A patient-oriented clinical decision support system for CRC risk assessment and preventative care

The Application of Knowledge-Based Clinical Decision Support Systems to Enhance Adherence to Evidence-Based Medicine in Chronic Disease

Among the technology-based solutions, clinical decision support systems (CDSSs) have the ability to keep up with clinicians with the latest evidence in a smart way. Hence, the main objective of our study was to investigate the applicability and characteristics of CDSSs regarding chronic disease. The Web of Science, Scopus, OVID, and PubMed databases were searched using keywords from January 2000 to February 2023. The review was completed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist. Then, an analysis was done to determine the characteristics and applicability of CDSSs. The quality of the appraisal was assessed using the Mixed Methods Appraisal Tool checklist (MMAT). A systematic database search yielded 206 citations. Eventually, 38 articles from sixteen countries met the inclusion criteria and were accepted for final analysis. The main approaches of all studies can be classified into adherence to evidence-based medicine (84.2%), early and accurate diagnosis (81.6%), identifying high-risk patients (50%), preventing medical errors (47.4%), providing up-to-date information to healthcare providers (36.8%), providing patient care remotely (21.1%), and standardizing care (71.1%). The most common features among the knowledge-based CDSSs included providing guidance and advice for physicians (92.11%), generating patient-specific recommendations (84.21%), integrating into electronic medical records (60.53%), and using alerts or reminders (60.53%). Among thirteen different methods to translate the knowledge of evidence into machine-interpretable knowledge, 34.21% of studies utilized the rule-based logic technique while 26.32% of studies used rule-based decision tree modeling. For CDSS development and translating knowledge, diverse methods and techniques were applied. Therefore, the development of a standard framework for the development of knowledge-based decision support systems should be considered by informaticians.

Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review

Background

Artificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application.

Objective

This study is a review of the knowledge-based and data-based CDSS literature regarding interpretability in health care. It highlights the relevance of interpretability for CDSS and the area for improvement from technological and medical perspectives.

Methods

A systematic search was conducted on the interpretability-related literature published from 2011 to 2020 and indexed in the five databases: Web of Science, PubMed, ScienceDirect, Cochrane, and Scopus. Journal articles that focus on the interpretability of CDSS were included for analysis. Experienced researchers also participated in manually reviewing the selected articles for inclusion/exclusion and categorization.

Results

Based on the inclusion and exclusion criteria, 20 articles from 16 journals were finally selected for this review. Interpretability, which means a transparent structure of the model, a clear relationship between input and output, and explainability of artificial intelligence algorithms, is essential for CDSS application in the healthcare setting. Methods for improving the interpretability of CDSS include ante-hoc methods such as fuzzy logic, decision rules, logistic regression, decision trees for knowledge-based AI, and white box models, post hoc methods such as feature importance, sensitivity analysis, visualization, and activation maximization for black box models. A number of factors, such as data type, biomarkers, human-AI interaction, needs of clinicians, and patients, can affect the interpretability of CDSS.

Conclusions

The review explores the meaning of the interpretability of CDSS and summarizes the current methods for improving interpretability from technological and medical perspectives. The results contribute to the understanding of the interpretability of CDSS based on AI in health care. Future studies should focus on establishing formalism for defining interpretability, identifying the properties of interpretability, and developing an appropriate and objective metric for interpretability; in addition, the user's demand for interpretability and how to express and provide explanations are also the directions for future research.

LncRNA LINC02535 Induces Colorectal Adenocarcinoma Progression via Modulating miR-30d-5p/CHD1

