Peripartum cardiomyopathy (PPCM) is a rare form of acute onset heart failure that presents in otherwise healthy pregnant women around the time of delivery. While most of these women respond to early intervention, about 20% progress to end-stage heart failure that symptomatically resembles dilated cardiomyopathy (DCM). In this study, we examined two independent RNAseq datasets from the left ventricle of end-stage PPCM patients and compared gene expression profiles to female DCM and non-failing donors. Differential gene expression, enrichment analysis and cellular deconvolution were performed to identify key processes in disease pathology. PPCM and DCM display similar enrichment in metabolic pathways and extracellular matrix remodeling suggesting these are similar processes across end-stage systolic heart failure. Genes involved in golgi vesicles biogenesis and budding were enriched in PPCM left ventricles compared to healthy donors but were not found in DCM. Furthermore, changes in immune cell populations are evident in PPCM but to a lesser extent compared to DCM, where the latter is associated with pronounced pro-inflammatory and cytotoxic T cell activity. This study reveals several pathways that are common to end-stage heart failure but also identifies potential targets of disease that may be unique to PPCM and DCM.

Cancer risk prediction is a cornerstone of personalized medicine that offers opportunities for early detection and preventive interventions. However, the current models are designed to predict cancer risk face several challenges. First, most rely on traditional statistical methods, which struggle to capture the complexity of genetic, family medical history, and lifestyle factors. Hence, the accuracy of these models is limited. Additionally, the models neglect to integrate multidimensional data sources, particularly genetic information like single nucleotide polymorphisms (SNPs), which could enhance prediction accuracy. Third, while the system might effectively predict risk, it cannot translate those predictions into actionable healthcare recommendations to reduce cancer risk. In this study, we address all three of these limitations. With a focus on six prevalent cancers—we extracted SNP data from the UK Biobank and designed a novel risk prediction model for cancer and personalized healthcare recommendations based upon the mixture of experts (MoE) paradigm and large language models (LLMs), respectively. Named MoE-HRS, experts based two router networks for separate processing by the Transformer and the convolutional neural network (CNN). Experiments on UK Biobank data show that our model outperforms state-of-the-art cancer risk prediction models. To bridge the gap between risk prediction and practical healthcare applications, we devised a healthcare recommender system powered by LLMs. This approach holds promise for enhancing early detection rates and promoting preventive healthcare management (relevant coding and data are available at https://github.com/bjtu-lucas-nlp/MoE-HRS ).

As developments in artificial intelligence and machine learning become more widespread in healthcare, their potential to transform clinical outcomes also increases. Peripartum cardiomyopathy is a rare and poorly-characterised condition that presents as heart failure in the last trimester prior to delivery or within 5–6 months postpartum. The lack of a definitive understanding of the molecular causes and clinical progress of this condition suggests that bibliometrics will be well-suited to creating new insights into this serious clinical problem. We examine similarities and differences between peripartum and its closely related familial dilated cardiomyopathy and idiopathic dilated cardiomyopathy. Using PubMed as the source of bibliometric data, we apply artificial intelligence–supported natural language processing to compare extracted data and genes association with these cardiomyopathies. Gene data were enhanced with additional metadata from third-party datasets and then analysed for their impact and specificity for peripartum cardiomyopathy. Artificial intelligence identified 14 genes that distinguished peripartum from both dilated and familial dilated cardiomyopathy. They are as follows: CTSD, RLN2, MMP23B*, SLC17A5, ST2*, PTHLH, CFH*, CFI, GPT, MR1, Rln1, SRI, STAT5A* and THBD. We then used the Human Protein Atlas website that uses affinity-purified rabbit polyclonal antibodies to identify genes that are expressed at the protein level (bold), or as RNA transcripts (*) in healthy human left ventricles. Additional analysis focussed on the full set of peripartum genes on linkage and specificity to cardiomyopathy yielded a different set of thirteen genes (bold font indicates those expressed in cardiomyocytes: PRL, RLN2, PLN, ST2, CTSD, F2, ACE, STAT3, TTN, SPP1, LGALS3, miR-146a, GNB3, SRI). This type of analysis can highlight new avenues for research, aimed at improving genomics-driven peripartum cardiomyopathy diagnosis as well as potential pathological and clinical sub-classification. We expect that this will allow for future improvements in identification, treatment and management of this condition. The first step in the application of these bibliometric-based artificial intelligence methods is to understand the current knowledge, and it is the aim of this paper to show how this might be achieved.