Artificial intelligence in medicine Hamet, Pavel; Tremblay, Johanne
Metabolism, clinical and experimental,
04/2017, Letnik:
69
Journal Article
Recenzirano
Abstract Artificial Intelligence (AI) is a general term that implies the use of a computer to model intelligent behavior with minimal human intervention. AI is generally accepted as having started ...with the invention of robots. The term derives from the Czech word robota , meaning biosynthetic machines used as forced labor. In this field, Leonardo Da Vinci's lasting heritage is today's burgeoning use of robotic-assisted surgery, named after him, for complex urologic and gynecologic procedures. Da Vinci's sketchbooks of robots helped set the stage for this innovation. AI, described as the science and engineering of making intelligent machines, was officially born in 1956. The term is applicable to a broad range of items in medicine such as robotics, medical diagnosis, medical statistics, and human biology—up to and including today's “omics”. AI in medicine, which is the focus of this review, has two main branches: virtual and physical. The virtual branch includes informatics approaches from deep learning information management to control of health management systems, including electronic health records, and active guidance of physicians in their treatment decisions. The physical branch is best represented by robots used to assist the elderly patient or the attending surgeon. Also embodied in this branch are targeted nanorobots , a unique new drug delivery system. The societal and ethical complexities of these applications require further reflection, proof of their medical utility, economic value, and development of interdisciplinary strategies for their wider application.
We need to consider the ethical challenges inherent in implementing machine learning in health care if its benefits are to be realized. Some of these challenges are straightforward, whereas others ...have less obvious risks but raise broader ethical concerns.
In this Viewpoint, Ezekiel Emanuel and Robert Wachter discuss reasons for the hype surrounding the use of artificial intelligence (AI) in health care and emphasize the need for changes in structures ...and culture that can change behaviors of clinicians if AI-derived evidence is to be effectively translated into practice.
Large efforts dedicated to detect somatic alterations across tumor genomes/exomes are expected to produce significant improvements in precision cancer medicine. However, high inter-tumor ...heterogeneity is a major obstacle to developing and applying therapeutic targeted agents to treat most cancer patients. Here, we offer a comprehensive assessment of the scope of targeted therapeutic agents in a large pan-cancer cohort. We developed an in silico prescription strategy based on identification of the driver alterations in each tumor and their druggability options. Although relatively few tumors are tractable by approved agents following clinical guidelines (5.9%), up to 40.2% could benefit from different repurposing options, and up to 73.3% considering treatments currently under clinical investigation. We also identified 80 therapeutically targetable cancer genes.
Display omitted
•Driver genes are comprehensively identified across a large pan-cancer cohort•In silico prescription links approved or experimental targeted therapies to patients•Up to 73.3% of patients could benefit from agents in clinical stages•80 therapeutically unexploited targetable cancer driver genes are identified
Using a large pan-cancer cohort, Rubio-Perez et al. develop an in silico drug prescription strategy based on driver alterations in each tumor and their druggability options and use it to identify druggable targets and promising repurposing opportunities.
We hypothesized that human atrial fibrillation (AF) may be sustained by localized sources (electrical rotors and focal impulses), whose elimination (focal impulse and rotor modulation FIRM) may ...improve outcome from AF ablation.
Catheter ablation for AF is a promising therapy, whose success is limited in part by uncertainty in the mechanisms that sustain AF. We developed a computational approach to map whether AF is sustained by several meandering waves (the prevailing hypothesis) or localized sources, then prospectively tested whether targeting patient-specific mechanisms revealed by mapping would improve AF ablation outcome.
We recruited 92 subjects during 107 consecutive ablation procedures for paroxysmal or persistent (72%) AF. Cases were prospectively treated, in a 2-arm 1:2 design, by ablation at sources (FIRM-guided) followed by conventional ablation (n = 36), or conventional ablation alone (n = 71; FIRM-blinded).
Localized rotors or focal impulses were detected in 98 (97%) of 101 cases with sustained AF, each exhibiting 2.1 ± 1.0 sources. The acute endpoint (AF termination or consistent slowing) was achieved in 86% of FIRM-guided cases versus 20% of FIRM-blinded cases (p < 0.001). FIRM ablation alone at the primary source terminated AF in a median 2.5 min (interquartile range: 1.0 to 3.1 min). Total ablation time did not differ between groups (57.8 ± 22.8 min vs. 52.1 ± 17.8 min, p = 0.16). During a median 273 days (interquartile range: 132 to 681 days) after a single procedure, FIRM-guided cases had higher freedom from AF (82.4% vs. 44.9%; p < 0.001) after a single procedure than FIRM-blinded cases with rigorous, often implanted, electrocardiography monitoring. Adverse events did not differ between groups.
Localized electrical rotors and focal impulse sources are prevalent sustaining mechanisms for human AF. FIRM ablation at patient-specific sources acutely terminated or slowed AF, and improved outcome. These results offer a novel mechanistic framework and treatment paradigm for AF. (Conventional Ablation for Atrial Fibrillation With or Without Focal Impulse and Rotor Modulation CONFIRM; NCT01008722).
