scholarly journals Using Domain Knowledge and Data-Driven Insights for Patient Similarity Analytics

2021 ◽  
Vol 11 (8) ◽  
pp. 699
Author(s):  
Ronald Wihal Oei ◽  
Hao Sen Andrew Fang ◽  
Wei-Ying Tan ◽  
Wynne Hsu ◽  
Mong-Li Lee ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
Vital Signs ◽  
Data Driven ◽  
Test Results ◽  
Substantial Agreement ◽  
Health Records ◽  
Specific Patient ◽  
Knowledge Based ◽  
Medical Institutions ◽  
Laboratory Test Results

Patient similarity analytics has emerged as an essential tool to identify cohorts of patients who have similar clinical characteristics to some specific patient of interest. In this study, we propose a patient similarity measure called D3K that incorporates domain knowledge and data-driven insights. Using the electronic health records (EHRs) of 169,434 patients with either diabetes, hypertension or dyslipidaemia (DHL), we construct patient feature vectors containing demographics, vital signs, laboratory test results, and prescribed medications. We discretize the variables of interest into various bins based on domain knowledge and make the patient similarity computation to be aligned with clinical guidelines. Key findings from this study are: (1) D3K outperforms baseline approaches in all seven sub-cohorts; (2) our domain knowledge-based binning strategy outperformed the traditional percentile-based binning in all seven sub-cohorts; (3) there is substantial agreement between D3K and physicians (κ = 0.746), indicating that D3K can be applied to facilitate shared decision making. This is the first study to use patient similarity analytics on a cardiometabolic syndrome-related dataset sourced from medical institutions in Singapore. We consider patient similarity among patient cohorts with the same medical conditions to develop localized models for personalized decision support to improve the outcomes of a target patient.

scholarly journals Individualised risk prediction model for new-onset, progression and regression of chronic kidney disease in a retrospective cohort of patients with type 2 diabetes under primary care in Hong Kong

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e035308
Author(s):  
Lin Yang ◽  
Tsun Kit Chu ◽  
Jinxiao Lian ◽  
Cheuk Wai Lo ◽  
Shi Zhao ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Type 2 Diabetes ◽  
Primary Care ◽  
Retrospective Cohort ◽  
Density Lipoprotein ◽  
Test Results ◽  
Health Records ◽  
Laboratory Test Results ◽  
New Onset

ObjectivesThis study is aimed to develop and validate a prediction model for multistate transitions across different stages of chronic kidney disease (CKD) in patients with type 2 diabetes mellitus under primary care.SettingWe retrieved the anonymised electronic health records of a population-based retrospective cohort in Hong Kong.ParticipantsA total of 26 197 patients were included in the analysis.Primary and secondary outcome measuresThe new-onset, progression and regression of CKD were defined by the transitions of four stages that were classified by combining glomerular filtration rate and urine albumin-to-creatinine ratio. We applied a multiscale multistate Poisson regression model to estimate the rates of the stage transitions by integrating the baseline demographic characteristics, routine laboratory test results and clinical data from electronic health records.ResultsDuring the mean follow-up time of 1.8 years, there were 2632 patients newly diagnosed with CKD, 1746 progressed to the next stage and 1971 regressed into an earlier stage. The models achieved the best performance in predicting the new-onset and progression with the predictors of sex, age, body mass index, systolic blood pressure, diastolic blood pressure, serum creatinine, haemoglobin A1c, total cholesterol, low-density lipoprotein, high-density lipoprotein, triglycerides and drug prescriptions.ConclusionsThis study demonstrated that individual risks of new-onset and progression of CKD can be predicted from the routine physical and laboratory test results. The individualised prediction curves developed from this study could potentially be applied to routine clinical practices, to facilitate clinical decision making, risk communications with patients and early interventions.

