Artificial intelligence or AI has been heralded as the most transformative technology in healthcare, including critical care medicine. Globally, healthcare specialists and health ministries are being pressured to create and implement a roadmap to incorporate applications of AI into care delivery. To date, the majority of Japan's approach to AI has been anchored in industry, and the challenges that have occurred therein offer important lessons for nations developing new AI strategies. Notably, the demand for an AI-literate workforce has outpaced training programs and knowledge. This is particularly observable within medicine, where clinicians may be unfamiliar with the technology. National policy and private sector involvement have shown promise in developing both workforce and AI applications in healthcare. In combination with Japan's unique national healthcare system and aggregable healthcare and socioeconomic data, Japan has a rich opportunity to lead in the field of medical AI.
The availability of large, deidentified health datasets has enabled significant innovation in using machine learning (ML) to better understand patients and their diseases. However, questions remain regarding the true privacy of this data, patient control over their data, and how we regulate data sharing in a way that that does not encumber progress or further potentiate biases for underrepresented populations. After reviewing the literature on potential reidentifications of patients in publicly available datasets, we argue that the cost—measured in terms of access to future medical innovations and clinical software—of slowing ML progress is too great to limit sharing data through large publicly available databases for concerns of imperfect data anonymization. This cost is especially great for developing countries where the barriers preventing inclusion in such databases will continue to rise, further excluding these populations and increasing existing biases that favor high-income countries. Preventing artificial intelligence’s progress towards precision medicine and sliding back to clinical practice dogma may pose a larger threat than concerns of potential patient reidentification within publicly available datasets. While the risk to patient privacy should be minimized, we believe this risk will never be zero, and society has to determine an acceptable risk threshold below which data sharing can occur—for the benefit of a global medical knowledge system.
Routinely collected electronic health records (EHR) in clinical information systems (CIS) are often heterogeneous, have inconsistent data formats and lack of documentation. We use the well-known open-source database schema of MIMIC-IV to address this issue aiming to support collaborative secondary analysis. Over 154 million data records from a German ICU have already been mapped and inserted into the schema successfully. However, discrepancies between the German and US health systems as well as specifics in our clinical source data hinder the direct translation to MIMIC. Evaluating and improving mapping completeness is part of the ongoing research.
Purpose. Elevations in initially obtained serum lactate levels are strong predictors of mortality in critically ill patients. Identifying patients whose serum lactate levels are more likely to increase can alert physicians to intensify care and guide them in the frequency of tending the blood test. We investigate whether machine learning models can predict subsequent serum lactate changes.Methods. We investigated serum lactate change prediction using the MIMIC-III and eICU-CRD datasets in internal as well as external validation of the eICU cohort on the MIMIC-III cohort. Three subgroups were defined based on the initial lactate levels: i) normal group (<2 mmol/L), ii) mild group (2-4 mmol/L), and iii) severe group (>4 mmol/L). Outcomes were defined based on increase or decrease of serum lactate levels between the groups. We also performed sensitivity analysis by defining the outcome as lactate change of >10% and furthermore investigated the influence of the time interval between subsequent lactate measurements on predictive performance.Results. The LSTM models were able to predict deterioration of serum lactate values of MIMIC-III patients with an AUC of 0.77 (95% CI 0.762-0.771) for the normal group, 0.77 (95% CI 0.768-0.772) for the mild group, and 0.85 (95% CI 0.840-0.851) for the severe group, with a slightly lower performance in the external validation. Conclusion.The LSTM demonstrated good discrimination of patients who had deterioration in serum lactate levels. Clinical studies are needed to evaluate whether utilization of a clinical decision support tool based on these results could positively impact decision-making and patient outcomes.
