Importance of sex and gender factors for COVID-19 infection and hospitalisation: a sex-stratified analysis using machine learning in UK Biobank data

Biomedical data analytics for better patient outcomes

Medical professionals today have access to immense amounts of data, which enables them to make decisions that enhance patient care and treatment efficacy. This innovative strategy can improve global health care by bridging the divide between clinical practice and medical research. This paper reviews biomedical developments aimed at improving patient outcomes by addressing three main questions regarding techniques, data sources and challenges. The review includes peer-reviewed articles from 2018 to 2023, found via systematic searches in PubMed, Scopus and Google Scholar. The results show diverse disease-specific applications. Challenges such as data quality and ethics are discussed, underscoring data analytics' potential for patient-focused health care. The review concludes that successful implementation requires addressing gaps, collaboration and innovation in biomedical science and data analytics.

The association of combinations of social factors and SARs-CoV-2 infection: A retrospective population-based cohort study in Ontario, 2020-2021

Objective

The COVID-19 pandemic highlighted and exacerbated health inequities worldwide. While several studies have examined the impact of individual social factors on COVID infection, our objective was to examine how interactions of social factors were associated with the risk of testing positive for SARS-CoV-2 during the first two years of the pandemic.

Study design and setting

We conducted an observational cohort study using linked health administrative data for Ontarians tested for SARS-CoV-2 between January 1st, 2020, and December 31st, 2021. We constructed multivariable models to examine the association between SARS-CoV-2 positivity and key variables including immigration status (immigrants vs. other Ontarians), and neighbourhood variables for household size, income, essential worker status, and visible minority status. We report main and interaction effects using odds ratios and predicted probabilities, with age and sex controlled in all models.

Results

Of 6,575,523 Ontarians in the cohort, 88.5 % tested negative, and 11.5 % tested positive for SARS-CoV-2. In all models, immigrants and those living in neighbourhoods with large average household sizes had greater odds of testing positive for SARS-CoV-2. The strength of these associations increased with increasing levels of neighbourhood marginalization for income, essential worker proportion and visible minority proportion. We observed little change in the probability of testing positive across neighbourhood income quintiles among other Ontarians who live in neighbourhoods with smaller households, but a large change in probability among other Ontarians who live in neighbourhoods with larger households.

Conclusion

Our study found that SARS-CoV-2 positivity was greater among people with certain combinations of social factors, but in all cases the probability of testing positive was consistently greater for immigrants than for other Ontarians. Examining interactions of social factors can provide a more nuanced and more comprehensive understanding of health inequity than examining factors separately.

Big data and AI for gender equality in health: bias is a big challenge

Artificial intelligence and machine learning are rapidly evolving fields that have the potential to transform women's health by improving diagnostic accuracy, personalizing treatment plans, and building predictive models of disease progression leading to preventive care. Three categories of women's health issues are discussed where machine learning can facilitate accessible, affordable, personalized, and evidence-based healthcare. In this perspective, firstly the promise of big data and machine learning applications in the context of women's health is elaborated. Despite these promises, machine learning applications are not widely adapted in clinical care due to many issues including ethical concerns, patient privacy, informed consent, algorithmic biases, data quality and availability, and education and training of health care professionals. In the medical field, discrimination against women has a long history. Machine learning implicitly carries biases in the data. Thus, despite the fact that machine learning has the potential to improve some aspects of women's health, it can also reinforce sex and gender biases. Advanced machine learning tools blindly integrated without properly understanding and correcting for socio-cultural sex and gender biased practices and policies is therefore unlikely to result in sex and gender equality in health.

The SIMI Gender '5 Ws' Rule for the integration of sex and gender-related variables in clinical studies towards internal medicine equitable research

Biological sex and sociocultural gender matter when it comes to health and diseases. They have been both proposed as the undeniable gateways towards a personalized approach in care delivery. The Gender Working Group of the Italian Society of Internal Medicine (SIMI) was funded in 2019 with the aim of promoting good practice in the integration of sex and gender domains in clinical studies. Starting from a narrative literature review and based on regular meetings which led to a shared virtual discussion during the national SIMI congress in 2021, the members of the WG provided a core operational framework to be applied by internal medicine (IM) specialists to understand and implement their daily activity as researchers and clinicians. The SIMI Gender '5 Ws' Rule for clinical studies has been conceptualized as follows: Who (Clinical Internal Medicine Scientists and Practitioners), What (Gender-related Variables-Gender Core Dataset), Where (Clinical Studies/Translational Research), When (Every Time It Makes Sense) and Why (Explanatory Power of Gender and Opportunities). In particular, the gender core dataset was identified by the following domains (variables to collect accordingly): relations (marital status, social support, discrimination); roles (occupation, caregiver status, household responsibility, primary earner, household dimension); institutionalized gender (education level, personal income, living in rural vs urban areas); and gender identity (validated questionnaires on personality traits). The SIMI Gender '5 Ws' Rule is a simple and easy conceptual framework that will guide IM for the design and analysis of clinical studies.

Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population

The rising incidence of fatty liver disease (FLD) poses a health challenge, and is expected to be the leading global cause of liver-related morbidity and mortality in the near future. Early case identification is crucial for disease intervention. A retrospective cross-sectional study was performed on 31,930 Taiwanese subjects (25,544 training and 6386 testing sets) who had received health check-ups and abdominal ultrasounds in Changhua Christian Hospital from January 2009 to January 2019. Clinical and laboratory factors were included for analysis by different machine-learning algorithms. In addition, the performance of the machine-learning algorithms was compared with that of the fatty liver index (FLI). Totally, 6658/25,544 (26.1%) and 1647/6386 (25.8%) subjects had moderate-to-severe liver disease in the training and testing sets, respectively. Five machine-learning models were examined and demonstrated exemplary performance in predicting FLD. Among these models, the xgBoost model revealed the highest area under the receiver operating characteristic (AUROC) (0.882), accuracy (0.833), F1 score (0.829), sensitivity (0.833), and specificity (0.683) compared with those of neural network, logistic regression, random forest, and support vector machine-learning models. The xgBoost, neural network, and logistic regression models had a significantly higher AUROC than that of FLI. Body mass index was the most important feature to predict FLD according to the feature ranking scores. The xgBoost model had the best overall prediction ability for diagnosing FLD in our study. Machine-learning algorithms provide considerable benefits for screening candidates with FLD.