The utility of clinical findings to predict laboratory values in hypertensive disorders of pregnancy

2016 ◽  
Vol 44 (3) ◽  
Author(s):  
Jane So ◽  
Elizabeth Young ◽  
Natalie Crnosija ◽  
Joseph Chappelle
Keyword(s):  
Severe Disease ◽  
Vital Signs ◽  
Retrospective Chart Review ◽  
Clinical Findings ◽  
Bivariate Analysis ◽  
Test Results ◽  
Quadrant Pain ◽  
Laboratory Findings ◽  
Abnormal Laboratory ◽  
Laboratory Test Results

AbstractPreeclampsia is the 2A retrospective chart review of women who presented for evaluation of hypertension in pregnancy during 2010. Demographic information, medical history, symptoms, vital signs, and laboratory results were collected. Bivariate analysis was used to investigate associations between predictors and the outcome.Of the 481 women in the sample, 22 were identified as having abnormal laboratory test results (4.6%). Women who reported right upper quadrant pain or tenderness had significantly increased likelihood of having laboratory abnormalities compared to those without the complaint.Only a small percentage of women evaluated were determined to have abnormal laboratory findings, predominantly among women with severe preeclampsia. Right upper quadrant pain or tenderness was positively correlated with laboratory abnormalities. The restriction of laboratory analysis in women with clinical evidence of severe disease may be warranted – a broader study should, however, first be used to confirm our findings.

scholarly journals Graphical display of diagnostic test results in electronic health Records: a comparison of 8 systems

2015 ◽  
Vol 22 (4) ◽  
pp. 900-904 ◽  
Author(s):  
Dean F Sittig ◽  
Daniel R Murphy ◽  
Michael W Smith ◽  
Elise Russo ◽  
Adam Wright ◽  
...  
Keyword(s):  
Electronic Health Records ◽  
Laboratory Test ◽  
Clinical Laboratory ◽  
Negative Impact ◽  
Laboratory Data ◽  
Test Results ◽  
Health Records ◽  
Laboratory Test Results ◽  
Data Points ◽  
Electronic Health

Abstract Accurate display and interpretation of clinical laboratory test results is essential for safe and effective diagnosis and treatment. In an attempt to ascertain how well current electronic health records (EHRs) facilitated these processes, we evaluated the graphical displays of laboratory test results in eight EHRs using objective criteria for optimal graphs based on literature and expert opinion. None of the EHRs met all 11 criteria; the magnitude of deficiency ranged from one EHR meeting 10 of 11 criteria to three EHRs meeting only 5 of 11 criteria. One criterion (i.e., the EHR has a graph with y-axis labels that display both the name of the measured variable and the units of measure) was absent from all EHRs. One EHR system graphed results in reverse chronological order. One EHR system plotted data collected at unequally-spaced points in time using equally-spaced data points, which had the effect of erroneously depicting the visual slope perception between data points. This deficiency could have a significant, negative impact on patient safety. Only two EHR systems allowed users to see, hover-over, or click on a data point to see the precise values of the x–y coordinates. Our study suggests that many current EHR-generated graphs do not meet evidence-based criteria aimed at improving laboratory data comprehension.

scholarly journals Artificial Intelligence in Clinical Decision Support: a Focused Literature Survey

2019 ◽  
Vol 28 (01) ◽  
pp. 120-127 ◽  
Author(s):  
Stefania Montani ◽  
Manuel Striani
Keyword(s):  
Artificial Intelligence ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Domain Knowledge ◽  
Knowledge Integration ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Data Driven ◽  
Knowledge Based ◽  
Hybrid Approaches

Objectives: This survey analyses the latest literature contributions to clinical decision support systems (DSSs) on a two-year period (2017-2018), focusing on the approaches that adopt Artificial Intelligence (AI) techniques in a broad sense. The goal is to analyse the distribution of data-driven AI approaches with respect to “classical" knowledge-based ones, and to consider the issues raised and their possible solutions. Methods: We included PubMed and Web of ScienceTM publications, focusing on contributions describing clinical DSSs that adopted one or more AI methodologies. Results: We selected 75 papers, 49 of which describe approaches in the data-driven AI area, 20 present purely knowledge-based DSSs, and 6 adopt hybrid approaches relying on both formalized knowledge and data. Conclusions: Recent studies in the clinical DSS area demonstrate a prevalence of data-driven AI, which can be adopted autonomously in purely data-driven systems, or in cooperation with domain knowledge in hybrid systems. Such hybrid approaches, able to conjugate all available knowledge sources through proper knowledge integration steps, represent an interesting example of synergy between the two AI categories. This synergy can lead to the resolution of some existing issues, such as the need for transparency and explainability, nowadays recognized as central themes to be addressed by both AI and medical informatics research.

