Objective: To describe and appraise the use of artificial intelligence (AI) techniques that can cope with longitudinal data from electronic health records (EHRs) to predict health-related outcomes. Methods: This review included studies in any language that: EHR was at least one of the data sources, collected longitudinal data, used an AI technique capable of handling longitudinal data, and predicted any health-related outcomes. We searched MEDLINE, Scopus, Web of Science, and IEEE Xplorer from inception to January 3, 2022. Information on the dataset, prediction task, data preprocessing, feature selection, method, validation, performance, and implementation was extracted and summarized using descriptive statistics. Risk of bias and completeness of reporting were assessed using a short form of PROBAST and TRIPOD, respectively. Results: Eighty-one studies were included. Follow-up time and number of registers per patient varied greatly, and most predicted disease development or next event based on diagnoses and drug treatments. Architectures generally were based on Recurrent Neural Networks-like layers, though in recent years combining different layers or transformers has become more popular. About half of the included studies performed hyperparameter tuning and used attention mechanisms. Most performed a single train-test partition and could not correctly assess the variability of the model’s performance. Reporting quality was poor, and a third of the studies were at high risk of bias. Conclusions: AI models are increasingly using longitudinal data. However, the heterogeneity in reporting methodology and results, and the lack of public EHR datasets and code sharing, complicate the possibility of replication. Registration: PROSPERO database (CRD42022331388).

Prevalence of both multimorbidity and frailty increases with age, but more evidence is needed to elucidate their relationship and their association with other health-related outcomes. We analysed the dynamics of both conditions as people age and calculate the associated risk of death, nursing home admission, and need for home care. Data were drawn from the primary care electronic health records of a longitudinal cohort of people aged 65 or older in Catalonia in 2010–2019. Frailty and multimorbidity were measured using validated instruments (eFRAGICAP, a cumulative deficit model; and SNAC-K, respectively), and their longitudinal evolution was described. Cox regression models accounted for the competing risk of death and adjusted by sex, socioeconomical status, and time-varying age, alcohol and smoking. We included 1 456 052 patients. Prevalence of multimorbidity was consistently high regardless of age, while frailty almost quadrupled from 65 to 99 years. Frailty worsened and also changed with age: up to 84 years, it was more related to concurrent diseases, and afterwards, to frailty-related deficits. While concurrent diseases contributed more to mortality, frailty-related deficits increased the risk of institutionalisation and the need for home care. The nature of people’s multimorbidity and frailty vary with age, as does their impact on health status. People become frailer as they age, and their frailty is more characterised by disability and other symptoms than by diseases. Mortality is most associated with the number of comorbidities, whereas frailty-related deficits are associated with needing specialised care. Instituto de Salud Carlos III through PI19/00535, and the PFIS Grant FI20/00040 (Co-funded by European Regional Development Fund/European Social Fund).

Background: Multimorbidity and frailty are characteristics of aging that need individualized evaluation, and there is a 2-way causal relationship between them. Thus, considering frailty in analyses of multimorbidity is important for tailoring social and health care to the specific needs of older people. Objective: This study aimed to assess how the inclusion of frailty contributes to identifying and characterizing multimorbidity patterns in people aged 65 years or older. Methods: Longitudinal data were drawn from electronic health records through the SIDIAP (Sistema d’Informació pel Desenvolupament de la Investigació a l’Atenció Primària) primary care database for the population aged 65 years or older from 2010 to 2019 in Catalonia, Spain. Frailty and multimorbidity were measured annually using validated tools (eFRAGICAP, a cumulative deficit model; and Swedish National Study of Aging and Care in Kungsholmen [SNAC-K], respectively). Two sets of 11 multimorbidity patterns were obtained using fuzzy c-means. Both considered the chronic conditions of the participants. In addition, one set included age, and the other included frailty. Cox models were used to test their associations with death, nursing home admission, and home care need. Trajectories were defined as the evolution of the patterns over the follow-up period. Results: The study included 1,456,052 unique participants (mean follow-up of 7.0 years). Most patterns were similar in both sets in terms of the most prevalent conditions. However, the patterns that considered frailty were better for identifying the population whose main conditions imposed limitations on daily life, with a higher prevalence of frail individuals in patterns like chronic ulcers &peripheral vascular. This set also included a dementia-specific pattern and showed a better fit with the risk of nursing home admission and home care need. On the other hand, the risk of death had a better fit with the set of patterns that did not include frailty. The change in patterns when considering frailty also led to a change in trajectories. On average, participants were in 1.8 patterns during their follow-up, while 45.1% (656,778/1,456,052) remained in the same pattern. Conclusions: Our results suggest that frailty should be considered in addition to chronic diseases when studying multimorbidity patterns in older adults. Multimorbidity patterns and trajectories can help to identify patients with specific needs. The patterns that considered frailty were better for identifying the risk of certain age-related outcomes, such as nursing home admission or home care need, while those considering age were better for identifying the risk of death. Clinical and social intervention guidelines and resource planning can be tailored based on the prevalence of these patterns and trajectories.

