Retrospective comparison of traditional and artificial intelligence-based heart failure phenotyping in a US health system to enable real-world evidence.

OBJECTIVE: Quantitatively evaluate the quality of data underlying real-world evidence (RWE) in heart failure (HF). DESIGN: Retrospective comparison of accuracy in identifying patients with HF and phenotypic information was made using traditional (ie, structured query language applied to structured electronic health record (EHR) data) and advanced (ie, artificial intelligence (AI) applied to unstructured EHR data) RWE approaches. The performance of each approach was measured by the harmonic mean of precision and recall (F1 score) using manual annotation of medical records as a reference standard. SETTING: EHR data from a large academic healthcare system in North America between 2015 and 2019, with an expected catchment of approximately 5 00 000 patients. POPULATION: 4288 encounters for 1155 patients aged 18-85 years, with 472 patients identified as having HF. OUTCOME MEASURES: HF and associated concepts, such as comorbidities, left ventricular ejection fraction, and selected medications. RESULTS: The average F1 scores across 19 HF-specific concepts were 49.0% and 94.1% for the traditional and advanced approaches, respectively (p<0.001 for all concepts with available data). The absolute difference in F1 score between approaches was 45.1% (98.1% relative increase in F1 score using the advanced approach). The advanced approach achieved superior F1 scores for HF presence, phenotype and associated comorbidities. Some phenotypes, such as HF with preserved ejection fraction, revealed dramatic differences in extraction accuracy based on technology applied, with a 4.9% F1 score when using natural language processing (NLP) alone and a 91.0% F1 score when using NLP plus AI-based inference. CONCLUSIONS: A traditional RWE generation approach resulted in low data quality in patients with HF. While an advanced approach demonstrated high accuracy, the results varied dramatically based on extraction techniques. For future studies, advanced approaches and accuracy measurement may be required to ensure data are fit-for-purpose.

Massive transfusion protocols: the role of aggressive resuscitation versus product ratio in mortality reduction.

BACKGROUND: Exsanguinating hemorrhage necessitating massive blood product transfusion is associated with high mortality rates. Recent data suggest that altering the fresh frozen plasma to packed red blood cell ratio (FFP:PRBC) results in significant mortality reductions. Our purpose was to evaluate mortality and blood product use in the context of a newly initiated massive transfusion protocol (MTP). STUDY DESIGN: In July 2005, our American College of Surgeons-verified Level I trauma center implemented an MTP supporting a 1:1.5 FFP:PRBC ratio, improved communications, and enhanced systems flow to optimize rapid blood product availability. During the 4 years surrounding protocol implementation, we reviewed data on trauma patients directly admitted through the emergency department and requiring 10 or more units PRBCs during the first 24 hours. RESULTS: For the 2 years before and subsequent to MTP initiation, there were 4,223 and 4,414 trauma activations, of which 40 and 37 patients, respectively, met study criteria. The FFP:PRBC ratios were identical, at 1:1.8 and 1:1.8 (p = 0.97). Despite no change in FFP:PRBC ratio, mortality decreased from 45% to 19% (p = 0.02). Other significant findings included decreased mean time to first product: cross-matched RBCs (115 to 71 minutes; p = 0.02), FFP (254 to 169 minutes; p = 0.04), and platelets (418 to 241 minutes; p = 0.01). CONCLUSIONS: MTP implementation is associated with mortality reductions that have been ascribed principally to increased plasma use and decreased FFP:PRBC ratios. Our study found a significant reduction in mortality despite unchanged FFP:PRBC ratios and equivalent overall mean numbers of transfusions. Our data underscore the importance of expeditious product availability and emphasize that massive transfusion is a complex process in which product ratio and time to transfusion represent only the beginning of understanding.

A county hospital surgical practice: a model for acute care surgery.

BACKGROUND: Trauma surgery has changed significantly over the past decade. Nonoperative evidence-based algorithms have become common and surgical trauma volume has become increasingly difficult to maintain. The acute care surgery (ACS) model, which integrates trauma, critical care, and emergency surgery, has been proposed as a future model of trauma practice. METHODS: Database information from an academic, county-based, trauma center was reviewed. A performance improvement surgical procedure database and level I trauma registry from 2005 were used to evaluate one center's ACS practice. RESULTS: There were 2,276 cases performed by 7 full-time and 5 part-time surgeons. Elective cases accounted for 64% (1,480) of caseload, emergency/urgent general surgery accounted for 32% (719) of cases, and emergency trauma surgeries accounted for 4% (96 procedures in 77 patients). In all, 23% were performed after hours. The ACS model supported controllable hours, adequate surgical volume, excellent patient care, and an appealing clinical practice. CONCLUSION: Surgical practice in a county-run trauma hospital can be similar to the ACS model, with positive results in terms of clinical volume and physician satisfaction. As clinical practices shift to the ACS model, there are lessons to be learned from currently existing, thriving, long-standing similar prototypes.

Innovation in surgery: a historical perspective.

OBJECTIVE: To describe the field of surgical innovation from a historical perspective, applying new findings from research in technology innovation. BACKGROUND: While surgical innovation has a rich tradition, as a field of study it is embryonic. Only a handful of academic centers of surgical innovation exist, all of which have arisen within the last 5 years. To this point, the field has not been well defined, nor have future options to promote surgical innovation been thoroughly explored. It is clear that surgical innovation is fundamental to surgical progress and has significant health policy implications. A process of systematically evaluating and promoting innovation in surgery may be critical in the evolving practice of medicine. METHODS: A review of the academic literature in technology innovation was undertaken. Articles and books were identified through technical, medical, and business sources. Luminaries in surgical innovation were interviewed to develop further relevance to surgical history. The concepts in technology innovation were then applied to innovation in surgery, using the historical example of surgical endoscopy as a representative area, which encompasses millennia of learning and spans multiple specialties of care. RESULTS: The history of surgery is comprised largely of individual, widely respected surgeon innovators. While respecting individual accomplishments, surgeons as a group have at times hindered critical innovation to the detriment of our profession and patients. As a clinical discipline, surgery relies on a tradition of research and attracting the brightest young minds. Innovation in surgery to date has been impressive, but inconsistently supported. CONCLUSION: A body of knowledge on technology innovation has been developed over the last decade but has largely not been applied to surgery. New surgical innovation centers are working to define the field and identify critical aspects of surgical innovation promotion. It is our responsibility as a profession to work to understand innovation in surgery, discover, translate, and commercialize advances to address major clinical problems, and to support the future of our profession consistently and rationally.

Inventing our future: training the next generation of surgeon innovators.

Current surgical care and technology has evolved over the centuries from the interplay between creative surgeons and new technologies. As both fields become more specialized, that interplay is threatened. A 2-year educational fellowship is described which teaches both the process and the discipline of medical/surgical device innovation. Multi-disciplinary teams (surgeons, engineers, business grads) are assembled to educate a generation of translators, who can bridge the gap between scientific and technologic advances and the needs of the physician and the patient.

The ethics of innovation in pediatric surgery.

Ethical issues in pediatric research have long been debated, and experimentation in pediatric surgery is under intense scrutiny. Extensive legislation and institutional systems that attempt to protect children while supporting necessary research are at times ineffective. Pediatric surgery has less funding and resources for innovation than fields with higher clinical volume. Not unlike pediatrics in general, innovation in pediatric surgery must be beyond criticism. And yet, for the sake of patients, innovation should not only be maintained, but must be encouraged.