Validation of a Major and Clinically Relevant Nonmajor Bleeding Phenotyping Algorithm on Electronic Health Records.

PURPOSE: Bleeding is an important health outcome of interest in epidemiological studies. We aimed to develop and validate rule-based algorithms to identify (1) major bleeding and (2) all clinically relevant bleeding (CRB) (composite of major and all clinically relevant nonmajor bleeding) within real-world electronic healthcare data. METHODS: We took a random sample (n = 1630) of inpatient admissions to Singapore public healthcare institutions in 2019 and 2020, stratifying by hospital and year. We included patients of all age groups, sex, and ethnicities. Presence of major bleeding and CRB were ascertained by two annotators through chart review. A total of 630 and 1000 records were used for algorithm development and validation, respectively. We formulated two algorithms: sensitivity- and positive predictive value (PPV)-optimized algorithms. A combination of hemoglobin test patterns and diagnosis codes were used in the final algorithms. RESULTS: During validation, diagnosis codes alone yielded low sensitivities for major bleeding (0.16) and CRB (0.24), although specificities and PPV were high (>0.97). For major bleeding, the sensitivity-optimized algorithm had much higher sensitivity and negative predictive values (NPVs) (sensitivity = 0.94, NPV = 1.00), however false positive rates were also relatively high (specificity = 0.90, PPV = 0.34). PPV-optimized algorithm had improved specificity and PPV (specificity = 0.96, PPV = 0.52), with little reduction in sensitivity and NPV (sensitivity = 0.88, NPV = 0.99). For CRB events, our algorithms had lower sensitivities (0.50-0.56). CONCLUSIONS: The use of diagnosis codes alone misses many genuine major bleeding events. We have developed major bleeding algorithms with high sensitivities, which can ascertain events within populations of interest.

A risk classification model for prioritising the management of quality issues relating to substandard medicines in Singapore.

BACKGROUND: Monitoring for substandard medicines by regulatory agencies is a key post-market surveillance activity. It is important to prioritise critical product defects for review to ensure that prompt risk mitigation actions are taken. METHODS: A regulatory risk impact prioritisation model for product defects (RISMED) with 11 factors considering the seriousness and extent of impact of a defect was developed. The model generated an overall score that categorised cases into high, medium or low impact. The model was further developed into a statistical risk scoring model (stat-RISMED) using multivariate logistic regression that classified cases into high and non-high impact. Both models were evaluated against an expert-derived gold standard annotation corpus and tested on an independent dataset. RESULTS: Product defect cases received from January 2011 to June 2020 (n = 660) were used to train stat-RISMED and cases from July 2020 to June 2021 (n = 220) for validation. The stat-RISMED identified four factors associated with high impact cases, namely defect classification based on MedDRA-HSA terms, therapeutic indication of product, detectability of defect and whether any overseas regulatory actions were performed. Compared to RISMED, stat-RISMED achieved an improved sensitivity (94% vs 42%) and positive predictive value (47% vs 43%) for the identification of high impact cases, against the gold standard labels. CONCLUSIONS: This study reported characteristics that predicts cases with high impact, and the use of a statistical model to identify such cases. The model may potentially be applied to prioritise product defect issues and strengthen overall surveillance efforts of substandard medicines.

Association of mitochondrial DNA content in peripheral blood with cancer-related fatigue and chemotherapy-related cognitive impairment in early-stage breast cancer patients: a prospective cohort study.

PURPOSE: Cancer-related fatigue (CRF) and chemotherapy-related cognitive impairment (CRCI) are reported to be associated with mitochondrial dysfunction. Hence, mitochondrial DNA (mtDNA) content, a biomarker of mitochondrial dysfunction, is hypothesized to correlate with the onset of CRF and CRCI. This study aims to evaluate the association between peripheral blood mtDNA content reduction and severity of CRF and CRCI in patients receiving chemotherapy. METHODS: This was a prospective cohort study. Early-stage breast cancer patients receiving anthracycline- or taxane-based chemotherapy were recruited. CRF was assessed using MFSI-SF, and CRCI was assessed using FACT-Cog and CANTAB at two timepoints: baseline (T1; prior to treatment) and 6 weeks after initiation of treatment (T2). mtDNA content was measured at both timepoints using real-time quantitative polymerase chain reaction. Multiple logistic regression was utilized to evaluate the association between mtDNA reduction and worsening of CRF and CRCI, adjusting for age, anxiety, insomnia, plasma cytokines concentrations, and other clinically important covariates. RESULTS: A total of 108 patients (age 52.0 ± 9.2 years; 82.4% Chinese; 64.8% receiving anthracycline-based chemotherapy) were recruited. Proportions of patients with worsening of CRF increased from the lower to the upper quartiles of mtDNA reduction (22.2, 33.3, 55.6, and 63.0% in quartiles 1, 2, 3, and 4, respectively, p = 0.001 for trend). Reduction of mtDNA content was significantly greater among those with worsening of CRF and CRCI compared to those without CRF [mean reduction (± SD): 36.5 (46.1) vs. 9.4 (34.5), p < 0.001]. After adjusting for covariates, every 1-unit reduction of the mtDNA content was associated with a 4% increased risk for worsening of CRF (95% CI, 1-6%; p = 0.009). CONCLUSIONS: This is the first study to show that the reduction of mtDNA content in peripheral blood is associated with the onset of CRF in patients receiving chemotherapy. Further validation studies are required to confirm the findings.

