IncidencePrevalence: An R package to calculate population-level incidence rates and prevalence using the OMOP common data model.

PURPOSE: Real-world data (RWD) offers a valuable resource for generating population-level disease epidemiology metrics. We aimed to develop a well-tested and user-friendly R package to compute incidence rates and prevalence in data mapped to the observational medical outcomes partnership (OMOP) common data model (CDM). MATERIALS AND METHODS: We created IncidencePrevalence, an R package to support the analysis of population-level incidence rates and point- and period-prevalence in OMOP-formatted data. On top of unit testing, we assessed the face validity of the package. To do so, we calculated incidence rates of COVID-19 using RWD from Spain (SIDIAP) and the United Kingdom (CPRD Aurum), and replicated two previously published studies using data from the Netherlands (IPCI) and the United Kingdom (CPRD Gold). We compared the obtained results to those previously published, and measured execution times by running a benchmark analysis across databases. RESULTS: IncidencePrevalence achieved high agreement to previously published data in CPRD Gold and IPCI, and showed good performance across databases. For COVID-19, incidence calculated by the package was similar to public data after the first-wave of the pandemic. CONCLUSION: For data mapped to the OMOP CDM, the IncidencePrevalence R package can support descriptive epidemiological research. It enables reliable estimation of incidence and prevalence from large real-world data sets. It represents a simple, but extendable, analytical framework to generate estimates in a reproducible and timely manner.

Trends of use and characterisation of anti-dementia drugs users: a large multinational-network population-based study.

BACKGROUND: An updated time-trend analysis of anti-dementia drugs (ADDs) is lacking. The aim of this study is to assess the incident rate (IR) of ADD in individuals with dementia using real-world data. SETTING: Primary care data (country/database) from the UK/CPRD-GOLD (2007-20), Spain/SIDIAP (2010-20) and the Netherlands/IPCI (2008-20), standardised to a common data model. METHODS: Cohort study. Participants: dementia patients ≥40 years old with ≥1 year of previous data. Follow-up: until the end of the study period, transfer out of the catchment area, death or incident prescription of rivastigmine, galantamine, donepezil or memantine. Other variables: age/sex, type of dementia, comorbidities. Statistics: overall and yearly age/sex IR, with 95% confidence interval, per 100,000 person-years (IR per 105 PY (95%CI)). RESULTS: We identified a total of (incident anti-dementia users/dementia patients) 41,024/110,642 in UK/CPRD-GOLD, 51,667/134,927 in Spain/SIDIAP and 2,088/17,559 in the Netherlands/IPCI.In the UK, IR (per 105 PY (95%CI)) of ADD decreased from 2007 (30,829 (28,891-32,862)) to 2010 (17,793 (17,083-18,524)), then increased up to 2019 (31,601 (30,483 to 32,749)) and decrease in 2020 (24,067 (23,021-25,148)). In Spain, IR (per 105 PY (95%CI)) of ADD decreased by 72% from 2010 (51,003 (49,199-52,855)) to 2020 (14,571 (14,109-15,043)). In the Netherlands, IR (per 105 PY (95%CI)) of ADD decreased by 77% from 2009 (21,151 (14,967-29,031)) to 2020 (4763 (4176-5409)). Subjects aged ≥65-79 years and men (in the UK and the Netherlands) initiated more frequently an ADD. CONCLUSIONS: Treatment of dementia remains highly heterogeneous. Further consensus in the pharmacological management of patients living with dementia is urgently needed.

Artificial intelligence for dementia-Applied models and digital health.

INTRODUCTION: The use of applied modeling in dementia risk prediction, diagnosis, and prognostics will have substantial public health benefits, particularly as "deep phenotyping" cohorts with multi-omics health data become available. METHODS: This narrative review synthesizes understanding of applied models and digital health technologies, in terms of dementia risk prediction, diagnostic discrimination, prognosis, and progression. Machine learning approaches show evidence of improved predictive power compared to standard clinical risk scores in predicting dementia, and the potential to decompose large numbers of variables into relatively few critical predictors. RESULTS: This review focuses on key areas of emerging promise including: emphasis on easier, more transparent data sharing and cohort access; integration of high-throughput biomarker and electronic health record data into modeling; and progressing beyond the primary prediction of dementia to secondary outcomes, for example, treatment response and physical health. DISCUSSION: Such approaches will benefit also from improvements in remote data measurement, whether cognitive (e.g., online), or naturalistic (e.g., watch-based accelerometry).

