The recent global focus on big data in medicine has been associated with the rise of artificial intelligence (AI) in diagnosis and decision-making following recent advances in computer technology. Up to now, AI has been applied to various aspects of medicine, including disease diagnosis, surveillance, treatment, predicting future risk, targeted interventions and understanding of the disease. There have been plenty of successful examples in medicine of using big data, such as radiology and pathology, ophthalmology cardiology and surgery. Combining medicine and AI has become a powerful tool to change health care, and even to change the nature of disease screening in clinical diagnosis. As all we know, clinical laboratories produce large amounts of testing data every day and the clinical laboratory data combined with AI may establish a new diagnosis and treatment has attracted wide attention. At present, a new concept of radiomics has been created for imaging data combined with AI, but a new definition of clinical laboratory data combined with AI has lacked so that many studies in this field cannot be accurately classified. Therefore, we propose a new concept of clinical laboratory omics (Clinlabomics) by combining clinical laboratory medicine and AI. Clinlabomics can use high-throughput methods to extract large amounts of feature data from blood, body fluids, secretions, excreta, and cast clinical laboratory test data. Then using the data statistics, machine learning, and other methods to read more undiscovered information. In this review, we have summarized the application of clinical laboratory data combined with AI in medical fields. Undeniable, the application of Clinlabomics is a method that can assist many fields of medicine but still requires further validation in a multi-center environment and laboratory.

The current prognostic tools for esophageal squamous cell carcinoma (ESCC) lack the necessary accuracy to facilitate individualized patient management strategies. To address this issue, this study was conducted to develop a machine learning (ML) prediction model for ESCC patients' survival management. Six ML approaches, including Rpart, Elastic Net, GBM, Random Forest, GLMboost, and the machine learning-extended CoxPH method, were employed to develop risk prediction models. The model was trained on a dataset of 1954 ESCC patients with 27 clinical features and validated on a dataset of 487 ESCC patients. The discriminative performance of the models was assessed using the concordance index (C-index). The best performing model was used for risk stratification and clinical evaluation. The study found that N stage, T stage, surgical margin, tumor grade, tumor length, sex, MPV, AST, FIB, and Mg are the important feature for ESCC patients’ survival. The machine learning-extended CoxPH model, Elastic Net, and Random Forest had similar performance in predicting the mortality risk of ESCC patients, and outperformed GBM, GLMboost, and Rpart. The risk scores derived from the CoxPH model effectively stratified ESCC patients into low-, intermediate-, and high-risk groups with distinctly different 3-year overall survival (OS) probabilities of 80.8%, 58.2%, and 29.5%, respectively. This risk stratification was also observed in the validation cohort. Furthermore, the risk model demonstrated greater discriminative ability and net benefit than the AJCC8th stage, suggesting its potential as a prognostic tool for predicting survival events and guiding clinical decision-making. The classical algorithm of the CoxPH method was also found to be sufficiently good for interpretive studies.

The serological detection of antibodies to Treponema pallidum is essential to the diagnosis of syphilis. However, for the presence of cross-reaction, the specific antibody tests [e.g., enzyme-linked immunosorbent assay (ELISA)] always have false-positive results. In this study, we derived and validated the dissociation of urea in an attempt to alleviate the situation of false-positive antibodies to T. pallidum detected by ELISA. Six serum samples that were false-positive antibodies to T. pallidum detected by ELISA, and 16 control serum samples (8 sera positive for both specific IgG and IgM, and 8 IgG-positive and IgM-negative sera) were collected to select the appropriate dissociated concentration and time of urea. Our goal was to establish improved an ELISA method based on the original detection system of ELISA. The sensitivity of the improved ELISA was evaluated by 275 serum samples with class IgM-positive antibodies to T. pallidum. At 6 mol/L with 10 minutes dissociation of urea, 6 samples with false-positive antibodies to T. pallidum were converted to negative, and compared with true-positive antibodies to T. pallidum. The sensitivity of the improved ELISA was 100% by detecting the class IgM-positive antibodies to T. pallidum in sera of patients with syphilis. Considering the importance at the diagnosis of syphilis, antibodies to T. pallidum in serum samples should be retested by the improved ELISA method to avoid false-positive results.

Platelets are vital in many pathophysiological processes, yet there is a lack of a comprehensive resource dedicated specifically to platelet research. To fill this gap, we have developed PlateletBase, a knowledge base aimed at enhancing the understanding and study of platelets and related diseases. Our team retrieved information from various public databases, specifically extracting and analyzing RNA sequencing (RNA-seq) data from 3711 samples across 41 different conditions available on the National Center for Biotechnology Information (NCBI). PlateletBase offers six analytical and visualization tools, enabling users to perform gene similarity analysis, pair correlation, multi-correlation, expression ranking, clinical information association, and gene annotation for platelets. The current version of PlateletBase includes 10,278 genomic entries, 31,758 transcriptomic entries, 4869 proteomic entries, 2614 omics knowledge entries, 1833 drugs, 97 platelet resources, 438 diseases/traits, and six analysis modules. Each entry has been carefully curated and supported by experimental evidence. Additionally, PlateletBase features a user-friendly interface designed for efficient querying, manipulation, browsing, visualization, and analysis of detailed platelet protein and gene information. The case studies on gray platelet syndrome and angina pectoris demonstrate that PlateletBase is a suitable tool for identifying diagnostic biomarkers and exploring disease mechanisms, thereby advancing research in platelet functionality. PlateletBase is accessible at http://plateletbase.clinlabomics.org.cn/.

In addition to hemostasis and coagulation, years of studies have proved that platelets are involved in the whole process of tumor progression, including tumor invasion, intravasation, extravasation, and so on. It means that this property of platelets can be used in anti-tumor therapy. However, traditional platelet-based antitumor drugs often cause autologous platelet damage due to lack of targeting, resulting in serious side effects. Therefore, the researchers designed a variety of anti-tumor drug delivery systems based on platelets by targeting platelets or platelet membrane coating. The drug delivery systems have special response modes, which is crucial in the design of nanoparticles. These modes enhance the targeting and improve the anti-tumor effect. Here, we present a review of recent discoveries in the field of the crosstalk between platelets and tumors and the progress of platelet-based anti-tumor nanoparticles.