http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Munetoshi Akazawa,Kazunori Hashimoto,Katsuhiko Noda,Kaname Yoshida 대한산부인과학회 2021 Obstetrics & Gynecology Science Vol.64 No.3
ObjectiveMost women with early stage endometrial cancer have a favorable prognosis. However, there is a subset of patientswho develop recurrence. In addition to the pathological stage, clinical and therapeutic factors affect the probabilityof recurrence. Machine learning is a subtype of artificial intelligence that is considered effective for predictive tasks. We tried to predict recurrence in early stage endometrial cancer using machine learning methods based on clinicaldata. MethodsWe enrolled 75 patients with early stage endometrial cancer (International Federation of Gynecology and Obstetricsstage I or II) who had received surgical treatment at our institute. A total of 5 machine learning classifiers were used,including support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and boostedtree, to predict the recurrence based on 16 parameters (age, body mass index, gravity/parity, hypertension/diabetic,stage, histological type, grade, surgical content and adjuvant chemotherapy). We analyzed the classification accuracyand the area under the curve (AUC). ResultsThe highest accuracy was 0.82 for SVM, followed by 0.77 for RF, 0.74 for LR, 0.66 for DT, and 0.66 for boosted trees. The highest AUC was 0.53 for LR, followed by 0.52 for boosted trees, 0.48 for DT, and 0.47 for RF. Therefore, the bestpredictive model for this analysis was LR. ConclusionThe performance of the machine learning classifiers was not optimal owing to the small size of the dataset. The useof a machine learning model made it possible to predict recurrence in early stage endometrial cancer.
Jun Omori,Osamu Goto,Kazutoshi Higuchi,Takamitsu Umeda,Naohiko Akimoto,Masahiro Suzuki,Kumiko Kirita,Eriko Koizumi,Hiroto Noda,Teppei Akimoto,Mitsuru Kaise,Katsuhiko Iwakiri 대한소화기내시경학회 2020 Clinical Endoscopy Vol.53 No.3
Background/Aims: Three-dimensional (3D) flexible endoscopy, a new imaging modality that provides a stereoscopic view, canfacilitate endoscopic hand suturing (EHS), a novel intraluminal suturing technique. This ex-vivo pilot study evaluated the usefulnessof 3D endoscopy in EHS. Methods: Four endoscopists (two certified, two non-certified) performed EHS in six sessions on a soft resin pad. Each sessioninvolved five stitches, under alternating 3D and two-dimensional (2D) conditions. Suturing time (sec/session), changes in suturingtime, and accuracy of suturing were compared between 2D and 3D conditions. Results: The mean suturing time was shorter in 3D than in 2D (9.8±3.4 min/session vs. 11.2±5.1 min/session) conditions and EHSwas completed faster in 3D conditions, particularly by non-certified endoscopists. The suturing speed increased as the 3D sessionsprogressed. Error rates (failure to grasp the needle, failure to thread the needle, and puncture retrial) in the 3D condition were lowerthan those in the 2D condition, whereas there was no apparent difference in deviation distance. Conclusions: 3D endoscopy may contribute to increasing the speed and accuracy of EHS in a short time period. Stereoscopicviewing during 3D endoscopy may help in efficient skill acquisition for EHS, particularly among novice endoscopists.