Artificial intelligence for dementia prevention.

INTRODUCTION: A wide range of modifiable risk factors for dementia have been identified. Considerable debate remains about these risk factors, possible interactions between them or with genetic risk, and causality, and how they can help in clinical trial recruitment and drug development. Artificial intelligence (AI) and machine learning (ML) may refine understanding. METHODS: ML approaches are being developed in dementia prevention. We discuss exemplar uses and evaluate the current applications and limitations in the dementia prevention field. RESULTS: Risk-profiling tools may help identify high-risk populations for clinical trials; however, their performance needs improvement. New risk-profiling and trial-recruitment tools underpinned by ML models may be effective in reducing costs and improving future trials. ML can inform drug-repurposing efforts and prioritization of disease-modifying therapeutics. DISCUSSION: ML is not yet widely used but has considerable potential to enhance precision in dementia prevention. HIGHLIGHTS: Artificial intelligence (AI) is not widely used in the dementia prevention field. Risk-profiling tools are not used in clinical practice. Causal insights are needed to understand risk factors over the lifespan. AI will help personalize risk-management tools for dementia prevention. AI could target specific patient groups that will benefit most for clinical trials.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review.

INTRODUCTION: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia. METHODS: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases. RESULTS: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort. DISCUSSION: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice. HIGHLIGHTS: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Understanding the inter-relationships of type 2 diabetes and hypertension with brain and cognitive health: A UK Biobank study.

AIM: To understand the impact of diabetes and co-morbid hypertension on cognitive and brain health. MATERIALS AND METHODS: We used data from the UK Biobank cohort consisting of ~500 000 individuals aged 40 to 69 years. Our outcomes included brain structural magnetic resonance imaging variables and cognitive function tests in a maximum of 38 918 individuals. We firstly tested associations with all outcomes between those with diabetes (n = 2043) and without (n = 36 875) and, secondly, compared those with co-morbid diabetes/hypertension (n = 1283) with those with only diabetes (n = 760), hypertension (n = 9649) and neither disease (n = 27 226). Our analytical approach comprised linear regression models, with adjustment for a range of demographic and health factors. Standardized betas are reported. RESULTS: Those with diabetes had worse brain and cognitive health for the majority of neuroimaging and cognitive measures, with the exception of g fractional anisotropy (white matter integrity), amygdala, pairs matching and tower rearranging. Compared with individuals with co-morbid diabetes and hypertension, those with only hypertension had better brain health overall, with the largest difference observed in the pallidum (ß = .189, 95% CI = 0.241; 0.137), while those with only diabetes differed in total grey volume (ß = .150, 95% CI = 0.122; 0.179). Individuals with only diabetes had better verbal and numeric reasoning (ß = .129, 95% CI = 0.077; 0.261), whereas those with only hypertension performed better on the symbol-digit substitution task (ß = .117, 95% CI = 0.048; 0.186). CONCLUSIONS: Individuals with co-morbid diabetes and hypertension have worse brain and cognitive health compared with those with only one of these diseases. These findings potentially suggest that prevention of both diabetes and hypertension may delay changes in brain structure, as well as cognitive decline and dementia diagnosis.

Risk of depression, suicide and psychosis with hydroxychloroquine treatment for rheumatoid arthritis: a multinational network cohort study.