Distinct and heterogeneous trajectories of self-perceived cognitive impairment among Asian breast cancer survivors.

OBJECTIVES: Currently, there are no studies that have established the self-perceived cognitive trajectories experienced by breast cancer patients (BCPs) post-chemotherapy. Therefore, we characterized the long-term trajectory of self-perceived cognitive function among Asian early-stage BCPs using the minimal clinically important difference of a subjective measure of cognitive function. METHODS: Early-stage BCPs who received chemotherapy were recruited and assessed at 4 time points: Before chemotherapy initiation (T1), 6 weeks post-chemotherapy initiation (T2), 12 weeks post-chemotherapy initiation (T3), and 15-months post-chemotherapy initiation (T4). All assessments were performed approximately within 2 weeks post-chemotherapy. Subjective and objective cognitive function were assessed using Functional Assessment of Cancer Therapy-Cognitive (version 3) and Headminder™. RESULTS: A total of 166 BCPs were recruited, of whom 131 completed assessment at all time points. Using the minimal clinically important difference of Functional Assessment of Cancer Therapy-Cognitive, 5 distinct cognitive trajectories were established. Of the 131 patients, 70 (53.4%) did not report any clinically significant cognitive impairment. Twenty-one (16.0%) patients reported acute cognitive changes during chemotherapy (T2 and/or T3) but not at T4. Forty patients (30.5%) reported clinically significant cognitive impairment at T4, of whom 18 did not report any cognitive impairment at earlier time points. Fifteen (11.5%) patients reported persistent cognitive impairment throughout all time points, while 7 (5.3%) patients reported intermittent cognitive impairment at T2 and T4 but not at T3. CONCLUSION: This is the first study to establish the existence of heterogeneous cognitive trajectories based on clinically significant thresholds of self-perceived cognitive impairment. The findings have important implications on the window for screening and management of post-chemotherapy cognitive impairment.

A Novel Derivation Predicting Survival After Primary Tumor Resection in Stage IV Colorectal Cancer: Validation of a Prognostic Scoring Model and an Online Calculator to Provide Individualized Survival Estimation.

BACKGROUND: A prognostic scoring model has been devised previously to predict survival following primary tumor resection in patients with metastatic colorectal cancer and unresectable metastases. This has yet to be validated. OBJECTIVE: The main objectives of this study are to validate the proposed prognostic scoring model and create an interactive online calculator to estimate an individual's survival after primary tumor resection. DESIGN: Clinical data and survival outcomes of patients were extracted from a prospectively maintained database. Patients were categorized into good, moderate, or poor survivor groups based on the previously proposed scoring algorithm. Discrimination was assessed and recalibration was performed, with the recalibrated model implemented as an interactive Web application to provide individualized survival probability. SETTINGS: This study was conducted at a tertiary referral center. PATIENTS: The study included 324 consecutive patients with metastatic colorectal carcinoma and unresectable metastases who underwent primary tumor resection between January 2008 and December 2013. MAIN OUTCOME MEASURES: The primary outcome measured was overall survival. RESULTS: Three hundred twenty-four patients were included in the study. Median survival in the good, moderate, and poor prognostic groups was 56.8, 25.7, and 19.9 months (log rank test, p = 0.003). The κ statistic was 0.638 and RD was 0.101. Significant differences in survival were found between the moderate and good prognostic groups (HR, 2.79; 95% CI, 1.51-5.15; p = 0.001) and between poor and good prognostic groups (HR, 4.12; 95% CI, 1.98-8.55; p < 0.001). The model was implemented as an interactive online calculator to provide individualized survival estimation after primary tumor resection (http://bit.ly/Stage4PrognosticScore). LIMITATIONS: Selection bias and single-center data preclude the generalizability of the proposed model. Information regarding the severity or likelihood of developing symptoms from the primary tumor were also not accounted for in the prognostic scoring model proposed. CONCLUSIONS: The prognostic scoring model provides good prognostic stratification of survival after primary tumor resection and may be a useful tool to predict survival after primary tumor resection. See Video Abstract at http://links.lww.com/DCR/A330.

