RESUMEN
Background: Chest radiography is the standard method for detecting rib fractures. Our study aims to develop an artificial intelligence (AI) model that, with only a relatively small amount of training data, can identify rib fractures on chest radiographs and accurately mark their precise locations, thereby achieving a diagnostic accuracy comparable to that of medical professionals. Methods: For this retrospective study, we developed an AI model using 540 chest radiographs (270 normal and 270 with rib fractures) labeled for use with Detectron2 which incorporates a faster region-based convolutional neural network (R-CNN) enhanced with a feature pyramid network (FPN). The model's ability to classify radiographs and detect rib fractures was assessed. Furthermore, we compared the model's performance to that of 12 physicians, including six board-certified anesthesiologists and six residents, through an observer performance test. Results: Regarding the radiographic classification performance of the AI model, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) were 0.87, 0.83, and 0.89, respectively. In terms of rib fracture detection performance, the sensitivity, false-positive rate, and free-response receiver operating characteristic (JAFROC) figure of merit (FOM) were 0.62, 0.3, and 0.76, respectively. The AI model showed no statistically significant difference in the observer performance test compared to 11 of 12 and 10 of 12 physicians, respectively. Conclusions: We developed an AI model trained on a limited dataset that demonstrated a rib fracture classification and detection performance comparable to that of an experienced physician.
RESUMEN
PURPOSE: To assess the effects of intravenous tranexamic acid (TXA) on visual clarity at various surgical stages and the correlation between the severity of synovitis and bursitis and the grade of visual clarity in patients undergoing arthroscopic shoulder surgery under an interscalene brachial plexus block. METHODS: This double-blind, randomized controlled study included patients undergoing arthroscopic rotator cuff repair. The TXA group underwent injection of a 100-mL mixture of 1,000 mg of TXA and normal saline solution intravenously whereas the control group was administered the same volume of normal saline solution at 10 minutes preoperatively. Visual clarity was rated according to a 3-grade visual clarity scoring system from grade 1 (clear) to grade 3 (poor) at 4 surgical stages (I, intra-articular soft-tissue procedures including synovectomy; II, acromioplasty; III, bursectomy; and IV, greater tuberoplasty). The primary outcome was arthroscopic visual clarity. The secondary outcomes were medications administered for hemodynamic stability, length of hospital stay, and thromboembolic events. RESULTS: Altogether, 63 patients were included in the study; they were divided into the TXA group, comprising 32 patients, and the control group, comprising 31 patients. The TXA group showed significantly better visual clarity than the control group (median [interquartile range], 1 [1-2] vs 2 [1-2]; P = .027) during stage I but not during stages II through IV. Spearman correlation analysis revealed a significant correlation between synovitis and visual clarity grade during synovectomy (correlation coefficient, 0.393; P = .001) but not between bursitis and visual clarity grade during bursectomy. Deep vein thrombosis and pulmonary embolism did not occur in either group. CONCLUSIONS: Intravenous TXA can improve visual clarity during intra-articular soft-tissue procedures, including synovectomy. However, it does not have a significant effect during acromioplasty, bursectomy, and greater tuberoplasty. TXA can be used to improve visual clarity in patients with suspected severe synovitis. LEVEL OF EVIDENCE: Level I, randomized controlled trial.
RESUMEN
BACKGROUND: Refractory angina pectoris (RAP) is a chronic, severe chest pain associated with coronary artery disease that cannot be resolved using optimal medical or surgical approaches. Spinal cord stimulation (SCS) is a suitable treatment option. Conventional waveforms of SCS have shown a potent effect on the tempering of RAP. However, SCS is associated with undesired paresthesia. The new burst SCS waveforms have been reported to have fewer adverse effects. CASE: We reviewed a case in which RAP was successfully treated with burst SCS in a middle-aged male, with a tonic waveform employed for breakthrough pain as needed. CONCLUSIONS: Appropriate use of tonic and burst stimulations according to the symptoms is expected to maximize the effect of relieving chest pain induced by RAP.
