide. The only cure for PE to date is to deliver the placenta and stop gestation. However, the timing of delivery among PE patients is essential to minimize the risk of severe maternal morbidities, and at the same time ensure the survival of the baby. Methods In this study, we constructed a series of deep learning-based models to predict the prognosis, or the time to delivery, since the initial diagnosis of PE using electronic health record (EHR) data. We extracted and processed 1578 pregnancies in Michigan Medicine at the University of Michigan in 2015-2021 as the discovery cohort. Using the Cox-nnet v2 algorithm, we built the baseline model with EHR information prior to diagnosis, as well as the full model including baseline information and lab testing results and vital signs at the time of diagnosis. We evaluated the models using the C-index and log-rank p-values in KM survival curves, using both 20% testing data of the Michigan cohort, as well as 1177 PE pregnancy EHR data from the Medical Center of the University of Florida. Results The baseline prognosis model for time to delivery since PE diagnosis achieved C-index values of 0.75 and 0.72 on the training and testing set respectively. While the full model reached C-indices of 0.77 and 0.74 in the same training and testing sets. Both models performed better than their Cox-PH model counterparts. The seven most important features in the baseline model in descending order were diagnosis gestational age, severe PE, history of PE, age, parity, gravidity, and uncomplicated diabetes. Meanwhile, 14 most important features were selected and interpreted in the full model, including diagnosis gestational age, parity, severe PE, history of PE, features in lab tests (white blood cell, platelet, and red blood cell counts, AST value), min respiratory rate, and features measuring blood pressure (minimum, mean and standard deviation of systolic blood pressure, and maximum and standard deviation of diastolic blood pressure). Conclusion The time to delivery predicting models provide clinicians valuable tools and options to quantify the delivery risks and make better decisions on the optimal delivery time of PE patients at the time of diagnosis. Implementation of these actionable models into PE clinical care practice is expected to significantly improve the management of PE patients.

Deep learning-based prognosis prediction among preeclamptic pregnancies using electronic health record data

Abstract More than 11.5 billion COVID-19 vaccine doses have been administered around the world. Although vaccine effectiveness for severe infections is reported to be 89.0%, breakthrough infections are common and may lead to severe outcome in fragile population. We conducted a real-world observational study on 420 COVID-19 admitted patients from July 2021 to January 2022 in a tertiary level Italian hospital. We collected patient’s vaccination and SARS-CoV-2 serological status, SARS-CoV-2 treatments, oxygen supports, intensive (ICU) and subintensive (sub-ICU) care unit admissions, length of staying (LoS) and in-hospital mortality. One-hundred-seventy-two vaccinated and 248 unvaccinated patients were admitted during the study period. Vaccinated group (Vg) had a significantly more elevated Charlson Comorbidity Index than Unvaccinated group (UVg), and no statistical differences were found in terms of in-hospital mortality, LoS or ICU and sub-ICU admissions. Among Vg, anti-S antibodies were detected in 86.18% of patients (seropositives). Vaccinated seronegative patients’ in-hospital mortality was significantly higher than vaccinated seropositive patients (33.33% vs 10.69%, p = 0.0055): in particular, mortality rate in 45–69 years old population was higher in vaccinated seronegative group, and comparable in patients ≥ 70 years old. No differences in terms of outcome were registered between Vg and UVg, taking into account that Vg was considerably older and with more comorbidities. In line with other recent observations, higher mortality rate was evidenced for seronegative vaccinated patients. Primary prophylaxis and early treatments result to be necessary, especially for older and immunosuppressed populations. 

/pdf/characteristics-of-covid-19-vaccinated-and-unvaccinated-svghrgqu.pdf

Characteristics of COVID-19 vaccinated and unvaccinated patients admitted to Careggi University Hospital, Florence, Italy

Abstract Background Preeclampsia is a potentially fatal complication during pregnancy, characterized by high blood pressure and presence of proteins in the urine. Due to its complexity, prediction of preeclampsia onset is often difficult and inaccurate. Methods This study aims to create quantitative models to predict the onset gestational age of preeclampsia using electronic health records. We retrospectively collected 1178 preeclamptic pregnancy records from the University of Michigan Health System(UM) as the discovery cohort, and 881 records from the University of Florida Health System(UF) as the validation cohort. We constructed two Cox-proportional hazards models with Lasso regularization: one baseline model utilizing maternal and pregnancy characteristics, and the other full model with additional lab results, vital signs, and medications in the first 20 weeks of pregnancy. We built the models using 80% of the UM data and subsequently tested them on the remaining 20% UM data and validated with UF data. We further stratified the patients into high and low risk groups for preeclampsia onset risk assessment. Findings The baseline model reached C-indices of 0.64 and 0.61 in the 20% UM testing data and the UF validation data, respectively, while the full model increased these C-indices to 0.69 and 0.61 respectively. Both the baseline and full models contain five selective features, among which number of fetuses in the pregnancy, hypertension and parity are shared between the two models with similar hazard ratios. In the baseline model, history of complicated type II diabetes and a mood/anxiety disorder during the first 20 weeks of pregnancy were important. In the full model, maximum diastolic blood pressure in early pregnancy was the predominant feature. Interpretation Electronic health record data provide useful information to predict gestational age of preeclampsia onset. Stratification of the cohorts using five-predictor Cox-PH models provide clinicians with convenient tools to assess the patient onset time of preeclampsia. Funding This study was supported by grants through the NIEHS, NICHD, NIDDK, and NCATS.