Background: The effectiveness of the immunity provided by SARS-CoV-2 vaccines is an important public health issue. We analyzed the determinants of 12-month serology in a multicenter European cohort of vaccinated healthcare workers (HCW). Methods: We analyzed the sociodemographic characteristics and levels of anti-SARS-CoV-2 spike antibodies (IgG) in a cohort of 16,101 vaccinated HCW from eleven centers in Germany, Italy, Romania, Slovakia and Spain. Considering the skewness of the distribution, the serological levels were transformed using log or cubic standardization and normalized by dividing them by center-specific standard errors. We fitted center-specific multivariate regression models to estimate the cohort-specific relative risks (RR) of an increase of one standard deviation of log or cubic antibody level and the corresponding 95% confidence interval (CI) for different factors and combined them in random-effects meta-analyses. Results: We included 16,101 HCW in the analysis. A high antibody level was positively associated with age (RR = 1.04, 95% CI = 1.00–1.08 per 10-year increase), previous infection (RR = 1.78, 95% CI 1.29–2.45) and use of Spikevax [Moderna] with combinations compared to Comirnaty [BioNTech/Pfizer] (RR = 1.07, 95% CI 0.97–1.19) and was negatively associated with the time since last vaccine (RR = 0.94, 95% CI 0.91–0.98 per 30-day increase). Conclusions: These results provide insight about vaccine-induced immunity to SARS-CoV-2, an analysis of its determinants and quantification of the antibody decay trend with time since vaccination.

Multimorbidity, the presence of two or more conditions in one person, is common but studies are often limited to observational data and single datasets. We address this gap by integrating large-scale primary-care and genetic data from multiple studies to interrogate multimorbidity patterns and producing digital resources to support future research. We defined chronic, common, and heritable conditions in individuals aged ≥65 years, using two large primary-care databases [CPRD (UK) N = 2,425,014 and SIDIAP (Spain) N = 1,053,640], and estimated heritability using the same definitions in UK Biobank (N = 451,197). We used logistic regression to estimate the co-occurrence of pairs of conditions in the primary care data. Linkage disequilibrium score regression was used to estimate genetic similarity between pairs of conditions. Meta-analyses were conducted across databases, and up to three sources of genetic data, for each pair of conditions. We classified pairs of conditions as across or within-domain based on the international classification of disease. We identified 72 chronic conditions, with 43.6% of 2546 pairs showing higher co-occurrence than chance in primary care and evidence of shared genetics. Many across-domain pairs exhibited substantial shared genetics (e.g., iron deficiency anaemia and peripheral arterial disease: genetic correlation R_g = 0.45 [95% Confidence Intervals 0.27:0.64]). 33 pairs displayed negative genetic correlations, such as skin cancer and rheumatoid arthritis (R_g = -0.14 [-0.21:-0.06]), due to potential adverse drug effects. Discordance between genetic and primary care data was also observed, e.g., abdominal aortic aneurysm and bladder cancer co-occurred in primary care but were not genetically correlated (Odds-Ratio = 2.23 [2.09:2.37], R_g = 0.04 [-0.20:0.28]) and schizophrenia and fibromyalgia were less likely to co-occur together in primary care but were positively genetically correlated (OR = 0.84 [0.75:0.94], R_g = 0.20 [0.11:0.29]). Most pairs of chronic conditions show evidence of shared genetics, and co-occurrence in primary care, suggesting shared mechanisms. The identified patterns of shared genetics, negative correlations and discordance between genetic and observational data provide a foundation for future multimorbidity research. UK Medical Research Council [MR/W014548/1].

Aging, multimorbidity, and polypharmacy are associated with medication-related problems (MRPs). This study aimed to assess the association that multimorbidity and mortality have with MRPs in older people over time. We followed multimorbid, older (65–99 years) people in Catalonia from 2012 to 2016, using longitudinal data and Cox models to estimate adjusted hazard ratios (HR). We reviewed electronic health records to collect explanatory variables and MRPs (duplicate therapy, drug–drug interactions, potentially inappropriate medications (PIM), and contraindicated drugs in chronic kidney disease (CKD) or liver disease). There were 723,016 people (median age: 74 years; 58.9% women) who completed follow-up. We observed a significant (p < 0.001) increase in the proportion with at least one MRP (2012: 66.9% to 2016: 75.5%); contraindicated drugs in CKD (11.1 to 18.5%) and liver disease (3.9 to 5.3%); and PIMs (62.5 to 71.1%), especially drugs increasing fall risk (67.5%). People with ≥10 diseases had more MRPs (in 2016: PIMs, 89.6%; contraindicated drugs in CKD, 34.4%; and in liver disease, 9.3%). All MRPs were independently associated with mortality, from duplicate therapy (HR 1.06; 95% confidence interval (CI) 1.04–1.08) to interactions (HR 1.60; 95% CI 1.54–1.66). Ensuring safe pharmacological treatment in elderly, multimorbid patient remains a challenge for healthcare systems.