With the development of artificial intelligence, machine learning has been widely used in diagnosis of diseases. It is crucial to conduct diagnostic test accuracy studies and evaluate the performance of models reasonably to improve the accuracy of diagnosis. For machine learning-based diagnostic test accuracy studies, this paper introduces the principles of study design in the aspects of target conditions, selection of participants, diagnostic tests, reference standards and ethics.
The kinematic model parameter deviation is the main factor affecting the positioning accuracy of neurosurgical robots. To obtain more realistic kinematic model parameters, this paper proposes an automatic parameters identification and accuracy evaluation method. First, an identification equation contains all robot kinematics parameter was established. Second, a multiple-pivot strategy was proposed to find the relationship between end-effector and tracking marker. Then, the relative distance error and the inverse kinematic coincidence error were designed to evaluate the identification accuracy. Finally, an automatic robot parameter identification and accuracy evaluation system were developed. We tested our method on both laboratory prototypes and real neurosurgical robots. The results show that this method can realize the neurosurgical robot kinematics model parameters identification and evaluation stably and quickly. Using the identified parameters to control the robot can reduce the robot relative distance error by 33.96% and the inverse kinematics consistency error by 67.30%.
Comparative diagnostic test accuracy study, a type of diagnostic accuracy test, aims to compare accuracy of two or more index tests in a study. The application of GRADE in comparative test accuracy differs from single test accuracy, mainly including the selection of appropriate comparative study designs, additional criteria for judging risk of bias, and the consequences of using comparative measures of test accuracy. The study focuses on basic principles and methods of GRADE approach in systematic reviews of comparative test accuracy to promote the understanding and application of the method by domestic scholars.
Objective To investigate the accuracy of split three-dimensional (3D) printing patient-specific instrumentation (PSI) in medial open-wedge high tibial osteotomy (MOWHTO) and its effectiveness in treating medial knee osteoarthritis.MethodsClinical data of 14 patients with medial knee osteoarthritis and treated with split 3D printing PSI-assisted MOWHTO between August 2019 and August 2020 were retrospectively analyzed. There were 5 males and 9 females with an average age of 61 years (range, 43-68 years). The disease duration ranged from 1 to 16 years, with an average of 4.7 years. Preoperative Kellgren-Lawrence grading of knee osteoarthritis included grade Ⅰ in 2 cases, grade Ⅱ in 6 cases, and grade Ⅲ in 6 cases. The Hospital for Special Surgery (HSS) score was 59.1±4.9. The weight bearing line ratio (WBL), hip-knee-ankle angle (HKA), medial proximal tibial angle (MPTA), posterior tibial slope angle (PTSA), and actual correction angle of the lower limbs were measured on postoperative imaging data, and compared with the preoperative measurements and the designed target values to evaluate the accuracy of the PSI-assisted surgery. The patients’ knee function were evaluated with the HSS score at 3 and 6 months postoperatively, and at last follow-up.ResultsOne patient suffered from an incision exudation at 2 weeks postoperatively, and the incision healed after symptomatic treatment. The incisions of other patients healed by first intention. All patients were followed up 7-19 months (mean, 14.8 months). There was no neural injuries, hinge fracture, plate or screw fractures, loosening, or other complications. The WBL was maintained at the postoperative level according to the X-ray examination during the follow-up period. The WBL, HKA, MPTA, and PTSA were all within a satisfactory range after operation. The WBL, HKA, and MPTA were significantly improved when compared with the preoperative measurements (P<0.05). There was no significant difference between preoperative and postoperative PTSA (P>0.05). The differences in postoperative WBL, HKA, MPTA, and correction angle compared with the preoperative designed target values were not significant (P>0.05). The HSS scores were 69.2±4.7, 77.7±4.3, and 88.1±5.4 at 3 and 6 months postoperatively, and last follow-up, respectively. The differences between time points were significant (P<0.05).ConclusionFor patients with medial knee osteoarthritis, the split 3D printing PSI can assist the surgeon in MOWHTO with accurate osteotomy orthopedics and achieve favorable effectiveness.
The standards for reporting of diagnostic accuracy (STARD) was developed for guiding the reporting of diagnostic accuracy studies. Its newest version was published in 2015. The study mainly introduced the checklist, terminology, and diagram of the STARD 2015. It is hoped that domestic researchers could use the STARD 2015 to guide the implementation and reporting of their diagnostic accuracy studies, so as to improve the reporting quality of diagnostic accuracy studies.
