Patient and Clinician Perceptions of the Pulse Oximeter in a Remote Monitoring Setting for COVID-19: Qualitative Study.

BACKGROUND: As a response to the COVID-19 pandemic, the Sydney Local Health District in New South Wales, Australia, launched the rpavirtual program, the first full-scale virtual hospital in Australia, to remotely monitor and follow up stable patients with COVID-19. As part of the intervention, a pulse oximeter wearable device was delivered to patients to monitor their oxygen saturation levels, a critical indicator of COVID-19 patient deterioration. Understanding users' perceptions toward the device is fundamental to assessing its usability and acceptability and contributing to the effectiveness of the intervention, but no research to date has explored the user experience of the pulse oximeter for remote monitoring in this setting. OBJECTIVE: This study aimed to explore the use, performance, and acceptability of the pulse oximeter by clinicians and patients in rpavirtual during COVID-19. METHODS: Semistructured interviews and usability testing were conducted. Stable adult patients with COVID-19 (aged ≥18 years) who used the pulse oximeter and were monitored by rpavirtual, and rpavirtual clinicians monitoring these patients were interviewed. Clinicians could be nurses, doctors, or staff who were part of the team that assisted patients with the use of the pulse oximeter. Usability testing was conducted with patients who had the pulse oximeter when they were contacted. Interviews were coded using the Theoretical Framework of Acceptability. Usability testing was conducted using a think-aloud protocol. Data were collected until saturation was reached. RESULTS: Twenty-one patients (average age 51, SD 13 years) and 15 clinicians (average age 41, SD 11 years) completed the interview. Eight patients (average age 51, SD 13 years) completed the usability testing. All participants liked the device and thought it was easy to use. They also had a good understanding of how to use the device and the device's purpose. Patients' age and device use-related characteristics (eg, the warmth of hands and hand steadiness) were identified by users as factors negatively impacting the accurate use of the pulse oximeter. CONCLUSIONS: Patients and clinicians had very positive perceptions of the pulse oximeter for COVID-19 remote monitoring, indicating high acceptability and usability of the device. However, factors that may impact the accuracy of the device should be considered when delivering interventions using the pulse oximeter for remote monitoring. Targeted instructions about the use of the device may be necessary for specific populations (eg, older people and patients unfamiliar with technology). Further research should focus on the integration of the pulse oximeter data into electronic medical records for real-time and secure patient monitoring.

Process mining for healthcare: Characteristics and challenges.

Process mining techniques can be used to analyse business processes using the data logged during their execution. These techniques are leveraged in a wide range of domains, including healthcare, where it focuses mainly on the analysis of diagnostic, treatment, and organisational processes. Despite the huge amount of data generated in hospitals by staff and machinery involved in healthcare processes, there is no evidence of a systematic uptake of process mining beyond targeted case studies in a research context. When developing and using process mining in healthcare, distinguishing characteristics of healthcare processes such as their variability and patient-centred focus require targeted attention. Against this background, the Process-Oriented Data Science in Healthcare Alliance has been established to propagate the research and application of techniques targeting the data-driven improvement of healthcare processes. This paper, an initiative of the alliance, presents the distinguishing characteristics of the healthcare domain that need to be considered to successfully use process mining, as well as open challenges that need to be addressed by the community in the future.

Usability evaluation of an integrated electronic medication management system implemented in an oncology setting using the unified theory of the acceptance and use of technology.

