As large language models (LLMs) expand and become more advanced, so do the natural language processing capabilities of conversational AI, or "chatbots". OpenAI's recent release, ChatGPT, uses a ...transformer-based model to enable human-like text generation and question-answering on general domain knowledge, while a healthcare-specific Large Language Model (LLM) such as GatorTron has focused on the real-world healthcare domain knowledge. As LLMs advance to achieve near human-level performances on medical question and answering benchmarks, it is probable that Conversational AI will soon be developed for use in healthcare. In this article we discuss the potential and compare the performance of two different approaches to generative pretrained transformers-ChatGPT, the most widely used general conversational LLM, and Foresight, a GPT (generative pretrained transformer) based model focused on modelling patients and disorders. The comparison is conducted on the task of forecasting relevant diagnoses based on clinical vignettes. We also discuss important considerations and limitations of transformer-based chatbots for clinical use.
Malaria is among the top-ranked parasitic diseases that pose a threat to the existence of the human race. This study evaluated the antimalarial effect of the rhizome of Zingiber officinale in ...infected mice, performed secondary metabolite profiling and detailed computational antimalarial evaluation through molecular docking, molecular dynamics (MD) simulation and density functional theory methods. The antimalarial potential of Z. officinale was performed using the in vivo chemosuppressive model; secondary metabolite profiling was carried out using liquid chromatography-mass spectrometry (LC-MS). Molecular docking was performed with Autodock Vina while the MD simulation was performed with Schrodinger desmond suite for 100 ns and DFT calculations with B3LYP (6-31G) basis set. The extract showed 64% parasitaemia suppression, with a dose-dependent increase in activity up to 200 mg/kg. The chemical profiling of the extract tentatively identified eight phytochemicals. The molecular docking studies with plasmepsin II and Plasmodium falciparum dihydrofolate reductase-thymidylate synthase (PfDHFR-TS) identified gingerenone A as the hit molecule, and MMGBSA values corroborate the binding energies obtained. The electronic parameters of gingerenone A revealed its significant antimalarial potential. The antimalarial activity elicited by the extract of Z. officinale and the bioactive chemical constituent supports its usage in ethnomedicine.
Communicated by Ramaswamy H. Sarma
•Screening bacterial isolates for antagonistic potential.•Molecular methods for identification of isolates.•Six potent antibacterial isolates against the test pathogenic species.•Pseudomonas was ...susceptible to antagonizing strains.•Necessity for new effective antibacterial formulation.
This study aims to screen bacterial isolates from Olabisi Onabanjo University Farmland for antibacterial activity against pathogenic microorganisms. Agar well diffusion method was used. Isolates were identified molecularly. Chi-square test revealed significant association between isolates, antibacterial activity with likelihood p-value = 0.000 and 5% significant level. Six among thirty-five isolates exhibited antibacterial activity against the test pathogenic species. A greater antibacterial activity (50 % inhibition) was observed in Lysinibacillus sphearicus strain PRE16. It inhibited the growth of Bacillus subtilis, Staphylococcus aureus and Escherichia coli by 23.00 ± 2.00, 18.00 ± 2.00 and 20.00 ± 4.00 respectively. DNA sequencing revealed antagonist isolates as Bacillus sp. BCN2, Brochothrix thermosphacta strain P30C4, Bacillus aryabhattai strain KNUC205, Alcaligenes faecalis strain KEM24, Bacillus arsenicus strain CSD05 and Lysinibacillus sphaericus strain PRE16. Phylogenetic analysis revealed close relatedness of most isolates with Bacillus species strains. These strains are suggested to be effective for the discovery of new antibacterial agents.
As foundation doctors, we have often found ourselves informing patients that a certain aspect of their medical information cannot be immediately found, either because it is on an electronic system we ...cannot access, or it is in a hospital that is unlinked to our own. Unsurprisingly, this frequently leaves patients flabbergasted and confused. We started to wonder: if patients' data are entered onto an electronic system: where do those data go? If medical data are searched for, where do those data come from? Why are there so many hidden sources of information that clinicians cannot access? In an ever-increasing digital sphere, electronic data will be the future of holistic health and social care planning, impacting every clinician's day-to-day role. From electronic healthcare records to the use of artificial intelligence solutions, this article will serve as an introduction to how data flows in modern healthcare systems.
An electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. ...Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments).
Foresight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital KCH, South London and Maudsley SLaM, and the US Medical Information Mart for Intensive Care III MIMIC-III), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall.
Foresight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% 95% CI 91–100) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required.
Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes.
National Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.
This study examined multilevel factors related to postnatal checkups for mothers in selected West African countries. The study analyzed data from Demographic and Health Surveys (DHS) for five West ...African countries: Sierra Leone (2013), Cote d'Ivoire (2012), Guinea (2012), Niger (2012), and Liberia (2013). The weighted sample sizes were 2125 (Cote d'Ivoire), 2908 (Guinea), 1905 (Liberia), 5660 (Niger), and 3754 (Sierra Leone). The outcome variable was maternal postnatal checkups. The explanatory variables were community and individual/household characteristics. With the use of Stata 12, the chi-square statistic and multilevel mixed-effects logistic regression were applied. More than two-thirds of respondents in Guinea and Niger did not receive a postnatal checkup after their last birth, while in Cote d'Ivoire, Liberia, and Sierra Leone, more than half of respondents received a postnatal checkup after their last childbirth. Community characteristics accounted for the following variations in postnatal checkups: 33.9% (Cote d'Ivoire), 37.2% (Guinea), 27.0% (Liberia), 33.5% (Niger), and 37.2% (Sierra Leone). Community factors thus had important relations to use of postnatal care in West Africa. Interventions targeting more community variables, particularly community education and poverty, may further improve postnatal care in West Africa.