OBJECTIVES: Concern has been raised in the rheumatology community regarding recent regulatory warnings that HCQ used in the coronavirus disease 2019 pandemic could cause acute psychiatric events. We aimed to study whether there is risk of incident depression, suicidal ideation or psychosis associated with HCQ as used for RA. METHODS: We performed a new-user cohort study using claims and electronic medical records from 10 sources and 3 countries (Germany, UK and USA). RA patients ≥18 years of age and initiating HCQ were compared with those initiating SSZ (active comparator) and followed up in the short (30 days) and long term (on treatment). Study outcomes included depression, suicide/suicidal ideation and hospitalization for psychosis. Propensity score stratification and calibration using negative control outcomes were used to address confounding. Cox models were fitted to estimate database-specific calibrated hazard ratios (HRs), with estimates pooled where I2 <40%. RESULTS: A total of 918 144 and 290 383 users of HCQ and SSZ, respectively, were included. No consistent risk of psychiatric events was observed with short-term HCQ (compared with SSZ) use, with meta-analytic HRs of 0.96 (95% CI 0.79, 1.16) for depression, 0.94 (95% CI 0.49, 1.77) for suicide/suicidal ideation and 1.03 (95% CI 0.66, 1.60) for psychosis. No consistent long-term risk was seen, with meta-analytic HRs of 0.94 (95% CI 0.71, 1.26) for depression, 0.77 (95% CI 0.56, 1.07) for suicide/suicidal ideation and 0.99 (95% CI 0.72, 1.35) for psychosis. CONCLUSION: HCQ as used to treat RA does not appear to increase the risk of depression, suicide/suicidal ideation or psychosis compared with SSZ. No effects were seen in the short or long term. Use at a higher dose or for different indications needs further investigation. TRIAL REGISTRATION: Registered with EU PAS (reference no. EUPAS34497; http://www.encepp.eu/encepp/viewResource.htm? id=34498). The full study protocol and analysis source code can be found at https://github.com/ohdsi-studies/Covid19EstimationHydroxychloroquine2.

Comparing multilabel classification methods for provisional biopharmaceutics class prediction.

The biopharmaceutical classification system (BCS) is now well established and utilized for the development and biowaivers of immediate oral dosage forms. The prediction of BCS class can be carried out using multilabel classification. Unlike single label classification, multilabel classification methods predict more than one class label at the same time. This paper compares two multilabel methods, binary relevance and classifier chain, for provisional BCS class prediction. Large data sets of permeability and solubility of drug and drug-like compounds were obtained from the literature and were used to build models using decision trees. The separate permeability and solubility models were validated, and a BCS validation set of 127 compounds where both permeability and solubility were known was used to compare the two aforementioned multilabel classification methods for provisional BCS class prediction. Overall, the results indicate that the classifier chain method, which takes into account label interactions, performed better compared to the binary relevance method. This work offers a comparison of multilabel methods and shows the potential of the classifier chain multilabel method for improved biological property predictions for use in drug discovery and development.

Optimising the use of electronic medical records for large scale research in psychiatry.

The explosion and abundance of digital data could facilitate large-scale research for psychiatry and mental health. Research using so-called "real world data"-such as electronic medical/health records-can be resource-efficient, facilitate rapid hypothesis generation and testing, complement existing evidence (e.g. from trials and evidence-synthesis) and may enable a route to translate evidence into clinically effective, outcomes-driven care for patient populations that may be under-represented. However, the interpretation and processing of real-world data sources is complex because the clinically important 'signal' is often contained in both structured and unstructured (narrative or "free-text") data. Techniques for extracting meaningful information (signal) from unstructured text exist and have advanced the re-use of routinely collected clinical data, but these techniques require cautious evaluation. In this paper, we survey the opportunities, risks and progress made in the use of electronic medical record (real-world) data for psychiatric research.

Collateral effects of the COVID-19 pandemic on endocrine treatments for breast and prostate cancer in the UK: a cohort study.