BACKGROUND: Medication management processes in an Oncology setting are complex and difficult to examine in isolation from interrelated processes and contextual factors. This qualitative study aims to evaluate the usability of an Electronic Medication Management System (EMMS) implemented in a specialised oncology unit using the Unified Theory of Acceptance and Use of Technology (UTAUT) framework. METHODS: The study was conducted in a 12-bed outpatient Oncology unit of a major teaching hospital 6 months following implementation of a commercial EMMS. In-depth semi-structured interviews were conducted with doctors, nurses and pharmacists using the system to assess usability. The UTAUT framework was used to analyse the results, which facilitated evaluation of interrelated aspects and provided a structured summary of user experience and usability factors. RESULTS: Direct cross-comparison between user groups illustrated that doctors and pharmacists were generally satisfied with the facilitating conditions (hardware and training), but had divergent perceptions of performance (automation, standardised protocols and communication and documented) and effort (mental and temporal demand) expectancy. In counterpoint, nurses were generally satisfied across all constructs. Prior experience using an alternative EMMS influenced performance and effort expectancy and was related to early dissatisfaction with the EMMS. Furthermore, whilst not originally designed for the healthcare setting, the flexibility of the UTAUT allowed for translation to the hospital environment. CONCLUSION: Nurses demonstrated overall satisfaction with the EMMS, whilst doctors and pharmacists perceived usability problems, particularly related to restricted automaticity and system complexity, which hindered perceived EMMS success. The study demonstrates the feasibility and utility of the UTAUT framework to evaluate usability of an EMMS for multiple user groups in the Oncology setting.

Ensemble learning for prediction of the bioactivity capacity of herbal medicines from chromatographic fingerprints.

BACKGROUND: Recent quality control of complex mixtures, including herbal medicines, is not limited to chemical chromatographic definition of one or two selected compounds; multivariate linear regression methods with dimension reduction or regularisation have been used to predict the bioactivity capacity from the chromatographic fingerprints of the herbal extracts. The challenge of this type of analysis requires a multi-dimensional approach at two levels: firstly each herb comprises complex mixtures of active and non-active chemical components; and secondly there are many factors relating to the growth, production, and processing of the herbal products. All these factors result in the significantly diverse concentrations of bioactive compounds in the herbal products. Therefore, it is imminent to have a predictive model with better generalisation that can accurately predict the bioactivity capacity of samples when only the chemical fingerprints data are available. RESULTS: In this study, the algorithm of Stacking Multivariate Linear Regression (SMLR) and a few other commonly used chemometric approaches were evaluated. They were to predict the Cluster of Differentiation 80 (CD80) expression bioactivity of a commonly used herb, Astragali Radix (AR), from the corresponding chemical chromatographic fingerprints. SMLR provides a superior prediction accuracy in comparison with the other multivariate linear regression methods of PCR, PLSR, OPLS and EN in terms of MSEtest and the goodness of prediction of test samples. CONCLUSIONS: SMLR is a better platform than some multivariate linear regression methods. The first advantage of SMLR is that it has better generalisation to predict the bioactivity capacity of herbal medicines from their chromatographic fingerprints. Future studies should aim to further improve the SMLR algorithm. The second advantage of SMLR is that single chemical compounds can be effectively identified as highly bioactive components which demands further CD80 bioactivity confirmation..

An improved independent component analysis model for 3D chromatogram separation and its solution by multi-areas genetic algorithm.

BACKGROUND: The 3D chromatogram generated by High Performance Liquid Chromatography-Diode Array Detector (HPLC-DAD) has been researched widely in the field of herbal medicine, grape wine, agriculture, petroleum and so on. Currently, most of the methods used for separating a 3D chromatogram need to know the compounds' number in advance, which could be impossible especially when the compounds are complex or white noise exist. New method which extracts compounds from 3D chromatogram directly is needed. METHODS: In this paper, a new separation model named parallel Independent Component Analysis constrained by Reference Curve (pICARC) was proposed to transform the separation problem to a multi-parameter optimization issue. It was not necessary to know the number of compounds in the optimization. In order to find all the solutions, an algorithm named multi-areas Genetic Algorithm (mGA) was proposed, where multiple areas of candidate solutions were constructed according to the fitness and distances among the chromosomes. RESULTS: Simulations and experiments on a real life HPLC-DAD data set were used to demonstrate our method and its effectiveness. Through simulations, it can be seen that our method can separate 3D chromatogram to chromatogram peaks and spectra successfully even when they severely overlapped. It is also shown by the experiments that our method is effective to solve real HPLC-DAD data set. CONCLUSIONS: Our method can separate 3D chromatogram successfully without knowing the compounds' number in advance, which is fast and effective.