Growing evidence has suggested that lncRNAs play a significant role in the development of colorectal adenocarcinoma. LncRNA LINC02535 was a potential novel lncRNA marker of neoplastic processes of the colon. Nevertheless, the function and mechanisms of LINC02535 in colorectal adenocarcinoma remain unclear. Proteins levels were measured by western blotting. EdU, CCK-8, Transwell, and wound healing assays were performed to investigate the function of LINC02535 in colorectal adenocarcinoma. The distribution of LINC02535 in cells was evaluated by subcellular fractionation assay. The interaction among RNAs was identified by luciferase reporter and RIP assays. In this study, our findings revealed that LINC02535 was highly expressed in colorectal adenocarcinoma cells. Knockdown of LINC02535 inhibited colorectal adenocarcinoma cell proliferation, migration, and invasion. Mechanistically, LINC02535 bound with miR-30d-5p and worked as a competing endogenous RNA to facilitate the expression of messenger RNA chromodomain helicase DNA-binding protein 1 (CHD1). miR-30d-5p directly targeted the sequence of CHD1 3'-untranslated region. Notably, CHD1 upregulation abolished the suppressive influence of LINC02535 inhibition on the malignant phenotypes of colorectal adenocarcinoma cells. Overall, it was disclosed that LINC02535 played an oncogenic role in colorectal adenocarcinoma progression by sponging miR-30d-5p to upregulate CHD1 expression.

Developing Automated Computer Algorithms to Phenotype Periodontal Disease Diagnoses in Electronic Dental Records

OBJECTIVE

 Our objective was to phenotype periodontal disease (PD) diagnoses from three different sections (diagnosis codes, clinical notes, and periodontal charting) of the electronic dental records (EDR) by developing two automated computer algorithms.

METHODS

 We conducted a retrospective study using EDR data of patients (n = 27,138) who received care at Temple University Maurice H. Kornberg School of Dentistry from January 1, 2017 to August 31, 2021. We determined the completeness of patient demographics, periodontal charting, and PD diagnoses information in the EDR. Next, we developed two automated computer algorithms to automatically diagnose patients' PD statuses from clinical notes and periodontal charting data. Last, we phenotyped PD diagnoses using automated computer algorithms and reported the improved completeness of diagnosis.

RESULTS

 The completeness of PD diagnosis from the EDR was as follows: periodontal diagnosis codes 36% (n = 9,834), diagnoses in clinical notes 18% (n = 4,867), and charting information 80% (n = 21,710). After phenotyping, the completeness of PD diagnoses improved to 100%. Eleven percent of patients had healthy periodontium, 43% were with gingivitis, 3% with stage I, 36% with stage II, and 7% with stage III/IV periodontitis.

CONCLUSIONS

 We successfully developed, tested, and deployed two automated algorithms on big EDR datasets to improve the completeness of PD diagnoses. After phenotyping, EDR provided 100% completeness of PD diagnoses of 27,138 unique patients for research purposes. This approach is recommended for use in other large databases for the evaluation of their EDR data quality and for phenotyping PD diagnoses and other relevant variables.

Real-time analysis and display of quantitative measures to track and improve clinical workflow

Purpose

Radiotherapy treatment planning is a complex process with multiple, dependent steps involving an interdisciplinary patient care team. Effective communication and real‐time tracking of resources and care path activities are key for clinical efficiency and patient safety.

Materials and Methods

We designed and implemented a secure, interactive web‐based dashboard for patient care path, clinical workflow, and resource utilization management. The dashboard enables visualization of resource utilization and tracks progress in a patient's care path from the time of acquisition of the planning CT to the time of treatment in real‐time. It integrates with the departmental electronic medical records (EMR) system without the creation and maintenance of a separate database or duplication of work by clinical staff. Performance measures of workflow were calculated.

Results

The dashboard implements a standardized clinical workflow and dynamically consolidates real‐time information queried from multiple tables in the EMR database over the following views: (1) CT Sims summarizes patient appointment information on the CT simulator and patient load; (2) Linac Sims summarizes patient appointment times, setup history, and notes, and patient load; (3) Task Status lists the clinical tasks associated with a treatment plan, their due date, status and ownership, and patient appointment details; (4) Documents provides the status of all documents in the patients' charts; and (5) Diagnoses and Interventions summarizes prescription information, imaging instructions and whether the plan was approved for treatment. Real‐time assessment and quantification of progress and delays in a patient's treatment start were achieved.

Conclusions

This study indicates it is feasible to develop and implement a dashboard, tailored to the needs of an interdisciplinary team, which derives and integrates information from the EMR database for real‐time analysis and display of resource utilization and clinical workflow in radiation oncology. The framework developed facilitates informed, data‐driven decisions on clinical workflow management as we seek to optimize clinical efficiency and patient safety.