/pdf/building-and-validating-5-feature-models-to-predict-3uqtvq70.pdf

Building and validating 5-feature models to predict preeclampsia onset time from electronic health record data

Predicting risk factors associated with preterm delivery using a machine learning model

Lymphomas vary in terms of clinical behavior, morphology, and response to therapies and thus accurate classification is essential for appropriate management of patients. In this study, using a set of 670 cases of lymphoma obtained from a center in Guatemala City, we propose an interpretable machine learning method, LymphoML, for lymphoma subtyping into eight diagnostic categories. LymphoML sequentially applies steps of (1) object segmentation to extract nuclei, cells, and cytoplasm from H&E-stained TMA cores, (2) feature extraction of morphological, textural, and architectural features, and (3) aggregation of per-object features to create patch-level feature vectors for lymphoma classification. LymphoML achieves a diagnostic accuracy of 64.3% (95% CI: [55.8%, 72.9%]) among 8 lymphoma subtypes using only tissue microarray core sections stained with hematoxylin and eosin (H&E), at a level similar to experienced hematopathologists. We find that the best model's set of nuclear and cytoplasmic morphological, textural, and architectural features are most discriminative for diffuse large B-cell lymphoma (F1 score: 78.7%), classic Hodgkin lymphoma (F1 score: 74.5%), and mantle cell lymphoma (F1 score: 71.0%). We find that nuclear shape features provide the highest diagnostic yield, with nuclear texture, cytoplasmic, and architectural features providing smaller gains in accuracy. Finally, we find that combining information from the H&E-based model together with the results of a limited set of immunohistochemical (IHC) stains resulted in a similar diagnostic accuracy (85.3% ([79.1%, 90.7%])) as with a much larger set of IHC stains (86.1% ([79.8%, 91.5%])). Our work suggests a potential way to incorporate machine learning tools into clinical practice to reduce the number of expensive IHC stains while achieving a similar level of diagnostic accuracy.

/pdf/lymphoml-an-interpretable-artificial-intelligence-based-35rm947x.pdf

LymphoML: An interpretable artificial intelligence-based method identifies morphologic features that correlate with lymphoma subtype

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a global pandemic with more than 485 millions infected. Questions about non-responders to SARS-CoV-2 vaccines remain unaddressed. Here, we report data from people after administering the complete dose of SARS-CoV-2 vaccines using the World Health Organization International Standard for anti-SARS-CoV-2 immunoglobulin. Our study showed that immune cells such as CD4 cells, CD8 cells, and B cells and anti-spike immunoglobulin G levels were significantly reduced in the elderly. There were 7.5% non-responders among the 18-59 yr group and 11.7% in the [≥]60 yr group. A titer of anti-SARS-CoV-2 spike immunoglobulin G is blew 50 BAU/mL to be considered as non-responders at intervals of 30 to 90 days after the last vaccine dose. Booster vaccination may be recommended for non-responders to reduce the disease severity and mortality.

/pdf/interpretation-of-non-responders-to-sars-cov-2-vaccines-tmktj7wu.pdf

Interpretation of non-responders to SARS-CoV-2 vaccines using WHO International Standard

Background: Obesity is a serious public health problem. According to statistics, there are millions obese people worldwide. The intestinal microbiota is the microbiota that lives in the gastrointestinal tract of the human body and can interact with the external environment through diet. Probing and summarizing the relationship between intestinal microbes and obesity has important guiding significance for the accurate control of the research direction and expanding the choice of obesity treatment methods. We aimed to use bibliometrics to qualitatively and quantitatively analyze the published literature and to reveal the research hotspots and development trends in the effects of intestinal microbes on obesity research. Methods: We obtained documents from the core collection of Web of Science (WoSCC) from 2013-2022 on 2nd February 2023. Microsoft Excel, Biblioshiny R language software packages and CiteSpace were employed to collect publication data, analyze publication trends, and visualize relevant results. Results: We identified 8888 original research articles on the effects of intestinal microbes on obesity published between 2013 and 2022. China made the highest number of publications on the topic, with 3036 publications (34.16%), and the United States with 87065 citations made the greatest contribution. University of Copenhagen was the most prolific institution (209 publications). Patrice D. Cani published the most related articles (97 publications), whereas Peter J. Turnbaugh was cited the most frequently (3307 citations). Nutrients was the journal with the most studies (399 publications, 4.49%), and Nature was the most commonly co-cited journal (6446 citations). The burst keywords "obese patient" and "serum" recently appeared as research frontiers. Conclusion: Although China has the largest number of publications, the United States, depending on its largest citations, has become the leader in the effects of intestinal microbes on obesity research. Current research hotspots focus on related mechanisms of the effects of intestinal microbes on obesity and therapeutic methods for obesity with intestinal microbes. Through diet, probiotic preparations and regulation of the intestinal flora, fecal microbe transplantation may have a significant impact on reducing the obesity epidemic. Considering the great potential and application prospects, intestinal microbe applications in obesity therapy will remain a research hotspot in the future.

/pdf/effects-of-intestinal-microbes-on-obesity-a-bibliometric-2zs44con.pdf

Effects of intestinal microbes on obesity: A bibliometric analysis from 2013-2022

Popular Tasks used by Researchers

How can I help with your research?

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

Anyone with the link can view this chat. You can switch it back to private anytime.

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

X. Yang

Author Tools

Chat about Author