Understanding the factors influencing acceptability of AI in medical imaging domains among healthcare professionals: A scoping review.

BACKGROUND: Artificial intelligence (AI) technology has the potential to transform medical practice within the medical imaging industry and materially improve productivity and patient outcomes. However, low acceptability of AI as a digital healthcare intervention among medical professionals threatens to undermine user uptake levels, hinder meaningful and optimal value-added engagement, and ultimately prevent these promising benefits from being realised. Understanding the factors underpinning AI acceptability will be vital for medical institutions to pinpoint areas of deficiency and improvement within their AI implementation strategies. This scoping review aims to survey the literature to provide a comprehensive summary of the key factors influencing AI acceptability among healthcare professionals in medical imaging domains and the different approaches which have been taken to investigate them. METHODS: A systematic literature search was performed across five academic databases including Medline, Cochrane Library, Web of Science, Compendex, and Scopus from January 2013 to September 2023. This was done in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. Overall, 31 articles were deemed appropriate for inclusion in the scoping review. RESULTS: The literature has converged towards three overarching categories of factors underpinning AI acceptability including: user factors involving trust, system understanding, AI literacy, and technology receptiveness; system usage factors entailing value proposition, self-efficacy, burden, and workflow integration; and socio-organisational-cultural factors encompassing social influence, organisational readiness, ethicality, and perceived threat to professional identity. Yet, numerous studies have overlooked a meaningful subset of these factors that are integral to the use of medical AI systems such as the impact on clinical workflow practices, trust based on perceived risk and safety, and compatibility with the norms of medical professions. This is attributable to reliance on theoretical frameworks or ad-hoc approaches which do not explicitly account for healthcare-specific factors, the novelties of AI as software as a medical device (SaMD), and the nuances of human-AI interaction from the perspective of medical professionals rather than lay consumer or business end users. CONCLUSION: This is the first scoping review to survey the health informatics literature around the key factors influencing the acceptability of AI as a digital healthcare intervention in medical imaging contexts. The factors identified in this review suggest that existing theoretical frameworks used to study AI acceptability need to be modified to better capture the nuances of AI deployment in healthcare contexts where the user is a healthcare professional influenced by expert knowledge and disciplinary norms. Increasing AI acceptability among medical professionals will critically require designing human-centred AI systems which go beyond high algorithmic performance to consider accessibility to users with varying degrees of AI literacy, clinical workflow practices, the institutional and deployment context, and the cultural, ethical, and safety norms of healthcare professions. As investment into AI for healthcare increases, it would be valuable to conduct a systematic review and meta-analysis of the causal contribution of these factors to achieving high levels of AI acceptability among medical professionals.

The Impact of an Electronic Medication Management System on Medication Deviations on Admission and Discharge from Hospital.

Medication errors at transition of care remain a concerning issue. In recent times, the use of integrated electronic medication management systems (EMMS) has caused a reduction in medication errors, but its effectiveness in reducing medication deviations at transition of care has not been studied in hospital-wide settings in Australia. The aim of this study is to assess medication deviations, such as omissions and mismatches, pre-EMMS and post-EMMS implementation at transition of care across a hospital. In this study, patient records were reviewed retrospectively to identify medication deviations (medication omissions and medication mismatches) at admission and discharge from hospital. A total of 400 patient records were reviewed (200 patients in the pre-EMMS and 200 patients in the post-EMMS group). Out of 400 patients, 112 in the pre-EMMS group and 134 patients in post-EMMS group met the inclusion criteria and were included in the analysis. A total of 105 out of 246 patients (42.7%) had any medication deviations on their medications. In the pre-EMMS group, 59 out of 112 (52.7%) patients had any deviations on their medications compared to 46 out of 134 patients (34.3%) from the post-EMMS group (p = 0.004). The proportion of patients with medication omitted from inpatient orders was 36.6% in the pre-EMMS cohort vs. 22.4% in the post-EMMS cohort (p = 0.014). Additionally, the proportion of patients with mismatches in medications on the inpatient charts compared to their medication history was 4.5% in the pre-EMMS group compared to 0% in the post-EMMS group (p = 0.019). Similarly, the proportion of patients with medications omitted from their discharge summary was 23.2% in the pre-EMMS group vs. 12.7% in the post-EMMS group (p = 0.03). Our study demonstrates a reduction in medication deviations after the implementation of the EMMS in hospital settings.