Background: The COVID-19 pandemic affected cancer screening, diagnosis and treatments. Many surgeries were substituted with bridging therapies during the initial lockdown, yet consideration of treatment side effects and their management was not a priority. Objectives: To examine how the changing social restrictions imposed by the pandemic affected incidence and trends of endocrine treatment prescriptions in newly diagnosed (incident) breast and prostate cancer patients and, secondarily, endocrine treatment-related outcomes (including bisphosphonate prescriptions, osteopenia and osteoporosis), in UK clinical practice from March 2020 to June 2022. Design: Population-based cohort study using UK primary care Clinical Practice Research Datalink GOLD database. Methods: There were 13,701 newly diagnosed breast cancer patients and 12,221 prostate cancer patients with ⩾1-year data availability since diagnosis between January 2017 and June 2022. Incidence rates (IR) and incidence rate ratios (IRR) were calculated across multiple time periods before and after lockdown to examine the impact of changing social restrictions on endocrine treatments and treatment-related outcomes, including osteopenia, osteoporosis and bisphosphonate prescriptions. Results: In breast cancer patients, aromatase inhibitor (AI) prescriptions increased during lockdown versus pre-pandemic [IRR: 1.22 (95% confidence interval (CI): 1.11-1.34)], followed by a decrease post-first lockdown [IRR: 0.79 (95% CI: 0.69-0.89)]. In prostate cancer patients, first-generation antiandrogen prescriptions increased versus pre-pandemic [IRR: 1.23 (95% CI: 1.08-1.4)]. For breast cancer patients on AIs, diagnoses of osteopenia, osteoporosis and bisphosphonate prescriptions were reduced across all lockdown periods versus pre-pandemic (IRR range: 0.31-0.62). Conclusion: During the first 2 years of the pandemic, newly diagnosed breast and prostate cancer patients were prescribed more endocrine treatments compared to pre-pandemic due to restrictions on hospital procedures replacing surgeries with bridging therapies. But breast cancer patients had fewer diagnoses of osteopenia and osteoporosis and bisphosphonate prescriptions. These patients should be followed up in the coming years for signs of bone thinning. Evidence of poorer management of treatment-related side effects will help assess resource allocation for patients at high risk for bone-related complications.

Effects of the COVID-19 pandemic on hormone treatments for breast and prostate cancer in the UK: implications for bone health The COVID-19 pandemic has had a big impact on health, going beyond just causing illness. One area it has influenced is how patients with breast cancer or prostate cancer are treated. Surgeries and radiotherapies were delayed from the first lockdown as hospitals reduced non-covid related procedures. Some patients with breast or prostate cancer were instead given some medications to help stop their cancers from growing until they were able to have surgery or radiotherapy. These medications (called endocrine treatments) have important side effects, such as conditions that affect the bones. Patients on these medications should be monitored by doctors for signs of bone thinning and should, in some cases, be given other medications to help stop this happening. This study used doctors' records from more than 5 million people to find out whether the pandemic affected the number of endocrine medications being prescribed in patients with breast or prostate cancer, and also looked at the number of these patients that were diagnosed with conditions that affect their bones and whether they were given medications that could protect their bone health. We found that during the first lockdown, patients with breast cancer or prostate cancer had more of some types of endocrine treatments compared to before the lockdown. However, they had fewer diagnoses of conditions related to bone health and fewer medications to protect their bones. It is possible that appointments and tests that are usually carried out to diagnose conditions relating to bone health were not performed in the months after the first lockdown, and so these conditions were underdiagnosed. The use of medications to protect their bones was also reduced, likely because this was not considered a priority during the pandemic. This highlights that such patients should be followed up in the coming years for signs of bone thinning, given the relatively poorer management of these side effects in these people after the pandemic.

The impact of the UK COVID-19 lockdown on the screening, diagnostics and incidence of breast, colorectal, lung and prostate cancer in the UK: a population-based cohort study.