The prognostic performance of adding patient-reported outcomes to the MASCC risk index to identify low-risk febrile neutropenia patients with solid tumors and lymphomas.

PURPOSE: This study aims to develop and validate a prognostic model (PROMASCC) by incorporating the Functional Assessment of Cancer Therapy-Neutropenia (FACT-N) elements, with the Multinational Association of Supportive Care in Cancer (MASCC) risk index, for identifying low-risk patients with febrile neutropenia (FN) for developing serious complications. METHODS: This was a single-center, cross-sectional observational study. Either English or Chinese versions of the FACT-N were administered to the eligible patients according to their language preference within 7 days of FN onset. Univariate analyses and multivariate analyses were performed to construct the PROMASCC model. The prognostic performance was compared between the PROMASCC model and MASCC risk index. The internal validation of the PROMASCC model was examined by bootstrapping technique. RESULTS: From August 2014 to April 2016, a total of 120 eligible patients were included in this study. In the univariate analyses, only the malaise subscale score has been significantly associated with the favorable outcome (without complications) (P = 0.024). Compared to the MASCC risk index, the PROMASCC model has shown advantages on the improved specificity (64.3 vs. 38.1%) and positive predictive value (81.0 vs. 73.7%), lower misclassification rate (24.2 vs. 25.8%), and increased area under receiver-operating characteristic curve (0.732 vs. 0.658). The bootstrapping procedure estimates the optimism-corrected area for the PROMASCC model to be 0.731 (95% CI 0.648 to 0.814). CONCLUSIONS: This study has developed and validated a PROMASCC model and demonstrated that additional measurement on patient's fatigue level could improve the risk stratification of patients with FN.

Acute autoimmune hepatitis following COVID-19 mRNA vaccination: A population-based study using electronic health records in Singapore.

Reports of coronavirus disease 2019 (COVID-19) vaccine-induced autoimmune hepatitis (AIH) have been largely limited to case reports and case series. To further investigate the association between COVID-19 mRNA vaccination and AIH, we conducted a nationwide study using observed-over-expected (O/E) and Self-Controlled Case Series (SCCS) analyses for acute presentations of AIH (AAIH) warranting admission. Patients were included if they had one or more of the following hepatitis-related signs and symptoms (fever, lethargy, jaundice or abdominal pain) reported up to 3 months prior to admission, deranged liver function tests [alanine transaminase (ALT) or aspartate aminotransferase (AST) greater than three times the upper limit of laboratory reference ranges], as well as biopsy results characteristic of AIH or response to steroid treatment for cases which did not undergo biopsy. Seventy-six patients fulfilled our case definition of AAIH within the study period from 1 January 2019 to 28 February 2023, with 6 patients having an estimated onset of AAIH within 42 days of COVID-19 mRNA vaccination. All 6 patients were females aged 40 years and above. In the O/E analysis, the rate ratios of AAIH among females aged 40 years and above in the primary cohort were 1.12 (95% confidence interval (CI) 0.14-9.40) and 1.06 (95% CI 0.24-4.74) in the 21 days and 42 days following vaccination respectively. In the SCCS analysis, we did not observe any statistically significant increase in incidence of AAIH in the 21 and 42 days following COVID-19 mRNA vaccination for both the primary and supplementary cohorts, as well as in the subgroup analysis involving females aged 40 years and above. Our findings suggest that COVID-19 mRNA vaccination does not appear to be associated with increased risk of AAIH requiring admissions in the population, although larger studies are required to confirm these findings.

An updated analysis on myocarditis and pericarditis cases reported following mRNA SARS-CoV-2 vaccination in Singapore.

INTRODUCTION: Messenger ribonucleic acid (mRNA) severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccines have been associated with myocarditis/pericarditis, especially in young males. We evaluated the risk of myocarditis/pericarditis following mRNA vaccines by brand, age, sex and dose number in Singapore. METHODS: Adverse event reports of myocarditis/pericarditis following mRNA vaccines received by the Health Sciences Authority from 30 December 2020 to 25 July 2022 were included, with a data lock on 30 September 2022. Case adjudication was done by an independent panel of cardiologists using the US Centers for Disease Control and Prevention case definition. Reporting rates were compared with expected rates using historical data from 2018 to 2020. RESULTS: Of the 152 adjudicated cases, males comprised 75.0%. The median age was 30 years. Most cases occurred after Dose 2 (49.3%). The median time to onset was 2 days. Reporting rates were highest in males aged 12-17 years for both primary series (11.5 [95% confidence interval [CI] 6.7-18.4] per 100,000 doses, post-Dose 2) and following booster doses (7.1 [95% CI 3.0-13.9] per 100,000 doses). In children aged 5-11 years, myocarditis remained very rare (0.2 per 100,000 doses). The reporting rates for Booster 1 were generally similar or lower than those for Dose 2. CONCLUSIONS: The risk of myocarditis/pericarditis with mRNA vaccines was highest in adolescent males following Dose 2, and this was higher than historically observed background rates. Most cases were clinically mild. The risk of myocarditis should be weighed against the benefits of receiving an mRNA vaccine, keeping in mind that SARS-CoV-2 infections carry substantial risks of myocarditis/pericarditis, as well as the evolving landscape of the disease.