Benchmarking the diagnostic test accuracy of certified AI products for screening pulmonary tuberculosis in digital chest radiographs: Preliminary evidence from a rapid review and meta-analysis.

BACKGROUND AND OBJECTIVE: The global market for AI systems used in lung tuberculosis (TB) detection has expanded significantly in recent years. Verifying their performance across diverse settings is crucial before medical organisations can invest in them and pursue safe, wide-scale deployment. The goal of this research was to synthesise the clinical evidence for the diagnostic accuracy of certified AI products designed for screening TB in chest X-rays (CXRs) compared to a microbiological reference standard. METHODS: Four databases were searched between June to September 2022. Data concerning study methodology, system characteristics, and diagnostic accuracy metrics was extracted and summarised. Study bias was evaluated using QUADAS-2 and by examining sources of funding. Forest plots for diagnostic odds ratio (DOR) and summary receiver operating characteristic (SROC) curves were constructed for the AI products individually and collectively. RESULTS: 10 out of 3642 studies satisfied the review criteria however only 8 were subject to meta-analysis following bias assessment. Three AI products were evaluated with a 95 % confidence interval producing the following pooled estimates for accuracy rankings: qXR v2 (sensitivity of 0.944 [0.887-0.973], specificity of 0.692 [0.549-0.805], DOR of 3.63 [3.17-4.09], Lunit INSIGHT CXR v3.1 (sensitivity of 0.853 [0.787-0.901], specificity of 0.646 [0.627-0.665], DOR of 2.37 [1.96-2.78]), and CAD4TB v3.07 (sensitivity of 0.917 [0.848-0.956], specificity of 0.371 [0.336-0.408], DOR of 1.91 [1.4-2.47]). Overall, the products had a sensitivity of 0.903 (0.859-0.934), specificity of 0.526 (0.409-0.641), and DOR of 2.31 (1.78-2.84). CONCLUSION: Current publicly available evidence indicates considerable variability in the diagnostic accuracy of available AI products although overall they have high sensitivity and modest specificity which is improving with time. These preliminary results are limited by the small number of studies and poor coverage for low TB burden settings. More research is needed to expand the clinical evidence base for the performance of AI products.

Understanding unintended consequences for EMR: a literature review.

While Electronic Medical Records (EMR) have been hailed as an important step for advancing healthcare, a number of studies have noted that its introduction also brings unintended consequences to healthcare organisations. This means that introducing EMR to key stakeholders such as clinicians, healthcare administrators, as well as to the overall healthcare organisations, may not be as straightforward as we have hoped for. There has been some empirical work and systematic reviews specifically addressing the unintended consequences for EMR. Given the complexity of these issues, continued effort to investigate them is critical. This paper first proposes an integration and systematisation of the existing literature on the unintended consequences of EMR (including its various definitions and classifications), and then provides insights for dealing with these issues, including mitigation strategies for addressing these issues.

Patient and clinician use characteristics and perceptions of pulse oximeter use: A scoping review.