Introduction: The COVID-19 pandemic had collateral effects on many health systems. Cancer screening and diagnostic tests were postponed, resulting in delays in diagnosis and treatment. This study assessed the impact of the pandemic on screening, diagnostics and incidence of breast, colorectal, lung, and prostate cancer; and whether rates returned to pre-pandemic levels by December, 2021. Methods: This is a cohort study of electronic health records from the United Kingdom (UK) primary care Clinical Practice Research Datalink (CPRD) GOLD database. The study included individuals registered with CPRD GOLD between January, 2017 and December, 2021, with at least 365 days of clinical history. The study focused on screening, diagnostic tests, referrals and diagnoses of first-ever breast, colorectal, lung, and prostate cancer. Incidence rates (IR) were stratified by age, sex, and region, and incidence rate ratios (IRR) were calculated to compare rates during and after lockdown with rates before lockdown. Forecasted rates were estimated using negative binomial regression models. Results: Among 5,191,650 eligible participants, the first lockdown resulted in reduced screening and diagnostic tests for all cancers, which remained dramatically reduced across the whole observation period for almost all tests investigated. There were significant IRR reductions in breast (0.69 [95% CI: 0.63-0.74]), colorectal (0.74 [95% CI: 0.67-0.81]), and prostate (0.71 [95% CI: 0.66-0.78]) cancer diagnoses. IRR reductions for lung cancer were non-significant (0.92 [95% CI: 0.84-1.01]). Extrapolating to the entire UK population, an estimated 18,000 breast, 13,000 colorectal, 10,000 lung, and 21,000 prostate cancer diagnoses were missed from March, 2020 to December, 2021. Discussion: The UK COVID-19 lockdown had a substantial impact on cancer screening, diagnostic tests, referrals, and diagnoses. Incidence rates remained significantly lower than pre-pandemic levels for breast and prostate cancers and associated tests by December, 2021. Delays in diagnosis are likely to have adverse consequences on cancer stage, treatment initiation, mortality rates, and years of life lost. Urgent strategies are needed to identify undiagnosed cases and address the long-term implications of delayed diagnoses.

Tracing Tomorrow: young people's preferences and values related to use of personal sensing to predict mental health, using a digital game methodology.

BACKGROUND: Use of personal sensing to predict mental health risk has sparked interest in adolescent psychiatry, offering a potential tool for targeted early intervention. OBJECTIVES: We investigated the preferences and values of UK adolescents with regard to use of digital sensing information, including social media and internet searching behaviour. We also investigated the impact of risk information on adolescents' self-understanding. METHODS: Following a Design Bioethics approach, we created and disseminated a purpose-built digital game (www.tracingtomorrow.org) that immersed the player-character in a fictional scenario in which they received a risk assessment for depression Data were collected through game choices across relevant scenarios, with decision-making supported through clickable information points. FINDINGS: The game was played by 7337 UK adolescents aged 16-18 years. Most participants were willing to personally communicate mental health risk information to their parents or best friend. The acceptability of school involvement in risk predictions based on digital traces was mixed, due mainly to privacy concerns. Most participants indicated that risk information could negatively impact their academic self-understanding. Participants overwhelmingly preferred individual face-to-face over digital options for support. CONCLUSIONS: The potential of digital phenotyping in supporting early intervention in mental health can only be fulfilled if data are collected, communicated and actioned in ways that are trustworthy, relevant and acceptable to young people. CLINICAL IMPLICATIONS: To minimise the risk of ethical harms in real-world applications of preventive psychiatric technologies, it is essential to investigate young people's values and preferences as part of design and implementation processes.

Anemia, hemoglobin concentration and cognitive function in the Longitudinal Ageing Study in India-Harmonized Diagnostic Assessment of Dementia (LASI-DAD) and the Health and Retirement Study.

Background: In India, anemia is widely researched in children and women of reproductive age, however, studies in older populations are lacking. Given the adverse effect of anemia on cognitive function and dementia this older population group warrants further study. The Longitudinal Ageing Study in India - Harmonized Diagnostic Assessment of Dementia (LASI-DAD) dataset contains detailed measures to allow a better understanding of anaemia as a potential risk factor for dementia. Method: 2,758 respondents from the LASI-DAD cohort, aged 60 or older, had a complete blood count measured from venous blood as well as cognitive function tests including episodic memory, executive function and verbal fluency. Linear regression was used to test the associations between blood measures (including anemia and hemoglobin concentration (g/dL)) with 11 cognitive domains. All models were adjusted for age and gender with the full model containing adjustments for rural location, years of education, smoking, region, BMI and population weights.Results from LASI-DAD were validated using the USA-based Health and Retirement Study (HRS) cohort (n=5720) to replicate associations between blood cell measures and global cognition. Results: In LASI-DAD, we showed an association between anemia and poor memory (p=0.0054). We found a positive association between hemoglobin concentration and ten cognitive domains tested (ß=0.041-0.071, p<0.05). The strongest association with hemoglobin was identified for memory-based tests (immediate episodic, delayed episodic and broad domain memory, ß=0.061-0.071, p<0.005). Positive associations were also shown between the general cognitive score and the other red blood count tests including mean corpuscular hemoglobin concentration (MCHC, ß=0.06, p=0.0001) and red cell distribution width (RDW, ß =-0.11, p<0.0001). In the HRS cohort, positive associations were replicated between general cognitive score and other blood count tests (Red Blood Cell, MCHC and RDW, p<0.05). Conclusion: We have established in a large South Asian population that low hemoglobin and anaemia are associated with low cognitive function, therefore indicating that anaemia could be an important modifiable risk factor. We have validated this result in an external cohort demonstrating both the variability of this risk factor cross-nationally and its generalizable association with cognitive outcomes.