Anaphylaxis post-COVID-19 vaccinations in Singapore.

INTRODUCTION: Anaphylaxis was the first serious adverse event (AE) of special interest surfaced in Singapore following coronavirus disease 2019 (COVID-19) vaccination. Individuals who developed physician-diagnosed severe allergic reactions to the mRNA vaccines would be medically ineligible for mRNA vaccines and offered non-mRNA alternatives. This paper describes anaphylaxis reports received by the Health Sciences Authority (HSA) and presents a review of individuals who received heterologous COVID-19 vaccination. METHODS: Reports of anaphylaxis associated with the COVID-19 vaccines received till 31 July 2022 were reviewed and adjudicated using the Brighton Collaboration case definition criteria by an HSA-appointed expert panel. Additional review was conducted for cases with heterologous vaccination for any subsequent reactions until administration of third dose of COVID-19 vaccines. RESULTS: Among 112 adjudicated anaphylaxis cases, majority occurred in females, adults and persons with allergy histories, which were consistent with global observations. Most cases (71%) occurred within 30 minutes of vaccination. The reporting incidence rates (IRs) of 0.67 and 0.55 per 100,000 administered doses for Comirnaty and Spikevax vaccines, respectively, were comparable with IRs reported overseas, whereas the IRs for non-mRNA vaccines (Sinovac-CoronaVac and Nuvaxovid) were much higher at 4.14 and 29.82 per 100,000 administered doses, respectively, likely due to selection bias. Review of the 20 cases following heterologous vaccination found varying reactions to subsequent vaccinations. CONCLUSION: Anaphylaxis is a rare but serious AE in which outcomes can be mitigated with timely medical intervention. The case review helped to guide vaccination strategies and added to the cumulative knowledge of safety with heterologous vaccination.

Automated Classification of Quality Defect Issues Relating to Substandard Medicines Using a Hybrid Machine Learning and Rule-Based Approach.

BACKGROUND AND OBJECTIVE: Substandard medicines can lead to serious safety issues affecting public health; however, the nature of such issues can be widely heterogeneous. Health product regulators seek to prioritise critical product quality defects for review to ensure that prompt risk mitigation measures are taken. This study aims to classify the nature of issues for substandard medicines using machine learning to augment a risk-based and timely review of cases. METHODS: A combined machine learning algorithm with a keyword-based model was developed to classify quality issues using text relating to substandard medicines (CISTERM). The nature of issues for product defect cases were classified based on Medical Dictionary for Regulatory Activities-Health Sciences Authority (MedDRA-HSA) lowest-level terms. RESULTS: Product defect cases received from January 2010 to December 2021 were used for training (n = 11,082) and for testing (n = 2771). The machine learning model achieved a good recall (precision) of 92% (96%) for 'Product adulterated and/or contains prohibited substance', 86% (90%) for 'Out of specification or out of trend test result' and 90% (91%) for 'Manufacturing non-compliance'. CONCLUSION: Post-market surveillance of substandard medicines remains a key activity for drug regulatory authorities. A combined machine learning algorithm with keyword-based model can help to prioritise the review of product quality defect issues in a timely manner.

Nationwide safety surveillance of COVID-19 mRNA vaccines following primary series and first booster vaccination in Singapore.

