Lost in Thought — The Limits of the Human Mind and the Future of Medicine

Obermeyer, Ziad; Lee, Thomas H.

doi:10.1056/nejmp1705348

Cited by 200 publications

(140 citation statements)

References 4 publications

Supporting

Mentioning

127

Contrasting

Unclassified

Order By: Relevance

“…There are growing concerns that medical school is not equipping future doctors with the skill-set to apply these methods to their design of health services 2. We have shown one example of what collaboration between two fields of study could look like13; our goal is that this becomes a more common way of working in medicine.…”

Section: Discussionmentioning

confidence: 96%

“…Medicine cannot afford to continue with patient–doctor interactions that are administratively labour intensive 1. Healthcare needs to move towards a scalable and efficient model 2. There is a consensus that opportunities to use data engineering in health are plentiful,2–4 but there is little in medical journals describing useful examples of this application.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effective resource management using machine learning in medicine: an applied example

et al. 2018

View full text Add to dashboard Cite

BackgroundThe field of medicine is rapidly becoming digitised, and in the process passively amassing large volumes of healthcare data. Machine learning and data analytics are advancing rapidly, but these have been slow to be taken up in the day-to-day delivery of healthcare. We present an application of machine learning to optimise a laboratory testing programme as an example of benefiting from these tools.MethodsCanterbury District Health Board has recently implemented a system for urgent lab sample processing in the community, reducing unnecessary emergency presentations to hospital. Samples are transported from primary care facilities to a central laboratory. To improve the efficiency of this service, our team built a prototype transport scheduling platform using machine learning techniques and simulated the efficiency and cost impact of the platform using historical data.ResultsOur simulation demonstrated procedural efficiency and potential for annual savings between 5% and 14% from implementing a real-time lab sample transport scheduling platform. Advantages included providing a forward job list to the laboratory, an expected time to result and a streamlined transport request process.ConclusionThere are a range of opportunities in healthcare to use large datasets for improved delivery of care. We have described an applied example of using machine learning techniques to improve the efficiency of community patient lab sample processing at scale. This is with a view to demonstrating practical avenues for collaboration between clinicians and machine learning engineers.

show abstract

Section: Discussionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Effective resource management using machine learning in medicine: an applied example

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The potential applications of AI in clinical settings include medial image analyses, disease diagnosis and risk prediction, with the aim of augmenting human intelligence but not replacing a clinician . Currently, AI algorithms have achieved super‐human performance on many tasks, such as image recognition and text analysis .…”

Section: Big Data In Medical Researchmentioning

confidence: 99%

“…7 The potential applications of AI in clinical settings include medial image analyses, disease diagnosis and risk prediction, 5 with the aim of augmenting human intelligence but not replacing a clinician. 8,9 Currently, AI algorithms have achieved super-human performance on many tasks, such as image recognition 10 and text analysis. 11 However, sometimes AI lacks the interpretability: the inner logic behind most machine learning models is hard to explain to physicians and it acts like a black box.…”

Section: Big Data In Medical Researchmentioning

confidence: 99%

Big data in nephrology: Are we ready for the change?

et al. 2019

View full text Add to dashboard Cite

Chronic kidney disease (CKD) is a major public health issue worldwide. However, the status of kidney health care needs to be strengthened globally and research evidence in nephrology is relatively limited. The unmet needs in nephrology leave ample space for imagination regarding leveraging big data and artificial intelligence (AI). Big data has potential to drive medical innovation, reduce medical costs and improve health care quality. Compared with other specialties such as cardiology, the scopes of utilizing big data in nephrology need to be enhanced. We reviewed the studies on the application of big data in nephrology, such as disease surveillance, risk prediction and clinical decision support systems (CDSS), and proposed several potential directions of utilizing big data and AI. The efforts including building a CKD surveillance system and collaborative network, implementing a real‐world cohort in a cost‐effective manner, strengthening the application and transformation of AI and CDSS, and stimulating the activeness of medical imaging in nephrology, could be considered. In the era of big data, a nephrologist would be stronger and smarter if he or she could get intelligent assistance from knowledge or big data‐driven CDSS.

show abstract

“…Increasingly ICUs are using clinical information systems (CIS) to collect, store and display physiological data. The availability of such routinely collected patient data presents the opportunity to apply methods from data science, with the potential to transform healthcare in a number of ways [7,8]. Two particular avenues for development are the automation of simple tasks [9] and the implementation of decision support systems [10], both of which could reduce the cognitive load of clinicians and free up scarce resource for tasks that require human expertise.…”

Section: Introductionmentioning

confidence: 99%

Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic health care data from MIMIC-III and Bristol, UK.

McWilliams

Lawson

Santos-Rodríguez

et al. 2018

Preprint

View full text Add to dashboard Cite

ObjectiveThe primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care. DesignWe used two datasets of routinely collected patient data to test and improve upon a set of previously proposed discharge criteria. SettingBristol Royal Infirmary general intensive care unit (GICU). PatientsTwo cohorts derived from historical datasets: 1870 intensive care patients from GICU in Bristol, and 7592 from MIMIC-III (a publicly available intensive care dataset). ResultsIn both cohorts few successfully discharged patients met all of the discharge criteria. Both a random forest and a logistic classifier, trained using multiple-source cross-validation, demonstrated improved performance over the original criteria and generalised well between the cohorts. The classifiers showed good agreement on which features were most predictive of readiness-fordischarge, and these were generally consistent with clinical experience. By weighting the discharge criteria according to feature importance from the logistic model we showed improved performance over the original criteria, while retaining good interpretability. ConclusionsOur findings indicate the feasibility of the proposed approach to ready-for-discharge classification, which could complement other risk models of specific adverse outcomes in a future decision support system. Avenues for improvement to produce a clinically useful tool are identified. Strengths and Limitations of this study: Training data from multiple source domains is leveraged to produce general classifiers.  The restrictive feature representation tested could be expanded to better exploit the richness of available data and boost performance.  Our approach has the potential to streamline the discharge process in cases where patient physiology makes them clear candidates for a de-escalation of care.  High-risk patients would require additional levels of decision support to facilitate complex discharge planning.

show abstract

Lost in Thought — The Limits of the Human Mind and the Future of Medicine

Cited by 200 publications

References 4 publications

Effective resource management using machine learning in medicine: an applied example

Effective resource management using machine learning in medicine: an applied example

Big data in nephrology: Are we ready for the change?

Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic health care data from MIMIC-III and Bristol, UK.

Contact Info

Product

Resources

About