Abstraction Hierarchy Based Explainable Artificial Intelligence

2020 ◽  
Vol 64 (1) ◽  
pp. 319-323
Author(s):  
Murat Dikmen ◽  
Catherine Burns
Keyword(s):  
Artificial Intelligence ◽  
Domain Knowledge ◽  
Evaluation Process ◽  
Data Driven ◽  
Data Set ◽  
Knowledge Based ◽  
Cognitive Work ◽  
Explainable Artificial Intelligence ◽  
Loan Approval

This work explores the application of Cognitive Work Analysis (CWA) in the context of Explainable Artificial Intelligence (XAI). We built an AI system using a loan evaluation data set and applied an XAI technique to obtain data-driven explanations for predictions. Using an Abstraction Hierarchy (AH), we generated domain knowledge-based explanations to accompany data-driven explanations. An online experiment was conducted to test the usefulness of AH-based explanations. Participants read financial profiles of loan applicants, the AI system’s loan approval/rejection decisions, and explanations that justify the decisions. Presence or absence of AH-based explanations was manipulated, and participants’ perceptions of the explanation quality was measured. The results showed that providing AH-based explanations helped participants learn about the loan evaluation process and improved the perceived quality of explanations. We conclude that a CWA approach can increase understandability when explaining the decisions made by AI systems.

scholarly journals Prognostic Value of Severity Score Change for Septic Shock in the Emergency Room

Diagnostics ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 743
Author(s):  
Tae Sik Hwang ◽  
Hyun Woo Park ◽  
Ha Young Park ◽  
Young Sook Park
Keyword(s):  
Septic Shock ◽  
Laboratory Test ◽  
Emergency Room ◽  
Characteristic Curve ◽  
Vital Signs ◽  
Scoring Systems ◽  
Early Warning Score ◽  
Time Of Arrival ◽  
Test Results ◽  
Laboratory Test Results

The vital signs or laboratory test results of sepsis patients may change before clinical deterioration. This study examined the differences in prognostic performance when systemic inflammatory response syndrome (SIRS), Sequential Organ Failure Assessment (SOFA), quick SOFA (qSOFA) scores, National Early Warning Score (NEWS), and lactate levels were repeatedly measured. Scores were obtained at arrival to triage, 1 h after fluid resuscitation, 1 h after vasopressor prescription, and before leaving the emergency room (ER) in 165 patients with septic shock. The relationships between score changes and in-hospital mortality, mechanical ventilation, admission to the intensive care unit, and mortality within seven days were compared using areas under receiver operating characteristic curve (AUROCs). Scores measured before leaving the ER had the highest AUROCs across all variables (SIRS score 0.827 [0.737–0.917], qSOFA score 0.754 [0.627–0.838], NEWS 0.888 [0.826–0.950], SOFA score 0.835 [0.766–0.904], and lactate 0.872 [0.805–0.939]). When combined, SIRS + lactate (0.882 [0.804–0.960]), qSOFA + lactate (0.872 [0.808–0.935]), NEWS + lactate (0.909 [0.855–0.963]), and SOFA + lactate (0.885 [0.832–0.939]) showed improved AUROCs. In patients with septic shock, scoring systems show better predictive performances at the timepoints reflecting changes in vital signs and laboratory test results than at the time of arrival, and combining them with lactate values increases their predictive powers.