Proteomic screening of potential N-glycoprotein biomarkers for colorectal cancer by TMT labeling combined with LC-MS/MS

BACKGROUND AND AIMS

Colorectal cancer (CRC) is part of the most widespread malignant tumors. At present, colonoscopy is a routine procedure in the diagnosis of CRC, but it is traumatic. Carcinoembryonic antigen, CA199, and CA242 are common serum markers for the diagnosis of CRC; however, they do not demonstrate satisfactory specificity and sensitivity for the diagnosis of CRC. Hence, Now it is necessary to screen many valuable serum biomarkers for CRC, proteomics methods have been used to investigate PTMs such as glycosylation of proteins with prominent roles in the occurrence and development of tumors.

METHODS

This study screens altering glycosylated proteins of CRC tissues using LC-MS/MS quantitative glycoproteomics, and then these candidate biomarkers for CRC are further validated by serum glycoproteomics.

RESULTS

The results of glycoproteomics in CRC tissues show that the abundance of 160 and 79 glycerogelatin proteins was obviously upregulated and downregulated compared with their adjacent tissues(P < 0.05). Bioinformatics analysis suggests that these molecules are mainly involved in many biological processes, including skeletal system development, collagen fibril organization, and receptor-mediated endocytosis. Results of serum glycoproteomics show that the changing trends of 2 protein glycosylation were consistent with MS results of CRC tissues, including ICAM1and APMAP. Areas under the ROC curve (AUC) results confirm that ICAM1and APMAP as early immune diagnosis markers of CRC has excellent sensitivity and specificity.

CONCLUSION

The ICAM1 and APMAP may serve as a potential tumor marker for CRC.

COPB2 gene silencing inhibits colorectal cancer cell proliferation and induces apoptosis via the JNK/c-Jun signaling pathway

Objectives

Colorectal cancer (CRC) is one of the most common malignant human tumors. It is associated with high morbidity and mortality rates. In recent years, tumor gene therapy has emerged as a promising new approach for colorectal cancer therapy. Herein, we identify and analyze the role of COPB2 (coatomer protein complex, subunit beta 2) in proliferation and apoptosis of CRC cells.

Methods

To investigate the role of COPB2 in the proliferation and apoptosis of CRC cells, a shCOPB2 vector and a shCtrl vector were constructed for transfection into RKO and HCT116 cells. Cells proliferation was subsequently measured via cell counting kit-8 (CCK8) assay and Celigo cell counting assay. Apoptosis was measured via flow cytometry. The activity level of Caspase 3/7 was measured. Finally, the level of several JNK/c-Jun apoptosis pathway-related proteins were measured to characterize the mechanism of apoptosis.

Results

Our results showed that the proliferation rate was decreased and the apoptosis rate was increased in shCOPB2-treated RKO and HCT116 cells compared to those in controls. After the silencing of COPB2, JNK/c-Jun signal pathway activation was increased, the expression levels of apoptosis pathway-related proteins, such as Bad, p53 and Caspase 3, were also increased.

Conclusion

COPB2 gene silencing can inhibit RKO and HCT116 cells proliferation and induce apoptosis via the JNK/c-Jun signaling pathway.

Modelling clinical experience data as an evidence for patient-oriented decision support

Background

Evidence-based Clinical Decision Support Systems (CDSSs) usually obtain clinical evidences from randomized controlled trials based on coarse-grained groups. Individuals who are beyond the scope of the original trials cannot be accurately and objectively supported. Also, patients’ opinions and preferences towards the health care delivered to them have rarely been considered. In this regards, we propose to use clinical experience data as an evidence to support patient-oriented decision-making.

Methods

The experience data of similar patients from social networks as subjective evidence and the argumentation rules derived from clinical guidelines as objective evidence are combined to support decision making together. They are integrated into a comprehensive decision support architecture. The patient reviews are crawled from social networks and sentimentally analyzed to become structured data which are mapped to the Clinical Sentiment Ontology (CSO). This is used to build a Patient Experience Knowledge Base (PEKB) that can complement the original clinical guidelines. An Experience Inference Engine (EIE) is developed to match similar experience cases from both patient preference features and patient conditions and ultimately, comprehensive clinical recommendations are generated.