The Impact of the COVID-19 Pandemic on Incidence and Short-Term Survival for Common Solid Tumours in the United Kingdom: A Cohort Analysis.

Purpose: The COVID-19 pandemic profoundly affected healthcare systems and patients. There is a need to comprehend the collateral effects of the pandemic on non-communicable diseases. We examined the impact of the pandemic on short-term survival for common solid tumours, including breast, colorectal, head and neck, liver, lung, oesophageal, pancreatic, prostate, and stomach cancer in the UK. Methods: This was a population-based cohort study of electronic health records from the UK primary care Clinical Practice Research Datalink GOLD database. In sum, 12,259,744 eligible patients aged ≥18 years with ≥1 year's history identified from January 2000 to December 2022 were included. We estimated age-standardised incidence and short-term (one- and two-year) survival for several common cancers from 2000 to 2019 (in five-year strata) and compared these to 2020-2022 using the Kaplan-Meier method. Results: Incidence decreased for most cancers in 2020 and recovered to different extents in 2021-2022. Short-term survival improved for most cancers between 2000 and 2019, but then declined, albeit minimally, for those diagnosed in 2020-2022. This was most pronounced for colorectal cancer, with one-year survival falling from 78.8% (95% CI 78%-79.6%) in 2015-2019 to 77% (95% CI 75.6-78.3%) for those diagnosed in 2020-2022. Conclusion: Short-term survival for many cancers was impacted, albeit minimally, by the pandemic in the UK, with reductions in survivorship from colorectal cancer equivalent to returning to the mortality seen in the first decade of the 2000s. While data on longer-term survival are needed to fully comprehend the impact of COVID-19 on cancer care, our findings illustrate the need for an urgent and substantial commitment from the UK National Health Service to address the existing backlog in cancer screening and diagnostic procedures to improve cancer care and mortality.

Coping with unbalanced class data sets in oral absorption models.

Class imbalance occurs frequently in drug discovery data sets. In oral absorption data sets, in the literature, there are considerably more highly absorbed compounds compared to poorly absorbed compounds. This produces models that are biased toward highly absorbed compounds which lack generalization to industry settings where more early stage drug candidates are poorly absorbed. This paper presents two strategies to cope with unbalanced class data sets: undersampling the majority high absorption class and misclassification costs using classification decision trees. The published data set by Hou et al. [J. Chem. Inf. Model.2007, 47, 208-218], which contained percentage human intestinal absorption of 645 drug and drug-like compounds, was used for the development and validation of classification trees using classification and regression tree (C&RT) analysis. The results indicate that undersampling the majority class, highly absorbed compounds, leads to a balanced distribution (50:50) training set which can achieve better accuracies for poorly absorbed compounds, whereas the biased training set achieved higher accuracies for highly absorbed compounds. The use of misclassification costs resulted in improved class predictions, when applied to reduce false positives or false negatives. Moreover, it was shown that the classical overall accuracy measure used in many publications is particularly misleading in the case of unbalanced data sets and more appropriate measures presented here may be used for a more realistic assessment of the classification models' performance. Thus, these strategies offer improvements to cope with unbalanced class data sets to obtain classification models applicable in industry.

Pre-processing feature selection for improved C&RT models for oral absorption.