RESUMEN
BACKGROUND: Atelectasis may play a substantial role in the development of pneumonia. However, pneumonia has never been evaluated as an outcome of atelectasis in surgical patients. We aimed to determine whether atelectasis is related to an increased risk of postoperative pneumonia, intensive care unit (ICU) admission and hospital length of stay (LOS). METHODS: The electronic medical records of adult patients who underwent elective non-cardiothoracic surgery under general anesthesia between October 2019 and August 2020 were reviewed. They were divided into two groups: one who developed postoperative atelectasis (atelectasis group) and the other who did not (non-atelectasis group). The primary outcome was the incidence of pneumonia within 30 days after the surgery. The secondary outcomes were ICU admission rate and postoperative LOS. RESULTS: Patients in the atelectasis group were more likely to have risk factors for postoperative pneumonia including age, body mass index, a history of hypertension or diabetes mellitus and duration of surgery, compared with those in the non-atelectasis. Among 1,941 patients, 63 (3.2%) developed postoperative pneumonia; 5.1% in the atelectasis group and 2.8% in the non-atelectasis (P = 0.025). In multivariable analysis, atelectasis was associated with an increased risk of pneumonia (adjusted odds ratio, 2.33; 95% CI: 1.24 - 4.38; P = 0.008). Median postoperative LOS was significantly longer in the atelectasis group (7 [interquartile range: 5-10 days]) than in the non-atelectasis (6 [3-8] days) (P < 0.001). Adjusted median duration was also 2.19 days longer in the atelectasis group (ß, 2.19; 95% CI: 0.821 - 2.834; P < 0.001). ICU admission rate was higher in the atelectasis group (12.1% vs. 6.5%; P < 0.001), but it did not differ between the groups after adjustment for confounders (adjusted odds ratio, 1.52; 95% CI: 0.88 - 2.62; P = 0.134). CONCLUSION: Among patients undergoing elective non-cardiothoracic surgery, patients with postoperative atelectasis were associated with a 2.33-fold higher incidence of pneumonia and a longer LOS than those without atelectasis. This finding alerts the need for careful management of perioperative atelectasis to prevent or reduce the adverse events including pneumonia and the burden of hospitalizations. TRIAL REGISTRATION: None.
Asunto(s)
Neumonía , Atelectasia Pulmonar , Humanos , Neumonía/epidemiología , Neumonía/etiología , Atelectasia Pulmonar/epidemiología , Registros Electrónicos de Salud , Estudios Retrospectivos , Procedimientos Quirúrgicos ElectivosRESUMEN
BACKGROUND: According to a recent meta-analysis, in patients with a body mass index (BMI) ≥ 30, a high fraction of inhaled oxygen (FiO2) did not increase postoperative atelectasis. However, a high FiO2 generally increases the risk of postoperative atelectasis. Therefore, this study aimed to evaluate the effect of FiO2 on the development of atelectasis in obese patients using the modified lung ultrasound score (LUSS). METHODS: Patients were assigned to 4 groups: BMI ≥ 30: group A (n = 21) and group B (n = 20) and normal BMI: group C (n = 22) and group D (n = 21). Groups A and C were administered 100% O2 during preinduction and emergence and 50% O2 during anesthesia. Groups B and D received 40% O2 for anesthesia. The modified LUSS was assessed before and 20 min after arrival to the postanesthesia care unit (PACU). RESULTS: The difference between the modified LUSS preinduction and PACU was significantly higher in group A with a BMI ≥ 30 (P = .006); however, there was an insignificant difference between groups C and D in the normal BMI group (P = .076). CONCLUSION: High FiO2 had a greater effect on the development of atelectasis in obese patients than did low FiO2; however, in normal-weight individuals, FiO2 did not have a significant effect on postoperative atelectasis.