BACKGROUND AND OBJECTIVES: The need to monitor patients outside of a formal clinical setting, such as a hospital or ambulatory care facility, has become increasingly important since COVID-19. It introduces significant challenges to ensure accurate and timely measurements, maintain strong patient engagement, and operationalise data for clinical decision-making. Remote Patient Monitoring (RPM) devices like the pulse oximeter help mitigate these difficulties, however, practical approaches to successfully integrate this technology into existing patient-clinician interactions that ensure the delivery of safe and effective care are vital. The objective of this scoping review was to synthesise existing literature to provide an overview of the variety of user perceptions associated with pulse oximeter devices, which may impact patients' and clinicians' acceptance of the devices in a RPM context. METHODS: A search over three databases was conducted between April 2021 - June 2021 using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Review (PRISMA-ScR) guidelines. A total of 16 articles were included in this scoping review. RESULTS: Results indicate there has been an increase in use of pulse oximeters across hospital and community settings for continuous vital signs monitoring and remote monitoring of patients over time. Research in this area is shifting towards increasing accessibility of care through the development and implementation of telehealth systems and phone oximeters. Aspects of pulse oximeter UX most frequently investigated are usability and acceptability, however, these terms are often undefined, or definitions vary across studies. Perceived effectiveness, opportunity costs, and attitude towards use remain unexplored areas of UX. Overall, patients and clinicians view the pulse oximeter positively and find it user-friendly. A high level of learnability was found for the device and additional benefits included increasing patient self-efficacy and clinician motivation to work. However, issues getting an accurate reading due to device usability are still experienced by some patients and clinicians. CONCLUSION: This scoping review is the first to summarise user perceptions of the pulse oximeter in a healthcare context. It showed that both patients and clinicians hold positive perceptions of the pulse oximeter and important factors to consider in designing user-focused services include ease-of-use and wearability of devices; context of use including user's prior health and IT knowledge; attitude towards use and perceived effectiveness; impact on user motivation and self-efficacy; and finally, potential user costs like inconvenience or increased anxiety. With the rapid increase in research studies examining pulse oximeter use for RPM since COVID-19, a systematic review is warranted as the next step to consolidate evidence and investigate the impact of these factors on pulse oximeter acceptance and effectiveness.

Medication safety improvements during care transitions in an Australian intensive care unit following implementation of an electronic medication management system.

BACKGROUND: For patients requiring admission to the Intensive Care Unit (ICU), transfers of care (TOC) during admission to and discharge from the ICU are particularly high-risk periods for medication errors. In the Australian setting, commonly general wards and the ICU do not share an integrated Electronic Medical ecord (EMR) and specifically an Electronic Medication Management System (EMMS) as part of the EMR. PURPOSE: To evaluate the effect of a hospital wide integrated EMMS on medication error rates during ICU admission and at TOC. METHOD: A 6-month historical control study was performed before and after implementation of the EMMS in the ICU of a tertiary hospital. Prescribing errors detected by pharmacists in the study period were divided into phase 1, (pre-EMMS, 6months), phase 2 (3 months post implementation after shakedown stage) and phase 3 (next 3 months of post implementation). They were categorized as prescribing error types under system or clinical intervention. Chi square statistics and interrupted time series analysis were used to determine if there was significant change in the proportion of patients who had an error at TOC during each phase. Logistics regression was used to determine the relationship between the dependent (error type) and the independent variable (study phase) for errors that occurred during TOC. RESULTS: Errors occurred during TOC in 42 %, 64 % and 19 % of patients in phase 1, 2 and 3 respectively. There was a significant decline in the proportion of patients with an error between phase 1 and 3 (p < 0.01). During a patient's ICU admission, at least one medication error occurred in 28.3 %, 62.6 % and 25.1 % in phase 1, 2 and 3 respectively. Besides procedural errors, the likelihood of an error occurring was greatest in phase 1, compared to phase 2 and 3 across system-related error categories. CONCLUSION: Medication errors during TOC reduced following implementation of the integrated ICU EMMS. EMMS safety features facilitated reduced system related prescribing errors as well as the severity of errors made.

Machine Learning Clustering for Blood Pressure Variability Applied to Systolic Blood Pressure Intervention Trial (SPRINT) and the Hong Kong Community Cohort.