There are currently thousands of molecular descriptors that can be calculated to represent a chemical compound. Utilizing all molecular descriptors in Quantitative Structure-Activity Relationships (QSAR) modeling can result in overfitting, decreased interpretability, and thus reduced model performance. Feature selection methods can overcome some of these problems by drastically reducing the number of molecular descriptors and selecting the molecular descriptors relevant to the property being predicted. In particular, decision trees such as C&RT, although they have an embedded feature selection algorithm, can be inadequate since further down the tree there are fewer compounds available for descriptor selection, and therefore descriptors may be selected which are not optimal. In this work we compare two broad approaches for feature selection: (1) a "two-stage" feature selection procedure, where a pre-processing feature selection method selects a subset of descriptors, and then classification and regression trees (C&RT) selects descriptors from this subset to build a decision tree; (2) a "one-stage" approach where C&RT is used as the only feature selection technique. These methods were applied in order to improve prediction accuracy of QSAR models for oral absorption. Additionally, this work utilizes misclassification costs in model building to overcome the problem of the biased oral absorption data sets with more highly absorbed than poorly absorbed compounds. In most cases the two-stage feature selection with pre-processing approach had higher model accuracy compared with the one-stage approach. Using the top 20 molecular descriptors from the random forest predictor importance method gave the most accurate C&RT classification model. The molecular descriptors selected by the five filter feature selection methods have been compared in relation to oral absorption. In conclusion, the use of filter pre-processing feature selection methods and misclassification costs produce models with better interpretability and predictability for the prediction of oral absorption.

Genetic risk, adherence to healthy lifestyle and acute cardiovascular and thromboembolic complications following SARS-COV-2 infection.

Current understanding of determinants for COVID-19-related cardiovascular and thromboembolic (CVE) complications primarily covers clinical aspects with limited knowledge on genetics and lifestyles. Here, we analysed a prospective cohort of 106,005 participants from UK Biobank with confirmed SARS-CoV-2 infection. We show that higher polygenic risk scores, indicating individual's hereditary risk, were linearly associated with increased risks of post-COVID-19 atrial fibrillation (adjusted HR 1.52 [95% CI 1.44 to 1.60] per standard deviation increase), coronary artery disease (1.57 [1.46 to 1.69]), venous thromboembolism (1.33 [1.18 to 1.50]), and ischaemic stroke (1.27 [1.05 to 1.55]). These genetic associations are robust across genders, key clinical subgroups, and during Omicron waves. However, a prior composite healthier lifestyle was consistently associated with a reduction in all outcomes. Our findings highlight that host genetics and lifestyle independently affect the occurrence of CVE complications in the acute infection phrase, which can guide tailored management of COVID-19 patients and inform population lifestyle interventions to offset the elevated cardiovascular burden post-pandemic.

Harnessing the potential of machine learning and artificial intelligence for dementia research.

Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal data sets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal data sets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification, and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

Development and validation of a dementia risk score in the UK Biobank and Whitehall II cohorts.

BACKGROUND: Current dementia risk scores have had limited success in consistently identifying at-risk individuals across different ages and geographical locations. OBJECTIVE: We aimed to develop and validate a novel dementia risk score for a midlife UK population, using two cohorts: the UK Biobank, and UK Whitehall II study. METHODS: We divided the UK Biobank cohort into a training (n=176 611, 80%) and test sample (n=44 151, 20%) and used the Whitehall II cohort (n=2934) for external validation. We used the Cox LASSO regression to select the strongest predictors of incident dementia from 28 candidate predictors and then developed the risk score using competing risk regression. FINDINGS: Our risk score, termed the UK Biobank Dementia Risk Score (UKBDRS), consisted of age, education, parental history of dementia, material deprivation, a history of diabetes, stroke, depression, hypertension, high cholesterol, household occupancy, and sex. The score had a strong discrimination accuracy in the UK Biobank test sample (area under the curve (AUC) 0.8, 95% CI 0.78 to 0.82) and in the Whitehall cohort (AUC 0.77, 95% CI 0.72 to 0.81). The UKBDRS also significantly outperformed three other widely used dementia risk scores originally developed in cohorts in Australia (the Australian National University Alzheimer's Disease Risk Index), Finland (the Cardiovascular Risk Factors, Ageing, and Dementia score), and the UK (Dementia Risk Score). CLINICAL IMPLICATIONS: Our risk score represents an easy-to-use tool to identify individuals at risk for dementia in the UK. Further research is required to determine the validity of this score in other populations.