Search

Objective Serum protein concentrations are diagnostically and prognostically valuable in cancer and other diseases, but their measurement via blood test is uncomfortable, inconvenient, and costly. This study investigates the possibility of predicting albumin, globulin, and albumin-globulin ratio from easily accessible physical characteristics (height, weight, Body Mass Index, age, gender) and vital signs (systolic blood pressure, diastolic blood pressure, mean arterial pressure, pulse pressure, pulse) using advanced machine learning techniques. Methods We obtained albumin concentration, globulin concentration, albumin-globulin ratio and predictor information (physical characteristics, vital signs) from physical exam records of 46,951 healthy adult participants in Hangzhou, China. We trained a computational model to predict each serum protein concentration from the predictors and then evaluated the predictive accuracy of each model on an independent portion of the dataset that was not used in model training. We also determined the relative importance of each feature within the model. Results Prediction accuracies were r=0.540 (95% CI: 0.539-0.540; Pearson r) for albumin, r=0.250 (95% CI: 0.249-0.251) for globulin, and r=0.373 (95% CI: 0.372-0.374) for albumin-globulin ratio. The most important predictive features were age (100% ± 0.0%; mean ± 95% CI of normalized importance), gender (34.4% ± 0.7%), pulse (25.6% ± 1.3%) and Body Mass Index (24.4% ± 2.3%) for albumin, pulse (83.7% ± 3.8%) for globulin, and age (99.2% ± 1.0%), gender (59.2% ± 1.7%), Body Mass Index (46.1% ± 4.2%) and height (40.0% ± 3.8%) for albumin-globulin ratio. Conclusions Our models predicted serum protein concentrations with appreciable accuracy showing the promise of this approach. Such models could serve to augment existing tools for identifying "at-risk" individuals for follow-up with a blood test.

Anecdotally accepted practice for evaluation of children with clinically suspected or radiographically proven wrist fracture in many urgent care and primary care settings is concurrent imaging of the forearm and elbow, despite the lack of evidence to support additional images. These additional radiographs may be an unnecessary source of radiation and use of health care resources. Our study assesses the necessity of additional radiographs of the forearm and elbow in children with wrist injury. We reviewed electronic medical records of children 17 and younger in whom wrist fracture was diagnosed in the emergency department. We identified the frequency with which additional radiographs of the proximal forearm and distal humerus demonstrated another site of acute injury. We identified 214 children with wrist fracture. Of those, 129 received additional radiographs of the elbow. Physical examination findings proximal to the wrist were documented in only 16 (12%) of these 129 children. A second injury proximal to the wrist fracture was present in 4 (3%) of these 129 children, all of whom exhibited physical examination findings at the elbow. No fractures were documented in children with a negative physical examination of the elbow. Although elbow fractures occasionally complicate distal forearm fractures in children, our findings indicate that a careful physical evaluation of the elbow is sufficient to guide further radiographic investigation. Routine radiographs of both the wrist and elbow in children with distal forearm fracture appear to be unnecessary when an appropriate physical examination is performed.

PurposeThe purpose of this paper is to propose a systematic approach to measuring, tracking, monitoring and continuously improving efficiency, availability and quality in healthcare operational settings.Design/methodology/approachThe proposed measure of healthcare operational effectiveness (HOE) consists of three indicators. They include an availability indicator, an quality indicator, and an efficiency indicator. The proposed approach tends to facilitate the systematic improvement at the different facets of operational effectiveness.FindingsThe proposed operational performance approach based on the HOE is consistent with the themes of performance measures and measurement reported in the literature.Research limitations/implicationsThe proposed healthcare operational effectiveness approach represents a serious attempt at quantifying the key facets of service effectiveness in healthcare operational settings. The validation of this performance assessment and measurement approach is worthy of future research.Practical implicationsThe approach advocated by the HOE has operational and strategic relevance to decision makers of healthcare organizations.Originality/valueThis paper presents a practical, systematic approach toward enhancing operational effectiveness in healthcare organizations. Relevant implementation issues associated with the proposed approach are also addressed.

The StarClose (Abbott Vascular, Redwood City, CA) arterial closure device utilizes an extraluminal nitinol clip to establish hemostasis. The purpose of this study was to determine the safety and efficacy of StarClose from a prospective peripheral arterial disease (PAD) registry. Over an 18-month time interval, 500 StarClose devices were used in 378 consecutive patients with symptomatic PAD after diagnostic and/or therapeutic endovascular cases. Patient demographics along with objective criteria including duplex ultrasound images, common femoral artery flow velocities, and ankle-brachial indexes (ABIs) were analyzed before and after StarClose placement. All outpatients received prophylactic antibiotic (one dose), periprocedural heparin (without protamine reversal), and antiplatelet therapy. Aspirin and clopidogrel (Plavix) was used for all patients undergoing therapeutic intervention. There were 378 patients who underwent procedures for aortoiliac or infrainguinal PAD, 99 of which were bilateral. Of the 500 arteriotomy closures, 296 were therapeutic interventions with sheath sizes of 6-8 F in the common femoral artery. The diagnostic studies (n = 204 arteriotomies) were performed with a 5F sheath. The technical success in achieving hemostasis was 97.2%; only 14 devices had a deployment problem requiring prolonged manual compression. Median length of stay was 157 min for patients done on an outpatient basis. Eleven of 260 (4.2%) on duplex follow-up had a doubling of the peak systolic velocity, only one of which was symptomatic. Late follow-up showed 42 of 360 (11.7%) with a drop in ABI >0.10. Nine major complications (2.0%) were identified in follow-up. The StarClose closure device has a low major complication rate and is safe and efficacious in patients with PAD, although stenosis at the arteriotomy site may occur. The device has achieved rapid hemostasis without need for anticoagulant reversal and requires significantly less time to ambulation than manual compression.