Excisional body contour surgery is the cornerstone treatment for skin laxity. Decision-making can be challenging when selecting the procedure. Dynamic definition liposculpture allows the surgeon to ...carve the underlying anatomy and provide more natural results, in which umbilical shape and position play a crucial role. The authors describe their experience using a decision-making algorithm as a tool to ease surgical planning for advanced excisional body contouring.
Following the algorithm designed by the senior author regarding excisional body contouring procedures, the authors searched their database for patients who were classified according to skin laxity and navel location to undergo one of the following procedures: mixed technologies plus umbilical mobilization, mixed technologies plus sliding mini-abdominoplasty, mini-tummy tuck with muscular plication, full abdominoplasty, reverse bridge abdominoplasty, or reverse full abdominoplasty.
A total of 563 women were consecutively operated on from February of 2014 to January of 2020. The six-procedure model algorithm helped the authors achieve very good results with low complication rates in patients with some grade of abdominal skin laxity. Most complications were reported as minor (9.6 percent). Major complications (3.9 percent) included three localized infections, four abnormal skin retractions, two cases of skin flap necrosis, and 13 cases of postoperative anemia.
This algorithm helped the authors choose the best excisional technique based on patients' anatomical features by following skin geometry to enhance aesthetic outcomes. Further studies are needed to support the algorithm validation and aesthetic outcomes.
Therapeutic, IV.
Display omitted
•Computer interpretable guidelines (CIG) methods papers are classifies into eight themes.•The themes cover the life-cycle of CIG development.•CIG research published in JBI and four ...additional prominent journals are reviewed.
Clinical practice guidelines (CPGs) aim to improve the quality of care, reduce unjustified practice variations and reduce healthcare costs. In order for them to be effective, clinical guidelines need to be integrated with the care flow and provide patient-specific advice when and where needed. Hence, their formalization as computer-interpretable guidelines (CIGs) makes it possible to develop CIG-based decision-support systems (DSSs), which have a better chance of impacting clinician behavior than narrative guidelines. This paper reviews the literature on CIG-related methodologies since the inception of CIGs, while focusing and drawing themes for classifying CIG research from CIG-related publications in the Journal of Biomedical Informatics (JBI). The themes span the entire life-cycle of CIG development and include: knowledge acquisition and specification for improved CIG design, including (1) CIG modeling languages and (2) CIG acquisition and specification methodologies, (3) integration of CIGs with electronic health records (EHRs) and organizational workflow, (4) CIG validation and verification, (5) CIG execution engines and supportive tools, (6) exception handling in CIGs, (7) CIG maintenance, including analyzing clinician’s compliance to CIG recommendations and CIG versioning and evolution, and finally (8) CIG sharing. I examine the temporal trends in CIG-related research and discuss additional themes that were not identified in JBI papers, including existing themes such as overcoming implementation barriers, modeling clinical goals, and temporal expressions, as well as futuristic themes, such as patient-centric CIGs and distributed CIGs.
•An innovative and comprehensive driving simulator experiment for examining driving behaviors in the connected environment.•Drivers maintain higher safety margins during car-following and ...lane-changing maneuvers in the connected environment.•Driver interactions with pedestrians and traffic lights in the connected environment are safer.•Communication delay and communication loss deteriorate driving performances and safety.
The connected environment provides surrounding traffic information to drivers via different driving aids that are expected to improve driving behavior and assist in avoiding safety-critical events. These driving aids include speed advisory, car-following assistance, lane-changing support, and advanced information about possible unseen hazards, among many others. While various studies have attempted to examine the effectiveness of different driving aids discretely, it is still vague how drivers perform when they are exposed to a connected environment with vehicle-to-vehicle and vehicle-to-infrastructure communication capabilities. As such, the objective of this study is to examine the effects of the connected environment on driving behavior and safety. To achieve this aim, an innovative driving simulator experiment was designed to mimic a connected environment using the CARRS-Q Advanced Driving Simulator. Two types of driving aids were disseminated in the connected environment: continuous and event-based information. Seventy-eight participants with diverse backgrounds drove the simulator in four driving conditions: baseline (without driving aids), perfect communication (uninterrupted supply of driving aids), communication delay (driving aids are delayed), and communication loss (intermittent loss of driving aids). Various key driving behavior indicators were analyzed and compared across various routine driving tasks such as car-following, lane-changing, interactions with traffic lights, and giving way to pedestrians at pedestrian crossings. Results suggest that drivers in the perfect communication scenario maintain a longer time-to-collision during car-following, a longer time-to-collision to pedestrian, a lower deceleration to avoid a crash during lane-changing, and a lower propensity of yellow light running. Overall, drivers in the connected environment are found to make informed (thus better) decisions towards safe driving.