Background: The real-world safety profile of COVID-19 mRNA vaccines remains incompletely elucidated. Methods: We performed a nationwide post-market safety surveillance analysis in Singapore, on vacinees aged 5 years and older, through mid-September 2022. Observed-over-expected (O/E) analyses were performed to identify potential safety signals among eight shortlisted adverse events of special interest (AESIs): strokes, cerebral venous thrombosis (CVT), acute myocardial infarction, myocarditis/pericarditis, pulmonary embolism, immune thrombocytopenia, convulsions and appendicitis. Self-controlled case series analyses (SCCS) were performed to validate signals of concern, occurring within 42 days of vaccination. Findings: Elevated risks were observed on O/E analyses for the following AESIs: myocarditis/pericarditis, [rate ratio (RR): 3.66, 95 % confidence interval (95 % CI): 2.71 to 4.94], appendicitis [RR: 1.14 (1.02 to 1.27)] and CVT [RR: 2.11 (1.18 to 3.77)]. SCCS analyses generated corroborative findings: myocarditis/pericarditis, [relative incidence (RI): 6.96 (3.95 to 12.27) at 1 to 7 days post-dose 2], CVT [RI: 4.30 (1.30 to 14.20) at 22 to 42 days post-dose 1] and appendicitis [RI: 1.31 (1.03 to 1.67) at 1 to 7 days post-dose 1]. Booster dose 1 continued to be associated with higher rates of myocarditis/pericarditis on O/E analysis [RR: 2.30, (1.39 to 3.80) and 1.69, (1.11 to 2.59)] at 21- and 42-days post-booster dose 1, respectively. Males aged 12 to 17 exhibited highest risks of both myocarditis/pericarditis [RI: 6.31 (1.36 to 29.3)] and appendicitis [RI: 2.01 (1.12 to 3.64)] after primary vaccination. Similarly, CVT was also predominantly observed in males aged above 50 (11 out of 16 cases), within 42-days of vaccination. Interpretation: Our data suggest that myocarditis/pericarditis, appendicitis and CVT are associated with primary vaccination using COVID-19 mRNA vaccines. Males at specific ages exhibit higher risks for all three AEs identified. The risk of myocarditis/pericarditis continues to be elevated after booster dose 1.

Applying the OMOP Common Data Model to Facilitate Benefit-Risk Assessments of Medicinal Products Using Real-World Data from Singapore and South Korea.

OBJECTIVES: The aim of this study was to characterize the benefits of converting Electronic Medical Records (EMRs) to a common data model (CDM) and to assess the potential of CDM-converted data to rapidly generate insights for benefit-risk assessments in post-market regulatory evaluation and decisions. METHODS: EMRs from January 2013 to December 2016 were mapped onto the Observational Medical Outcomes Partnership-CDM (OMOP-CDM) schema. Vocabulary mappings were applied to convert source data values into OMOP-CDM-endorsed terminologies. Existing analytic codes used in a prior OMOP-CDM drug utilization study were modified to conduct an illustrative analysis of oral anticoagulants used for atrial fibrillation in Singapore and South Korea, resembling a typical benefit-risk assessment. A novel visualization is proposed to represent the comparative effectiveness, safety and utilization of the drugs. RESULTS: Over 90% of records were mapped onto the OMOP-CDM. The CDM data structures and analytic code templates simplified the querying of data for the analysis. In total, 2,419 patients from Singapore and South Korea fulfilled the study criteria, the majority of whom were warfarin users. After 3 months of follow-up, differences in cumulative incidence of bleeding and thromboembolic events were observable via the proposed visualization, surfacing insights as to the agent of preference in a given clinical setting, which may meaningfully inform regulatory decision-making. CONCLUSIONS: While the structure of the OMOP-CDM and its accessory tools facilitate real-world data analysis, extending them to fulfil regulatory analytic purposes in the post-market setting, such as benefit-risk assessments, may require layering on additional analytic tools and visualization techniques.

Combining Machine Learning with a Rule-Based Algorithm to Detect and Identify Related Entities of Documented Adverse Drug Reactions on Hospital Discharge Summaries.

INTRODUCTION: Discharge summaries contain valuable information about adverse drug reactions, but their unstructured nature makes them challenging to analyse and use as a signal source for pharmacovigilance. Machine learning has shown promise in identifying discharge summaries that contain related drug-adverse event pairs but has fared relatively poorer in entity extraction. METHODS: A hybrid model is developed combining rule-based and machine learning algorithms using discharge summaries with the aim of maximising capture of related drug-adverse event pairs. The rule first identifies segments containing adverse event entities within a 100-character distance from a drug term; machine learning subsequently estimates the relatedness of the drug and adverse event entities contained. The approach is validated on four independent datasets that are temporally and geographically separated from model development data. The impact of restricted drug-adverse event pair detection on recall is evaluated by using two of the four validation datasets that do not impose rule-based restrictions to annotations. RESULTS: The hybrid model achieves a recall of 0.80 (fivefold cross validation), 0.80 (temporal) and 0.76 (geographical) on validation using datasets containing only pre-identified target text segments that fulfil the rule-based algorithm criteria. When tested on datasets that additionally contained drug-adverse event pairs not restricted by the rule-based criteria, recall of the model declines to 0.68 and 0.62 on temporally and geographically separated datasets, respectively. CONCLUSIONS: The proposed hybrid model demonstrates reasonable generalisability on external validation. Rule-based restriction of the detection space results in an approximately 12-14% reduction in recall but improves identification of the related drug and adverse event terms.

Analysis of Dual Combination Therapies Used in Treatment of Hypertension in a Multinational Cohort.

