RESUMEN
Importance: Artificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and potential impact of these newly developed algorithms are currently unknown. Objective: To evaluate the performance of AI algorithms designed to diagnose hip fractures on radiographs and predict postoperative clinical outcomes following hip fracture surgery relative to current practices. Data Sources: A systematic review of the literature was performed using the MEDLINE, Embase, and Cochrane Library databases for all articles published from database inception to January 23, 2023. A manual reference search of included articles was also undertaken to identify any additional relevant articles. Study Selection: Studies developing machine learning (ML) models for the diagnosis of hip fractures from hip or pelvic radiographs or to predict any postoperative patient outcome following hip fracture surgery were included. Data Extraction and Synthesis: This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses and was registered with PROSPERO. Eligible full-text articles were evaluated and relevant data extracted independently using a template data extraction form. For studies that predicted postoperative outcomes, the performance of traditional predictive statistical models, either multivariable logistic or linear regression, was recorded and compared with the performance of the best ML model on the same out-of-sample data set. Main Outcomes and Measures: Diagnostic accuracy of AI models was compared with the diagnostic accuracy of expert clinicians using odds ratios (ORs) with 95% CIs. Areas under the curve for postoperative outcome prediction between traditional statistical models (multivariable linear or logistic regression) and ML models were compared. Results: Of 39 studies that met all criteria and were included in this analysis, 18 (46.2%) used AI models to diagnose hip fractures on plain radiographs and 21 (53.8%) used AI models to predict patient outcomes following hip fracture surgery. A total of 39â¯598 plain radiographs and 714â¯939 hip fractures were used for training, validating, and testing ML models specific to diagnosis and postoperative outcome prediction, respectively. Mortality and length of hospital stay were the most predicted outcomes. On pooled data analysis, compared with clinicians, the OR for diagnostic error of ML models was 0.79 (95% CI, 0.48-1.31; P = .36; I2 = 60%) for hip fracture radiographs. For the ML models, the mean (SD) sensitivity was 89.3% (8.5%), specificity was 87.5% (9.9%), and F1 score was 0.90 (0.06). The mean area under the curve for mortality prediction was 0.84 with ML models compared with 0.79 for alternative controls (P = .09). Conclusions and Relevance: The findings of this systematic review and meta-analysis suggest that the potential applications of AI to aid with diagnosis from hip radiographs are promising. The performance of AI in diagnosing hip fractures was comparable with that of expert radiologists and surgeons. However, current implementations of AI for outcome prediction do not seem to provide substantial benefit over traditional multivariable predictive statistics.
Asunto(s)
Inteligencia Artificial , Fracturas de Cadera , Humanos , Fracturas de Cadera/diagnóstico por imagen , Fracturas de Cadera/cirugía , Pronóstico , Algoritmos , Tiempo de InternaciónRESUMEN
BACKGROUND: The number of periprosthetic fractures above a total knee arthroplasty continues to increase. These fractures are associated with a high risk of morbidity and mortality. Techniques for addressing these fractures include open reduction internal fixation (ORIF) and revision arthroplasty, including distal femoral replacement (DFR). The primary aim of this review is to compare mortality and reoperation rates between ORIF and DFR when used to treat periprosthetic distal femur fractures. METHODS: A systematic review including MEDLINE, Embase and Cochrane Library databases was completed from inception to April 10, 2021. Studies including a comparator cohort were meta-analyzed. RESULTS: Fourteen studies were identified for inclusion, of which, five had sufficient homogeneity for inclusion in a meta-analysis. 30-day and 2-year mortality was 4.1% and 14.6% in the DFR group. There was no statistically significant difference between ORIF and DFR (log Odds-Ratio (OR) = -0.14, 95 %CI: -0.77 to 0.50). The reoperation rate in the DFR group was 9.3% versus 14.8% for ORIF, with no difference between groups (log OR = 0.10, 95 %CI: -0.59 to 0.79). There was no difference in rates of deep infection (log OR = 0.22, 95 %CI: -0.83 to 1.28). Direct comparison of functional outcomes was not possible, though did not appear significant. CONCLUSION: DFR in the setting of periprosthetic distal femur fractures is equivalent to ORIF with respect to mortality and reoperation rate and thus a safe and reliable treatment strategy. DFR may be more reliable in complex fracture patterns where the ability to obtain adequate fixation is difficult.
Asunto(s)
Fracturas del Fémur , Fracturas Periprotésicas , Fracturas del Fémur/etiología , Fracturas del Fémur/cirugía , Fémur/cirugía , Fijación Interna de Fracturas/efectos adversos , Fijación Interna de Fracturas/métodos , Humanos , Fracturas Periprotésicas/cirugía , Reoperación , Estudios RetrospectivosRESUMEN
BACKGROUND: Delirium is an acute and reversible geriatric syndrome that represents a decompensation of cerebral function. Delirium is associated with adverse postoperative outcomes, but controversy exists regarding whether delirium is an independent predictor of mortality. Thus, we assessed the association between incident postoperative delirium and mortality in adult noncardiac surgery patients. METHODS: A systematic search was conducted using Cochrane, MEDLINE/PubMed, Cumulative Index to Nursing and Allied Health Literature, and Embase. Screening and data extraction were conducted by two independent reviewers. Pooled-effect estimates calculated with a random-effects model were expressed as odds ratios with 95% CIs. Risk of bias was assessed using the Cochrane Risk of Bias Tool for Non-Randomized Studies. RESULTS: A total of 34 of 4,968 screened citations met inclusion criteria. Risk of bias ranged from moderate to critical. Pooled analysis of unadjusted event rates (5,545 patients) suggested that delirium was associated with a four-fold increase in the odds of death (odds ratio = 4.12 [95% CI, 3.29 to 5.17]; I = 24.9%). A formal pooled analysis of adjusted outcomes was not possible due to heterogeneity of effect measures reported. However, in studies that controlled for prespecified confounders, none found a statistically significant association between incident postoperative delirium and mortality (two studies in hip fractures; n = 729) after an average follow-up of 21 months. Overall, as study risk of bias decreased, the association between delirium and mortality decreased. CONCLUSIONS: Few high-quality studies are available to estimate the impact of incident postoperative delirium on mortality. Studies that controlled for prespecified confounders did not demonstrate significant independent associations of delirium with mortality.