This study describes a randomised control trial investigating whether printed leaflets or social media are more effective in increasing knowledge of the risks of sun exposure and melanoma in people aged 18–29. The study participants were 18–29-year-old university students or graduates, recruited in London. A baseline level of knowledge was measured using the Skin Cancer and Sun Knowledge questionnaire. Study participants were then randomised into either a leaflet arm or Facebook arm. Identical information was delivered through a SunSafe campaign via either posted leaflets or Facebook during a 10-day exposure window. Following this, participants repeated the Skin Cancer and Sun Knowledge questionnaire. Following the SunSafe intervention, the mean knowledge score improved in both groups to a statistically significant degree (Facebook = 1.82, leaflets = 3.04, P < 0.001). Moreover, the improvement in knowledge score of the leaflet arm was statistically significantly greater than in the Facebook arm (95% confidence interval: 0.35–2.09, P = 0.0059). Participants of lighter skin colour demonstrated greater levels of knowledge about skin cancer and sun exposure at baseline (P = 0.005; P < 0.05). There was no correlation between sex and baseline knowledge (P = 0.7725). There was no significant effect of skin tone or sex on the knowledge change (P = 0.139 and 0.643). The findings suggest that printed information in the form of leaflets is more impactful in increasing knowledge than online platforms such as Facebook among a young adult demographic in the UK. These findings should be considered when designing public health campaigns, acting as a reminder to not neglect traditional media in health promotion.
BackgroundDespite wide usage across all areas of medicine, it is uncertain how useful standard reference ranges of laboratory values are for critically ill patients.ObjectivesThe aim of this study is to assess the distributions of standard laboratory measurements in more than 330 selected intensive care units (ICUs) across the USA, Amsterdam, Beijing and Tarragona; compare differences and similarities across different geographical locations and evaluate how they may be associated with differences in length of stay (LOS) and mortality in the ICU.MethodsA multi-centre, retrospective, cross-sectional study of data from five databases for adult patients first admitted to an ICU between 2001 and 2019 was conducted. The included databases contained patient-level data regarding demographics, interventions, clinical outcomes and laboratory results. Kernel density estimation functions were applied to the distributions of laboratory tests, and the overlapping coefficient and Cohen standardised mean difference were used to quantify differences in these distributions.ResultsThe 259 382 patients studied across five databases in four countries showed a high degree of heterogeneity with regard to demographics, case mix, interventions and outcomes. A high level of divergence in the studied laboratory results (creatinine, haemoglobin, lactate, sodium) from the locally used reference ranges was observed, even when stratified by outcome.ConclusionStandardised reference ranges have limited relevance to ICU patients across a range of geographies. The development of context-specific reference ranges, especially as it relates to clinical outcomes like LOS and mortality, may be more useful to clinicians.
Background Healthcare systems function as an important component and a contributing factor in global health. The application of information technology (IT) in healthcare systems function as a basis for the utilization of data science, whichin its practical application-not only provides opportunities to increase the quality of care, improve efficiency, and decrease costs but also buries the risk of hindering existing workflows, decreasing staff satisfaction, and further siloing access to patient data. Methods Three different applications of health information technology (HIT), applied in the context of data science, will be examined in this chapter with regard to their opportunities and challenges for the system and, as a result of this, for global health. Results Electronic health records, health information exchange, and artificial intelligence have great potential to alleviate some of healthcare systems' greatest burdens and make modern medicine more evidence-based, yet their successful implementation yields a multidisciplinary approach, constant development and evaluation, and collaboration amongst all stakeholders. Conclusions Stakeholders and implementers must consider the opportunities and challenges that come with the planning, implementation, and maintenance of HIT in order to minimize negative impacts and leverage its full potential for an overall improvement of global health. Keywords Health information technology • Electronic health records • Health information exchange • Artificial intelligence (AI) Learning Objectives In this chapter, we discuss the role of health information technology (HIT) in increasingly complex, challenging, and constantly evolving healthcare systems with regard to its role in data science (for more details on the methods of data science, please refer
AI will take on an increasingly important role in medicine. Therefore, AI competencies should be taught in medical school. We investigated the inventory of AI-related courses at German medical schools. The majority of faculty offer courses on AI, but mainly at the elective and introductory levels. Regarding the topic of AI, there is a gap in German medical education that should be closed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.