Importance: More than 1 billion adults have hypertension globally, of whom 70% cannot achieve their hypertension control goal with monotherapy alone. Data are lacking on clinical use patterns of dual combination therapies prescribed to patients who escalate from monotherapy. Objective: To investigate the most common dual combinations prescribed for treatment escalation in different countries and how treatment use varies by age, sex, and history of cardiovascular disease. Design, Setting, and Participants: This cohort study used data from 11 electronic health record databases that cover 118 million patients across 8 countries and regions between January 2000 and December 2019. Included participants were adult patients (ages ≥18 years) who newly initiated antihypertensive dual combination therapy after escalating from monotherapy. There were 2 databases included for 3 countries: the Iqvia Longitudinal Patient Database (LPD) Australia and Electronic Practice-based Research Network 2019 linked data set from South Western Sydney Local Health District (ePBRN SWSLHD) from Australia, Ajou University School of Medicine (AUSOM) and Kyung Hee University Hospital (KHMC) databases from South Korea, and Khoo Teck Puat Hospital (KTPH) and National University Hospital (NUH) databases from Singapore. Data were analyzed from June 2020 through August 2021. Exposures: Treatment with dual combinations of the 4 most commonly used antihypertensive drug classes (angiotensin-converting enzyme inhibitor [ACEI] or angiotensin receptor blocker [ARB]; calcium channel blocker [CCB]; ß-blocker; and thiazide or thiazide-like diuretic). Main Outcomes and Measures: The proportion of patients receiving each dual combination regimen, overall and by country and demographic subgroup. Results: Among 970 335 patients with hypertension who newly initiated dual combination therapy included in the final analysis, there were 11 494 patients from Australia (including 9291 patients in Australia LPD and 2203 patients in ePBRN SWSLHD), 6980 patients from South Korea (including 6029 patients in Ajou University and 951 patients in KHMC), 2096 patients from Singapore (including 842 patients in KTPH and 1254 patients in NUH), 7008 patients from China, 8544 patients from Taiwan, 103 994 patients from France, 76 082 patients from Italy, and 754 137 patients from the US. The mean (SD) age ranged from 57.6 (14.8) years in China to 67.7 (15.9) years in the Singapore KTPH database, and the proportion of patients by sex ranged from 24 358 (36.9%) women in Italy to 408 964 (54.3%) women in the US. Among 12 dual combinations of antihypertensive drug classes commonly used, there were significant variations in use across country and patient subgroup. For example starting an ACEI or ARB monotherapy followed by a CCB (ie, ACEI or ARB + CCB) was the most commonly prescribed combination in Australia (698 patients in ePBRN SWSLHD [31.7%] and 3842 patients in Australia LPD [41.4%]) and Singapore (216 patients in KTPH [25.7%] and 439 patients in NUH [35.0%]), while in South Korea, CCB + ACEI or ARB (191 patients in KHMC [20.1%] and 1487 patients in Ajou University [24.7%]), CCB + ß-blocker (814 patients in Ajou University [13.5%] and 217 patients in KHMC [22.8%]), and ACEI or ARB + CCB (147 patients in KHMC [15.5%] and 1216 patients in Ajou University [20.2%]) were the 3 most commonly prescribed combinations. The distribution of 12 dual combination therapies were significantly different by age and sex in almost all databases. For example, use of ACEI or ARB + CCB varied from 873 of 3737 patients ages 18 to 64 years (23.4%) to 343 of 2292 patients ages 65 years or older (15.0%) in South Korea's Ajou University database (P for database distribution by age < .001), while use of ACEI or ARB + CCB varied from 2121 of 4718 (44.8%) men to 1721 of 4549 (37.7%) women in Australian LPD (P for drug combination distributions by sex < .001). Conclusions and Relevance: In this study, large variation in the transition between monotherapy and dual combination therapy for hypertension was observed across countries and by demographic group. These findings suggest that future research may be needed to investigate what dual combinations are associated with best outcomes for which patients.

Augmenting Product Defect Surveillance Through Web Crawling and Machine Learning in Singapore.

INTRODUCTION: Substandard medicines are medicines that fail to meet their quality standards and/or specifications. Substandard medicines can lead to serious safety issues affecting public health. With the increasing number of pharmaceuticals and the complexity of the pharmaceutical manufacturing supply chain, monitoring for substandard medicines via manual environmental scanning can be laborious and time consuming. METHODS: A web crawler was developed to automatically detect and extract alerts on substandard medicines published on the Internet by regulatory agencies. The crawled data were labelled as related to substandard medicines or not. An expert-derived keyword-based classification algorithm was compared against machine learning algorithms to identify substandard medicine alerts on two validation datasets (n = 4920 and n = 2458) from a later time period than training data. Models were comparatively assessed for recall, precision and their F1 scores (harmonic mean of precision and recall). RESULTS: The web crawler routinely extracted alerts from the 46 web pages belonging to nine regulatory agencies. From October 2019 to May 2020, 12,156 unique alerts were crawled of which 7378 (60.7%) alerts were set aside for validation and contained 1160 substandard medicine alerts (15.7%). An ensemble approach of combining machine learning and keywords achieved the best recall (94% and 97%), precision (85% and 80%) and F1 scores (89% and 88%) on temporal validation. CONCLUSIONS: Combining robust web crawler programmes with rigorously tested filtering algorithms based on machine learning and keyword models can automate and expand horizon scanning capabilities for issues relating to substandard medicines.