Asunto(s)
Delirio/mortalidad , Complicaciones Posoperatorias/mortalidad , Procedimientos Quirúrgicos Operativos/estadística & datos numéricos , Anciano , Anciano de 80 o más Años , Femenino , Humanos , Incidencia , Masculino , Persona de Mediana Edad , Oportunidad RelativaRESUMEN
The term "vasculogenic mimicry" (VM) refers to the phenomenon in which vascular-like channels, which are not lined by endothelial cells, are formed in tumors. Since its discovery in 1999, it has been observed in several tumor types and is proposed to provide blood perfusion to tumors in absence of co-apted or neo-angiogenic blood vessels. Pituitary tumors are generally slow growing, benign adenomas which are less vascularized than the normal pituitary gland. To date, VM in pituitary adenomas has not been described. In this histological study, we assessed the presence of VM in a series of surgically resected clinically non-functioning pituitary adenomas (NFPAs) using CD34 and Periodic Acid-Schiff (PAS) double staining. To identify VM, slides were assessed for the presence of CD34-negative and PAS-positive channels indicating that they were not lined by endothelial cells. The histological staining pattern suggestive of VM was noted in 22/49 (44.9%) of the specimens studied. VM was observed in both recurring and non-recurring NFPAs. The incidence of VM present varied from case to case and within groups. There was no association between the presence of VM and gender, tumor size, Ki-67 index, recurrence or cavernous sinus invasion. VM was not noted in cases of non-tumorous pituitaries. Our findings suggest the existence of a complementary perfusion system in pituitary adenomas, implying potential clinical implications with respect to response to therapy and clinical course. Further research is warranted to confirm the presence of VM in pituitary adenomas to elucidate its clinical relevance in patients diagnosed with a pituitary adenoma.
Asunto(s)
Adenoma/patología , Neoplasias Hipofisarias/patología , Adulto , Femenino , Humanos , Masculino , Persona de Mediana EdadRESUMEN
Short-term consumption of a high-fat diet (HFD) can result in an oxidative shift in adult skeletal muscle. However, the impact of HFD on young, growing muscle is largely unknown. Thus, 4-week-old mice were randomly divided into sedentary HFD (60% kcal from fat), sedentary standard chow (control), or exercise-trained standard chow. Tibialis anterior (TA) and soleus muscles were examined for morphological and functional changes after 3 weeks. HFD consumption increased body and epididymal fat mass and induced whole body glucose intolerance versus control mice. Compared to controls, both HFD and exercise-trained TA muscles displayed a greater proportion of oxidative fibers and a trend for an increased succinate dehydrogenase (SDH) content. The soleus also displayed an oxidative shift with increased SDH content in HFD mice. Despite the aforementioned changes, palmitate oxidation rates were not different between groups. To determine if the adaptive changes with HFD manifest as a functional improvement, all groups performed pre- and postexperiment aerobic exercise tests. As expected, exercise-trained mice improved significantly compared to controls, however, no improvement was observed in HFD mice. Interestingly, capillary density was lower in HFD muscles; a finding which may contribute to the lack of functional differences seen with HFD despite the oxidative shift in skeletal muscle morphology. Taken together, our data demonstrate that young, growing muscle exhibits early oxidative shifts in response to a HFD, but these changes do not translate to functional benefits in palmitate oxidation, muscle fatigue resistance, or whole body exercise capacity.
RESUMEN
The idea that microvasculature might be a histopathological biomarker in the prognosis and treatment of tumors is garnering even more attention in the scientific community. The roles of neovascularity in tumor progression and metastasis, have become a hot-topic of investigation in cancer research. A number of methods of quantitatively analyzing pituitary adenoma microvasculature have been applied, and fractal analysis is emerging as a potential effective model for this aim. Additionally, new and more specific immunological techniques have been developed for the detection of microvessels. CD105 (Endoglin) has been proposed as a valuable antigen that marks only newly formed vessels, rather than the entire tumor microvascular system. The combination of different types of immunostaining techniques for the detection of microvessels in pituitary adenomas with fractal analysis as an objective and computer-aided technique to quantify and describe morphological aspects of microvessels has potential implications in future clinical and surgical applications. Tumor treatments, such as anti-angiogenic therapy, as well as intraoperative tools, stand to be enhanced by increasing advances in microvascular research. We here review the methods used for the quantitative analysis of microvessels of the pituitary in its physiopathological states, with the aim to show the pituitary adenoma as a model for the study of neoplastic angioarchitecture and the importance of the introduction of new techniques for the study of angiogenesis, with the relative scientific, medical and surgical implications.