Visit-to-visit blood pressure variability (BPV) has been shown to be a predictor of cardiovascular disease. We aimed to classify the BPV levels using different machine learning algorithms. Visit-to-visit blood pressure readings were extracted from the SPRINT study in the United States and eHealth cohort in Hong Kong (HK cohort). Patients were clustered into low, medium, and high BPV levels with the traditional quantile clustering and 5 machine learning algorithms including K-means. Clustering methods were assessed by Stability Index. Similarities were assessed by Davies-Bouldin Index and Silhouette Index. Cox proportional hazard regression models were fitted to compare the risk of myocardial infarction, stroke, and heart failure. A total of 8133 participants had average blood pressure measurement 14.7 times in 3.28 years in SPRINT and 1094 participants who had average blood pressure measurement 165.4 times in 1.37 years in HK cohort. Quantile clustering assigned one-third participants as high BPV level, but machine learning methods only assigned 10% to 27%. Quantile clustering is the most stable method (stability index: 0.982 in the SPRINT and 0.948 in the HK cohort) with some levels of clustering similarities (Davies-Bouldin Index: 0.752 and 0.764, respectively). K-means clustering is the most stable across the machine learning algorithms (stability index: 0.975 and 0.911, respectively) with the lowest clustering similarities (Davies-Bouldin Index: 0.653 and 0.680, respectively). One out of 7 in the population was classified with high BPV level, who showed to have higher risk of stroke and heart failure. Machine learning methods can improve BPV classification for better prediction of cardiovascular diseases.

A Deep Learning-Based Approach for Gait Analysis in Huntington Disease.

Huntington Disease (HD) is a genetic neurodegenerative disease which leads to involuntary movements and impaired balance. These changes have been quantified using footstep pressure sensor mats such as Protokinetics' Zeno Walkway. Drawing from distances between recorded footsteps, patients' disease severity have been measured in terms of high level gait characteristics such as gait width and stride length. However, little attention has been paid to the pressure data collected during formation of individual footsteps. This work investigates the potential of classifying patient disease severity based on individual footstep pressure data using deep learning techniques. Using the Motor Subscale of the Unified HD Rating Scale (UHDRS) as the gold standard, our experiments showed that using VGG16 and similar modules can achieve classification accuracy of 89%. Image pre-processing are key steps for better model performance. This classification accuracy is compared to results based on 3D CNN (82%) and SVM (86.9%).

The Digitization of the ICU: An Evaluation of Usability and Hospital-Wide Acceptability.

This paper explores the impact of an electronic medication management system (EMMS) on users in an intensive care unit using the Unified Theory and Use of Technology constructs. It also explores the impact of having a consistent EMMS hospital wide, as it is the first Australian hospital to implement the same EMMS hospital wide. The research model was evaluated using survey data from 100 nurses, doctors and pharmacists both within the ICU and externally, to assess the usability and acceptability of the system. Results showed that performance expectancy, effort expectancy, social influence and facilitating condition all correlate with overall user satisfaction. Overall, teams external to the ICU are in strong favor of its implementation whist user acceptance from within the ICU itself is poor.

Socialising Health Burden Through Different Network Topologies: A Simulation Study.

An aging population and the expectation of premium quality health services combined with the increasing economic burden of the healthcare system requires a paradigm shift toward patient oriented healthcare. The guardian angel theory described by Szolovits [1] explores the notion of enlisting patients as primary providers of information and motivation to patients with similar clinical history through social connections. In this study, an agent based model was developed to simulate to explore how individuals are affected through their levels of intrinsic positivity. Ring, point-to-point (paired buddy), and random networks were modelled, with individuals able to send messages to each other given their levels of variables positivity and motivation. Of the 3 modelled networks it is apparent that the ring network provides the most equal, collective improvement in positivity and motivation for all users. Further study into other network topologies should be undertaken in the future.

A Conceptual Measurement Model for eHealth Readiness: a Team Based Perspective.