Detecting adverse drug reactions in discharge summaries of electronic medical records using Readpeer.

BACKGROUND: Hospital discharge summaries offer a potentially rich resource to enhance pharmacovigilance efforts to evaluate drug safety in real-world clinical practice. However, it is infeasible for experts to read through all discharge summaries to find cases of drug-adverse event (AE) relations. PURPOSE: The objective of this paper is to develop a natural language processing (NLP) framework to detect drug-AE relations from unstructured hospital discharge summaries. BASIC PROCEDURES: An NLP algorithm was designed using customized dictionaries of drugs, adverse event (AE) terms, and rules based on trigger phrases, negations, fuzzy logic and word distances to recognize drug, AE terms and to detect drug-AE relations. Furthermore, a customized annotation tool was developed to facilitate expert review of discharge summaries from a tertiary hospital in Singapore in 2011. MAIN FINDINGS: A total of 33 trial sets with 50 to 100 records per set were evaluated (1620 discharge summaries) by our algorithm and reviewed by pharmacovigilance experts. After every 6 trial sets, drug and AE dictionaries were updated, and rules were modified to improve the system. Excellent performance was achieved for drug and AE entity recognition with over 92% precision and recall. On the final 6 sets of discharge summaries (600 records), our algorithm achieved 75% precision and 59% recall for identification of valid drug-AE relations. PRINCIPAL CONCLUSIONS: Adverse drug reactions are a significant contributor to health care costs and utilization. Our algorithm is not restricted to particular drugs, drug classes or specific medical specialties, which is an important attribute for a national regulatory authority to carry out comprehensive safety monitoring of drug products. Drug and AE dictionaries may be updated periodically to ensure that the tool remains relevant for performing surveillance activities. The development of the algorithm, and the ease of reviewing and correcting the results of the algorithm as part of an iterative machine learning process, is an important step towards use of hospital discharge summaries for an active pharmacovigilance program.

Optimizing Vancomycin Dosing in Chronic Kidney Disease by Deriving and Implementing a Web-Based Tool Using a Population Pharmacokinetics Analysis.

Background: Chronic kidney disease (CKD) patients requiring intravenous vancomycin bear considerable risks of adverse outcomes both from the infection and vancomycin therapy itself, necessitating especially precise dosing to avoid sub- and supratherapeutic vancomycin exposure. Methods: In this retrospective study, we performed a population pharmacokinetic analysis to construct a vancomycin dose prediction model for CKD patients who do not require renal replacement therapy. The model was externally validated on an independent cohort of patients to assess its prediction accuracy. The pharmacokinetic parameter estimates and the equations were productized into a Web application (VancApp) subsequently implemented in routine care. The association between VancApp-based dosing and time-to-target concentration attainment, 30-day mortality, and nephrotoxicity were assessed postimplementation. Results: The model constructed from an initial cohort (n = 80) revealed a population clearance and volume of distribution of 1.30 L/h and 1.23 L/kg, respectively. External model validation (n = 112) demonstrated a mean absolute prediction error of 1.25 mg/L. Following 4 months of clinical implementation of VancApp as an optional alternative to usual care [VancApp (n = 22) vs. usual care (n = 21)], patients who had received VancApp-based dosing took a shorter time to reach target concentrations (median: 66 vs. 102 h, p = 0.187) and had fewer 30-day mortalities (14% vs. 24%, p = 0.457) compared to usual care. While statistical significance was not achieved, the clinical significance of these findings appear promising. Conclusion: Clinical implementation of a population pharmacokinetic model for vancomycin in CKD can potentially improve dosing precision in CKD and could serve as a practical means to improve vital clinical outcomes.

Prediction of overall survival following colorectal cancer surgery in elderly patients.