Objective To compare the inter-observer agreement, consistency with the gold standard, and accuracy of the 2007 and 2018 versions of the AO/OTA classification in femoral intertrochanteric fractures, and to identify easily confused fracture types. Methods X-ray images of patients with femoral intertrochanteric fractures at Daping Hospital, Army Medical University between 2017 and 2021 were retrospectively collected. Three senior orthopedic trauma surgeons independently classified the fractures using both the 2007 and 2018 AO/OTA versions. A committee of five experts established the gold standard. Kappa coefficients were used to evaluate inter-observer agreement and consistency with the gold standard, while a confusion matrix was used to analyze accuracy and confusion points. Results A total of 236 patients were included. Regarding inter-observer agreement, the 2007 version was superior to the 2018 version at the subtype level [Kappa value: (0.473-0.739) vs. (0.322-0.658)], with no significant difference at the subgroup level [Kappa value: (0.234-0.453) vs. (0.204-0.442)]. Regarding consistency with the gold standard, the 2018 version was slightly better than the 2007 version [Kappa value: (0.332-0.629) vs. (0.269-0.581)] at the subgroup level. In terms of accuracy, the 2007 version showed higher accuracy at the subtype level (72.50% vs. 70.11%), whereas the 2018 version demonstrated better accuracy at the subgroup level (59.04% vs. 51.99%). The most easily confused subtypes in both versions were A1 and A2. At the subgroup level, A2.2 was the most easily confused type in both versions. Conclusions There is inconsistency in the application of both classification versions by surgeons. The 2007 version demonstrates slightly better inter-observer agreement at the subtype level, while the 2018 version shows better accuracy at the subgroup level. The A2.2 subgroup is a major point of confusion, suggesting that clinical attention should be focused on this type or that auxiliary tools may be needed to improve accuracy.
Objective To compare the effectiveness of robot-assisted and traditional freehand screw placement in the treatment of atlantoaxial dislocation. Methods The clinical data of 55 patients with atlantoaxial dislocation who met the selection criteria between January 2021 and January 2024 were retrospectively analyzed. According to different screw placement methods, they were divided into the traditional group (using the traditional freedhand screw placement, 31 cases) and the robot group (using the Mazor X robot-assisted screw placement, 24 cases). There was no significant difference in gender, age, body mass index, etiology, and preoperative visual analogue scale (VAS) score, cervical spine Japanese Orthopaedic Association (JOA) score between the two groups (P>0.05). The operation time, intraoperative blood loss, operation cost, and intraoperative complications were recorded and compared between the two groups. The VAS score and cervical spine JOA score were used to evaluate the improvement of pain and cervical spinal cord function before operation and at 1 month after operation. CT examination was performed at 3 days after operation, and the accuracy of screw placement was evaluated according to Neo grading criteria. Results All the 55 patients successfully completed the operation. The operation time, intraoperative blood loss, and operation cost in the robot group were significantly higher than those in the traditional group (P<0.05). A total of 220 C1 and C2 pedicle screws were inserted in the two groups, and 94 were inserted in the robot group, with an accuracy rate of 95.7%, among them, 2 were inserted by traditional freehand screw placement due to bleeding caused by intraoperative slip. And 126 pedicle screws were inserted in the traditional group, with an accuracy rate of 87.3%, which was significantly lower than that in the robot group (P<0.05). There were 1 case of venous plexus injury in the robot group and 3 cases in the traditional group, which improved after pressure hemostasis treatment. No other intraoperative complication such as vertebral artery injury or spinal cord injury occurred in both groups. All patients were followed up 4-16 months with an average of 6.6 months, and there was no significant difference in the follow-up time between the two groups (P>0.05). Postoperative neck pain significantly relieved in both groups, and neurological symptoms relieved to varying degrees. The VAS score and cervicle spine JOA score of both groups significantly improved at 1 month after operation when compared with preoperative scores (P<0.05), and there was no significant difference in the score change between the two groups (P>0.05). Conclusion In the treatment of atlantoaxial dislocation, the accuracy of robot-assisted screw placement is superior to the traditional freedhand screw placement.
ObjectiveTo compare the investigation results of compliance and accuracy of hand hygiene in medical staff achieved by Hospital Infection Management Department and Department Infection Management Teams, and analyze the reasons for differences of the results and take measures to improve the investigation ability of hand hygiene in hospitals. MethodsWe statistically analyzed the results of compliance and accuracy of hand hygiene from January to December 2013 investigated by the infection management department and 25 infection management teams. Both the hospital and departments used "WHO Standard Observation Form". Single-blind method was used to observe the implementation of hand hygiene in medical staff. ResultsThe hospital infection management department investigation showed that hand hygiene compliance and accuracy were 64.97% and 87.78%, respectively, while the investigation by infection management teams showed that hand hygiene compliance and accuracy were 90.54% and 93.37%, respectively. The differences between the investigation results of two-level organizations were statistically significant (χ2=286.2, P<0.001; χ2=532.6, P<0.001). ConclusionWe should take measures to enforce the training of hand hygiene implementation and the observation method, and improve the guidance and assessment, promote investigators' working responsibility and observation ability, so that the survey data can accurately reflect the actual situation to urge medical staff to form good hand hygiene habits.
Machine learning-based diagnostic tests have certain differences of measurement indicators with traditional diagnostic tests. In this paper, we elaborate the definitions, calculation methods and statistical inferences of common measurement indicators of machine learning-based diagnosis models in detail. We hope that this paper will be helpful for clinical researchers to better evaluate machine learning diagnostic models.
The correct and reasonable statistical analysis method can make the results of comparative diagnosis test accuracy more convincing. In this paper, the accuracy of diagnostic tests is divided into 2 forms: binary-scale outcomes and ordinal-scale/continuous-scale outcomes. Taking diagnostic indicators such as sensitivity, specificity, receiver operating characteristic (ROC) curves and area under curve (AUC) values as entry points, combined with examples, this paper introduced how to compare the diagnostic results of tests by parameter estimation and hypothesis testing, with the aim of providing references for the comparative diagnosis test accuracy.