scholarly journals Review of a New Multimodal Antidepressant Vortioxetine

2016 ◽  
Vol 16 (2) ◽  
pp. 44-48 ◽  
Author(s):  
M Oppa ◽  
D Cesnekova ◽  
G Nosalova ◽  
I Ondrejka
Keyword(s):  
Vital Signs ◽  
Inadequate Response ◽  
Cognitive Effects ◽  
Test Results ◽  
Major Depressive ◽  
Uptake Inhibition ◽  
Uptake Inhibitors ◽  
Laboratory Test Results ◽  
Significant Efficacy ◽  
Low Incidence

Abstract Vortioxetine is a novel antidepressant with two mechanisms of action – direct effect on several serotonin receptors and serotonin re-uptake inhibition. It shows antidepressant, anxiolytic and cognitive effects during the treatment of major depressive disorder (MDD). The aim of this article was to summarize the use of vortioxetine in clinical studies and assess the efficacy and tolerability. Most of the studies reported a statistically significant efficacy for vortioxetine versus placebo. In addition, vortioxetine showed efficacy in patients with an inadequate response to selective serotonin re-uptake inhibitors (SSRI) or serotonin-noradrenaline re-uptake inhibitors (SNRI) monotherapy and improved cognitive function in patients with MDD. In these studies, vortioxetine was well tolerated – most common observed adverse effect was nausea – and it was not associated with clinically important changes in laboratory test results or vital signs. Vortioxetine showed a relatively low incidence of sexual dysfunction.

scholarly journals An individualized risk prediction model for new-onset, progression and regression of chronic kidney disease in a retrospective cohort of patients with type 2 diabetes under primary care in Hong Kong

2020 ◽  
Author(s):  
Lin Yang ◽  
Tsun Kit Chu ◽  
Jinxiao Lian ◽  
Cheuk Wai Lo ◽  
Shi Zhao ◽  
...  
Keyword(s):  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Electronic Health Records ◽  
Laboratory Test ◽  
List Type ◽  
Test Results ◽  
Health Records ◽  
Laboratory Test Results ◽  
Electronic Health ◽  
New Onset

AbstractObjectivesThis study is aimed to develop and validate a prediction model for multi-state transitions across different stages of chronic kidney disease in patients with type 2 diabetes mellitus under primary care.SettingWe retrieved the anonymized electronic health records of a population based retrospective cohort in Hong Kong.ParticipantsA total of 26,197 patients were included in the analysis.Primary and secondary outcome measuresThe new-onset, progression, and regression of chronic kidney disease were defined by the transitions of four stages that were classified by combining glomerular filtration rate and urine albumin-to-creatinine ratio. We applied a multi-scale multi-state Poisson regression model to estimate the rates of the stage transitions by integrating the baseline demographic characteristics, routine laboratory test results and clinical data from electronic health records.ResultsDuring the mean follow-up time of 1.7 years, there were 2,935 patients newly diagnosed with chronic kidney disease, 1,443 progressed to the next stage and 1,971 regressed into an earlier stage. The models achieved the best performance in predicting the new-onset and progression with the predictors of sex, age, body mass index, systolic blood pressure, diastolic blood pressure, serum creatinine, HbA1c, total cholesterol, LDL, HDL, triglycerides and drug prescriptions.ConclusionsThis study demonstrated that individual risks of new-onset and progression of chronic kidney disease can be predicted from the routine physical and laboratory test results. The individualized prediction curves developed from this study could potentially be applied to routine clinical practices, to facilitate clinical decision making, risk communications with patients and early interventions.Article summaryStrengths of this studyEarly predictions for chronic kidney disease progression and timely intervention is critical for clinical management of patients with diabetes.We successfully developed a multi-scale multi-state Poisson regression models that achieved the satisfactory performance in predicting the new-onset and progression of chronic kidney diseases.The model incorporates the predictors of demographic characteristics, routine laboratory test results and clinical data from electronic health records.The individualized prediction curves could potentially be applied to facilitate clinical decision making, risk communications with patients and early interventions of CKD progression.Limitations of this studyThe cohort has a relatively short follow-up period and the retrospective study design might suffer from report bias and selection bias.

Sign in / Sign up

Export Citation Format

Share Document