BACKGROUND: With advanced age and chronic illness, the life expectancy of a patient with colorectal cancer (CRC) becomes less dependent on the malignant disease and more on their pre-morbid condition. Justifying major surgery for these elderly patients can be challenging. An accurate tool demonstrating post-operative survival probability would be useful for surgeons and their patients. AIM: To integrate clinically significant prognostic factors relevant to elective colorectal surgery in the elderly into a validated pre-operative scoring system. METHODS: In this retrospective cohort study, patients aged 70 and above who underwent surgery for CRC at Singapore General Hospital between 1 January 2005 and 31 December 2012 were identified from a prospectively maintained database. Patients with evidence of metastatic disease, and those who underwent emergency surgery or had surgery for benign colorectal conditions were excluded from the analysis. The primary outcome was overall 3-year overall survival (OS) following surgery. A multivariate model predicting survival was derived and validated against an equivalent external surgical cohort from Kyungpook National University Chilgok Hospital, South Korea. Statistical analyses were performed using Stata/MP Version 15.1. RESULTS: A total of 1267 patients were identified for analysis. The median post-operative length of stay was 8 [interquartile range (IQR) 6-12] d and median follow-up duration was 47 (IQR 19-75) mo. Median OS was 78 (IQR 65-85) mo. Following multivariate analysis, the factors significant for predicting overall mortality were serum albumin < 35 g/dL, serum carcinoembryonic antigen ≥ 20 µg/L, T stage 3 or 4, moderate tumor cell differentiation or worse, mucinous histology, rectal tumors, and pre-existing chronic obstructive lung disease. Advanced age alone was not found to be significant. The Korean cohort consisted of 910 patients. The Singapore cohort exhibited a poorer OS, likely due to a higher proportion of advanced cancers. Despite the clinicopathologic differences, there was successful validation of the model following recalibration. An interactive online calculator was designed to facilitate post-operative survival prediction, available at http://bit.ly/sgh_crc. The main limitation of the study was selection bias, as patients who had undergone surgery would have tended to be physiologically fitter. CONCLUSION: This novel scoring system generates an individualized survival probability following colorectal resection and can assist in the decision-making process. Validation with an external population strengthens the generalizability of this model.

Rectal Cancer Surveillance-Recurrence Patterns and Survival Outcomes from a Cohort Followed up Beyond 10 Years.

AIM: The intensity and duration of surveillance for rectal cancer after surgical resection remain contentious. We evaluated the pattern of recurrences in a rectal cancer cohort followed up beyond 10 years. METHODS: An analysis was performed on a retrospective database of 326 patients with rectal cancer who underwent curative surgical resection from 1999 to 2007. The above study duration was chosen to ensure at least 10 years of follow-up. Data on patient demographics, peri-operative details, and follow-up outcomes were extracted from the database. The pattern of recurrences and investigative modality that detected recurrences was identified. Patients were followed up until either year 2016 or the day of their demise. RESULTS: Two hundred seventeen patients (66.6%) were male and 109 patients (33.3%) female. Median age was 64 years old. Close to a third of the patients received adjuvant therapy (34%). Among the 326 patients studied, 29.8% of (97/326) patients developed recurrence. 7.7% (25/326) had loco-regional recurrence while 22.1% (72/326) had distant metastasis. Median time to recurrence was 16 months (4-83) and 18 months (3-81), respectively. Computed tomography scan was the best modality to detect both loco-regional and distant recurrences (48% in loco-regional and 41.7% in distant metastasis). The most common site of distant metastasis is the lung (34.7%). The salvage rate for loco-regional and distant recurrences was 52 and 12.5%, respectively. CONCLUSION: The predominant pattern of recurrence in rectal cancer is distant disease. Surveillance regimes may need to be altered to increase early detection of distant metastases.

HbA1c variability in type 2 diabetes is associated with the occurrence of new-onset albuminuria within three years.

AIMS: To evaluate the association between HbA1c coefficient of variation (HbA1c-CV) and 3-year new-onset albuminuria risk. METHODS: A retrospective cohort study involving 716 normoalbuminuric type 2 diabetes patients was conducted between 2010 and 2014. HbA1c-CV was used to categorize patients into low, moderate or high variability groups. Multivariate logistic models were constructed and validated. Integrated discrimination (IDI) and net reclassification (NRI) improvement indices were used to quantify the added predictive value of HbA1c-CV. RESULTS: The mean age of our cohort was 56.1±12.9years with a baseline HbA1c of 8.3±1.3%. Over 3-years of follow-up, 35.2% (n=252) developed albuminuria. An incremental risk of albuminuria was observed with moderate (6.68-13.43%) and high (above 13.44%) HbA1c-CV categories demonstrating adjusted odds ratios of 1.63 (1.12-2.38) and 3.80 (2.10-6.97) for 3-year new-onset albuminuria, respectively. Including HbA1c-CV for 3-year new-onset albuminuria prediction improved model discrimination (IDI: 0.023, NRI: 0.293, p<0.05). The final model had a C-statistic of 0.760±0.018 on validation. CONCLUSION: HbA1c-CV improves 3-year prediction of new-onset albuminuria. Together with mean HbA1c, baseline urine albumin-to-creatinine ratio and presence of hypertension, accurate 3-year new-onset albuminuria prediction may be possible.