Despite the shift towards collaborative healthcare and the increase in the use of eHealth technologies, there does not currently exist a model for the measurement of eHealth readiness in interdisciplinary healthcare teams. This research aims to address this gap in the literature through the development of a three phase methodology incorporating qualitative and quantitative methods. We propose a conceptual measurement model consisting of operationalized themes affecting readiness across four factors: (i) Organizational Capabilities, (ii) Team Capabilities, (iii) Patient Capabilities, and (iv) Technology Capabilities. The creation of this model will allow for the measurement of the readiness of interdisciplinary healthcare teams to use eHealth technologies to improve patient outcomes.

E-Health Readiness for Teams: A Comprehensive Conceptual Model.

The use of information technology in the delivery of healthcare services is pervasive but faces many barriers. We propose a four-factor comprehensive conceptual model to provide a measure of interdisciplinary healthcare readiness to provide healthcare services using e-health. We incorporate factors from a series of focus group studies and the wider literature and construct a conceptual model. We utilise the Delphi method to establish content validity and use a series of Q sorts for initial construct validity. This model will improve patient outcomes through healthcare teams identifying barriers to using e-health effectively and efficiently.

Enabler for Interdisciplinary eHealthcare: A Qualitative Study.

The complex relations between Health Technologies and clinical practices have been the focus of intensive research in recent years. This research represents a shift towards a holistic view where evaluation of health technologies is linked to organisational practices. In this paper, we address the gaps in existing literature regarding the holistic evaluation of e-health in clinical practice. We report the results from a qualitative study conducted to gain insight into e-health in practice within an interdisciplinary healthcare domain. Findings from this qualitative study, provides the foundation for the creation of a generic measurement model that allows for the comparative analysis of health technologies and assist in the decision-making of its stakeholders.

Prediction of Radix Astragali Immunomodulatory Effect of CD80 Expression from Chromatograms by Quantitative Pattern-Activity Relationship.

The current use of a single chemical component as the representative quality control marker of herbal food supplement is inadequate. In this CD80-Quantitative-Pattern-Activity-Relationship (QPAR) study, we built a bioactivity predictive model that can be applicable for complex mixtures. Through integrating the chemical fingerprinting profiles of the immunomodulating herb Radix Astragali (RA) extracts, and their related biological data of immunological marker CD80 expression on dendritic cells, a chemometric model using the Elastic Net Partial Least Square (EN-PLS) algorithm was established. The EN-PLS algorithm increased the biological predictive capability with lower value of RMSEP (11.66) and higher values of Rp2 (0.55) when compared to the standard PLS model. This CD80-QPAR platform provides a useful predictive model for unknown RA extract's bioactivities using the chemical fingerprint inputs. Furthermore, this bioactivity prediction platform facilitates identification of key bioactivity-related chemical components within complex mixtures for future drug discovery and understanding of the batch-to-batch consistency for quality clinical trials.

An Ensemble Approach for Record Matching in Data Linkage.

OBJECTIVES: To develop and test an optimal ensemble configuration of two complementary probabilistic data matching techniques namely Fellegi-Sunter (FS) and Jaro-Wrinkler (JW) with the goal of improving record matching accuracy. METHODS: Experiments and comparative analyses were carried out to compare matching performance amongst the ensemble configurations combining FS and JW against the two techniques independently. RESULTS: Our results show that an improvement can be achieved when FS technique is applied to the remaining unsure and unmatched records after the JW technique has been applied. DISCUSSION: Whilst all data matching techniques rely on the quality of a diverse set of demographic data, FS technique focuses on the aggregating matching accuracy from a number of useful variables and JW looks closer into matching the data content (spelling in this case) of each field. Hence, these two techniques are shown to be complementary. In addition, the sequence of applying these two techniques is critical. CONCLUSION: We have demonstrated a useful ensemble approach that has potential to improve data matching accuracy, particularly when the number of demographic variables is limited. This ensemble technique is particularly useful when there are multiple acceptable spellings in the fields, such as names and addresses.