Healthcare Big Data in Hong Kong: Development and Implementation of Artificial Intelligence-Enhanced Predictive Models for Risk Stratification

Tse, Gary; Lee, Quinncy; Chou, Oscar Hou In; Chung, Cheuk To; Lee, Sharen; Chan, Jeffrey Shi Kai; Li, Guoliang; Kaur, Narinder; Roever, Leonardo; Liu, Haipeng; Liu, Tong; Zhou, Jiandong

doi:10.1016/j.cpcardiol.2023.102168

Cited by 11 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, we have developed CVD risk models for diabetes mellitus 37-39 , which captured data from both primary and secondary care settings. The first version, PowerAI-Diabetes, third-in-world, Chinese-specific AI-driven predictive model for predicting diabetic complications and first-in-world to incorporate lipid and glycaemic variability with AI, was recently developed 40 . We are incorporating new information such as treatment effects of first- and second-line anti-diabetic medications, such as metformin, sulphonylureas 41,42 , SGLT2 inhibitors, DPP4 inhibitors, GLP1 agonists 43,44 , which would impact on the risks of CVD and other adverse events.…”

Section: Discussionmentioning

confidence: 99%

ChineseCVD: first-in-world, web-based, Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects

Chang,

Tse,

Lee

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundWeb-based risk prediction tools for cardiovascular diseases are crucial for providing rapid risk estimates for busy clinicians, but there is none available specifically for Chinese subjects. This study developed ChineseCVD, first-in-world web-based Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects.MethodsAdult patients attending government-funded family medicine clinics in Hong Kong between 1stJanuary 2000 and 31stDecember 2003 were included. The primary outcome was major adverse cardiovascular events (MACE) defined as a composite of myocardial infarction, heart failure, transient ischaemic attacks/ischaemic strokes, and cardiovascular mortality.ResultsA total of 155,066 patients were used as the derivation cohort. Over a median follow-up of 16.1 (11.6-17.8) years, 31,061 (20.44%) had MACE. Cox regression identified male gender, age, comorbidities, cardiovascular medications, systolic and diastolic blood pressure, and laboratory test results (neutrophil-lymphocyte ratio, creatinine, ALP, AST, ALT, HbA1c, fasting glucose, triglyceride, LDL and HDL) as significant predictors of the above outcomes. ChineseCVD further incorporates the impact of smoking status, COVID-19 infection, number of COVID-19 vaccination doses, and modifier effects of newest medication classes of PCSK9i and SGLT2i. The calculator enables clinicians to demonstrate to patients how risks vary with different medications.ConclusionsThe ChineseCVD risk calculator enables rapid web-based risk assessment for adverse cardiovascular outcomes, thereby facilitating clinical decision-making at the bedside or in the clinic.

show abstract

Section: Discussionmentioning

confidence: 99%

ChineseCVD: first-in-world, web-based, Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects

Chang,

Tse,

Lee

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, it is essential to conduct future studies with more detailed data to further explore this aspect. Finally, future work should consider building personalized predictive models specifically for PCa patients for better risk stratification, as performed for other diseases 41 …”

Section: Discussionmentioning

confidence: 99%

“…Finally, future work should consider building personalized predictive models specifically for PCa patients for better risk stratification, as performed for other diseases. 41 …”

Section: Discussionmentioning

confidence: 99%

Statin use and mortality risk in Asian patients with prostate cancer receiving androgen deprivation therapy: A population‐based cohort study

Lee,

Chan,

Hui

et al. 2023

Cancer Medicine

Self Cite

View full text Add to dashboard Cite

BackgroundThis study aimed to examine the associations between the use of statins concurrent with androgen deprivation therapy (ADT) and the risks of mortality in Asian patients diagnosed with prostate cancer (PCa).MethodsAdult patients (≥18 years old) diagnosed with PCa who were receiving any form of ADT and were being treated at public hospitals in Hong Kong from December 1999 to March 2021 were retrospectively identified, with follow‐up conducted until September 2021. Patients who had received medical castration for <180 days without subsequent bilateral orchidectomy, those who had used statins concurrently with ADT for <180 days, and those with missing baseline total cholesterol levels were excluded. Statin users were defined as individuals who had used statins for ≥180 days concurrent with ADT, while non‐users were those who had not used any statins. PCa‐related mortality was the primary outcome, while all‐cause mortality served as the secondary outcome. Inverse probability treatment weighting was employed to balance the covariates.ResultsA total of 4920 patients were included, consisting of 2578 statin users and 2342 non‐users (mean age 76.1 ± 8.2 years). Over a mean follow‐up period of 4.2 ± 3.3 years, it was observed that statin users had significantly lower risks of both PCa‐related mortality (weighted hazard ratio [wHR] 0.56 [95% confidence interval (CI) 0.48, 0.65], p < 0.001) and all‐cause mortality (wHR 0.57 [95% CI 0.51, 0.63], p < 0.001), regardless of the type of ADT used. Notably, these associations were more pronounced among patients with less advanced PCa, as indicated by the absence of androgen receptor antagonist or chemotherapy usage (p value for interaction <0.001 for both outcomes).Conclusion(s)The use of statins concurrent with ADT was associated with reduced mortality risks among Asian patients with PCa. These findings suggest the need for additional research to explore the potential role of statins in the treatment of PCa patients.

show abstract

“…Big data analytical techniques, such as statistical analysis, data mining, machine learning, and deep learning, have developed significantly in recent years, attracting the attention of researchers and scientists in a wide range of applications [ 1 – 3 ]. Making decisions based on concrete evidence via a big data platform is crucial and has a significant impact on precision medicine and personalized therapy implementation [ 4 – 7 ]. The field of anesthesia poses challenges in terms of both technical competence and decision-making, the latter being frequently influenced by time constraints and continuously changing clinical conditions [ 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Anesthesia decision analysis using a cloud-based big data platform

Zhang,

Li,

Jing

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

Big data technologies have proliferated since the dawn of the cloud-computing era. Traditional data storage, extraction, transformation, and analysis technologies have thus become unsuitable for the large volume, diversity, high processing speed, and low value density of big data in medical strategies, which require the development of novel big data application technologies. In this regard, we investigated the most recent big data platform breakthroughs in anesthesiology and designed an anesthesia decision model based on a cloud system for storing and analyzing massive amounts of data from anesthetic records. The presented Anesthesia Decision Analysis Platform performs distributed computing on medical records via several programming tools, and provides services such as keyword search, data filtering, and basic statistics to reduce inaccurate and subjective judgments by decision-makers. Importantly, it can potentially to improve anesthetic strategy and create individualized anesthesia decisions, lowering the likelihood of perioperative complications.

show abstract

Healthcare Big Data in Hong Kong: Development and Implementation of Artificial Intelligence-Enhanced Predictive Models for Risk Stratification

Cited by 11 publications

References 26 publications

ChineseCVD: first-in-world, web-based, Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects

ChineseCVD: first-in-world, web-based, Chinese-specific Cardiovascular Risk Calculator incorporating long COVID, COVID-19 vaccination, SGLT2i and PCSK9i treatment effects

Statin use and mortality risk in Asian patients with prostate cancer receiving androgen deprivation therapy: A population‐based cohort study

Anesthesia decision analysis using a cloud-based big data platform

Contact Info

Product

Resources

About