New beginnings
2019; Elsevier BV; Volume: 2; Issue: 1 Linguagem: Inglês
10.1016/s2589-7500(19)30223-7
ISSN2589-7500
Autores Tópico(s)Anatomy and Medical Technology
ResumoThe New Year is a time for reflection; a chance to look back and assess what has happened in the past year and to make resolutions for the year ahead. The best resolutions are based on predictions of what is to come and we think there is no better way to start the New Year than to look at past predictions from the world of science fiction and indulge in a nostalgic review of which of them came to be. Science fiction serves as an inspiration for the development of real-life advances, be it in the medical arena or further afield. Motorola's inspiration for the mobile phone was reportedly Captain Kirk's communicator in Star Trek. Self-driving cars, once the brain child of Isaac Asimov for the New York Times in 1964 and portrayed convincingly in Total Recall (1990), are now a promising development. Both The Jetsons (1962) and 2001: A Space Odyssey (1968) predicted the advent of video calls (along with home robots and tablets, respectively), with the HAL 9000 also eerily similar to Apple's Siri or Amazon's Alexa (though thankfully not too similar). But what about health care? In August, 2019, Koen Willemsen and colleagues' article on 3D-printed spinal implants gave us insight into some of the design and regulatory challenges. Star Trek enthusiasts might well also recognise the 3D printer as a version of the replicator. Though yet unable to produce meals from thin air, the ability to print was beyond the realms of possibility for widespread adoption just 10 years ago. However, now 3D printing of surgical implants for situations in which off-the-shelf implants are unsuitable—as in the case of birth defects or injury, which vary from individual to individual—are becoming available in hospitals and research units owing to the plummeting costs of the technology in addition to improved accuracy of the final product. New developments in bioengineering have also led to 3D printing of tissues and vasculature, which are making organ printing a possibility. Also from Star Trek, the medical tricorder would be an obvious contender for science fiction-turned-reality—just last month at the Radiological Society of North America meeting, reports of a portable chest X-ray and CT scanners led the way towards this piece of kit; portable MRI is also encouragingly close to being a reality, with a vision of bringing MRI to the bedside. From the Six Million Dollar Man (1973), the inspiration behind progression in nerve-controlled prostheses is made clear. The use of big data to predict remission, recovery and quality of life outcomes in people with first episode psychosis, or determining the dose required in radiotherapy are two exciting ways in which technology has progressed. These developments, alongside the new findings that machines are as accurate at detecting disease from medical imaging as humans, has thrown a new spotlight on machines in medicine. With a recent study in The Lancet Digital Health also showing that machine learning algorithms can be as effective in the hands of relative novices as experts, machine learning is likely to impact primary care. An inconceivable concept years ago would have been the idea that we could use computers to make large, population-level predictions, or use machine learning to predict individuals with difficult-to-detect diseases such as familial hypercholesterolaemia, as done in the study by Kelly Myers and colleagues. Tackling antibiotic resistance, a theme from the 1969 book The Andromeda Strain by Michael Crichton, has become a global priority 50 years on. Timothy Rawson and colleagues published research in The Lancet Digital Health on the use of microneedles for antibiotic monitoring in vivo, which could mark the way towards personalised dosing recommendations. Pilot studies such as these are important and move ideas of science fiction origin into the realm of possibility. New research that has the potential for improving medical outcomes and effectiveness is a priority for The Lancet Digital Health. Of course, not all science fiction has come true—it is fiction after all, and Back to the Future has not yet inspired flying cars! Personalised advertising is not quite as widespread as that featured in Minority Report (2002), nor has the concept of replacing credit cards with biometric verification become prevalent. Just because some of these developments in technology seem normal to us, doesn't mean it wasn't science fiction once. Who knows what the next decade will yield? For Isaac Asimov's essay see https://archive.nytimes.com/www.nytimes.com/books/97/03/23/lifetimes/asi-v-fair.html?category=medtech/For more on 3D printing of tissue and vasculature see https://www.ft.com/content/67fbca0c-6c05-11e9-80c7-60ee53e6681dFor more on portable MRI see https://www.statnews.com/2019/10/25/smaller-lighter-cheaper-a-serial-entrepreneur-wants-his-portable-mri-to-transform-medicine/ For Isaac Asimov's essay see https://archive.nytimes.com/www.nytimes.com/books/97/03/23/lifetimes/asi-v-fair.html?category=medtech/ For more on 3D printing of tissue and vasculature see https://www.ft.com/content/67fbca0c-6c05-11e9-80c7-60ee53e6681d For more on portable MRI see https://www.statnews.com/2019/10/25/smaller-lighter-cheaper-a-serial-entrepreneur-wants-his-portable-mri-to-transform-medicine/ Challenges in the design and regulatory approval of 3D-printed surgical implants: a two-case seriesPatient-specific treatment approaches incorporating 3D-printed implants can be helpful in carefully selected cases when conventional methods are not an option. Comprehensive and efficient interactions between medical engineers and physicians are essential to establish well designed frameworks to navigate the logistical and regulatory aspects of technology development to ensure the safety and legal validity of patient-specific treatments. The framework described here could encourage physicians to treat (once untreatable) patients with novel personalised techniques. Full-Text PDF Open AccessDevelopment and validation of multivariable prediction models of remission, recovery, and quality of life outcomes in people with first episode psychosis: a machine learning approachIn our machine learning analysis, we showed that prediction models can reliably and prospectively identify poor remission and recovery outcomes at 1 year for patients with first-episode psychosis using baseline clinical variables at first clinical contact. Full-Text PDF Open AccessAn image-based deep learning framework for individualising radiotherapy dose: a retrospective analysis of outcome predictionOur results indicate that there are image-distinct subpopulations that have differential sensitivity to radiotherapy. The image-based deep learning framework proposed herein is the first opportunity to use medical images to individualise radiotherapy dose. Our results signify a new roadmap for deep learning-guided predictions and treatment guidance in the image-replete and highly standardised discipline of radiation oncology. Full-Text PDF Open AccessA comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysisOur review found the diagnostic performance of deep learning models to be equivalent to that of health-care professionals. However, a major finding of the review is that few studies presented externally validated results or compared the performance of deep learning models and health-care professionals using the same sample. Additionally, poor reporting is prevalent in deep learning studies, which limits reliable interpretation of the reported diagnostic accuracy. New reporting standards that address specific challenges of deep learning could improve future studies, enabling greater confidence in the results of future evaluations of this promising technology. Full-Text PDF Open AccessAutomated deep learning design for medical image classification by health-care professionals with no coding experience: a feasibility studyAll models, except the automated deep learning model trained on the multilabel classification task of the NIH CXR14 dataset, showed comparable discriminative performance and diagnostic properties to state-of-the-art performing deep learning algorithms. The performance in the external validation study was low. The quality of the open-access datasets (including insufficient information about patient flow and demographics) and the absence of measurement for precision, such as confidence intervals, constituted the major limitations of this study. Full-Text PDF Open AccessPrecision screening for familial hypercholesterolaemia: a machine learning study applied to electronic health encounter dataThe FIND FH model successfully scans large, diverse, and disparate health-care encounter databases to identify individuals with familial hypercholesterolaemia. Full-Text PDF Open AccessMicroneedle biosensors for real-time, minimally invasive drug monitoring of phenoxymethylpenicillin: a first-in-human evaluation in healthy volunteersThis study is proof-of-concept of real-time, microneedle sensing of penicillin in vivo. Future work will explore microneedle use in patient populations, their role in data generation to inform dosing recommendations, and their incorporation into closed-loop control systems for automated drug delivery. Full-Text PDF Open Access
Referência(s)