Results

A prototype system is designed and implemented to show the feasibility of the decision support architecture. The system allows patients and domain experts to easily explore various choices and trade-offs via modifying attribute values to select the most appropriate decisions.

Conclusions

The integrated decision support architecture built is generic to solving a wide range of clinical problems. This will lead to better-informed clinical decisions and ultimately improved patient care.

Long noncoding MAGI2-AS3 promotes colorectal cancer progression through regulating miR-3163/TMEM106B axis

Colorectal cancer (CRC), is mostly derived from normal colon epithelial cells, and has been reported to be one of most common gastrointestinal malignancies globally. An increasing number of researchers have claimed that long noncoding RNAs (lncRNAs) exert significant functions in tumor progression. Nevertheless, the function of MAGI2-AS3 remains uncertain in CRC. The expression of MAGI2-AS3, miR-3163, and transmembrane protein 106B (TMEM106B) messenger RNA was examined by quantitative real-time polymerase chain reaction. Cell apoptosis was measured by caspase-3 activity test. Cell proliferation was tested by cell-counting kit 8 and 5-ethynyl-2'-deoxyuridine assays. Cell migration was detected by transwell assay. Western blot analysis examined the protein expression of TMEM106B. The expression of Ki-67 was evaluated by immunohistochemistry assay. The binding capacity between miR-3163 and MAGI2-AS3 (or TMEM106B) was studied by radioimmunoprecipitation and luciferase reporter assays. The expression of MAGI2-AS3 and TMEM106B was conspicuously upregulated whereas miR-3163 presented lower expression in CRC cells. MAGI2-AS3 deficiency facilitated cell apoptosis but hampered cell proliferation and migration. MAGI2-AS3 combined with miR-3163 and negatively regulated miR-3163 expression. In addition, the administration of sh-MAGI2-AS3 or miR-3163 mimics suppressed CRC cell growth in vivo. Subsequently, miR-3163 targeted TMEM106B and the transfection of sh-MAGI2-AS3 or miR-3163 mimics downregulated TMEM106B expression. Rescue assays verified that TMEM106B overexpression recovered the effects of MAGI2-AS3 inhibition on cell apoptosis, proliferation, and migration in CRC. MAGI2-AS3 drives CRC progression through regulating miR-3163/TMEM106B axis. This supplies innovative insights on the investigation of molecular mechanism in CRC progression.

SNHG14 promotes the tumorigenesis and metastasis of colorectal cancer through miR-32-5p/SKIL axis

Colorectal cancer (CRC) is regarded as one of the top ten malignant cancers, which has caused millions of mortalities all over the world. Although advanced therapeutic methods have been employed to treat CRC, the prognosis of CRC patients remains unsatisfactory. Many researchers claimed long noncoding RNAs (lncRNAs) frequently participate in the development of cancers. Small nucleolar RNA host gene 14 (SNHG14) was proved to play roles in various cancers. Nevertheless, neither biological function nor regulatory mechanism of SNHG14 has been explored in CRC. This investigation is aimed at exploring the role of SNHG14 in CRC. The expression of genes including SNHG14, miR-32-5p, and ski-oncogene-like (SKIL) was measured by RT-qPCR assay. 5-Ethynyl-2'-deoxyuridine (EdU) assay was employed to measure cell proliferation. Cell migration and invasion were evaluated by transwell assay. Western blot assay was performed to test the protein expression. The binding capacity between miR-32-5p and SNHG14 (or SKIL) was explored by luciferase reporter and RNA immunoprecipitation (RIP) assays. SNHG14 expression is upregulated in CRC cells. Moreover, SNHG14 suppression inhibited the proliferation, metastasis, and epithelial-mesenchymal transition (EMT) process in CRC cells. miR-32-5p presented lower expression, which was negatively regulated by SNHG14. SKIL could combine with miR-32-5p. The mRNA and protein expression of SKIL was downregulated by SNHG14 knockdown or miR-32-5p overexpression. At last, the inhibitory effect of SNHG14 suppression on proliferation, metastasis, and EMT process was rescued by SKIL overexpression. SNHG14 regulates CRC progression via miR-32-5p/SKIL axis, providing a novel point in treatment of CRC patients.