Assessment of Automated Identification of Phases in Videos of Cataract Surgery Using Machine Learning and Deep Learning Techniques.

Importance: Competence in cataract surgery is a public health necessity, and videos of cataract surgery are routinely available to educators and trainees but currently are of limited use in training. Machine learning and deep learning techniques can yield tools that efficiently segment videos of cataract surgery into constituent phases for subsequent automated skill assessment and feedback. Objective: To evaluate machine learning and deep learning algorithms for automated phase classification of manually presegmented phases in videos of cataract surgery. Design, Setting, and Participants: This was a cross-sectional study using a data set of videos from a convenience sample of 100 cataract procedures performed by faculty and trainee surgeons in an ophthalmology residency program from July 2011 to December 2017. Demographic characteristics for surgeons and patients were not captured. Ten standard labels in the procedure and 14 instruments used during surgery were manually annotated, which served as the ground truth. Exposures: Five algorithms with different input data: (1) a support vector machine input with cross-sectional instrument label data; (2) a recurrent neural network (RNN) input with a time series of instrument labels; (3) a convolutional neural network (CNN) input with cross-sectional image data; (4) a CNN-RNN input with a time series of images; and (5) a CNN-RNN input with time series of images and instrument labels. Each algorithm was evaluated with 5-fold cross-validation. Main Outcomes and Measures: Accuracy, area under the receiver operating characteristic curve, sensitivity, specificity, and precision. Results: Unweighted accuracy for the 5 algorithms ranged between 0.915 and 0.959. Area under the receiver operating characteristic curve for the 5 algorithms ranged between 0.712 and 0.773, with small differences among them. The area under the receiver operating characteristic curve for the image-only CNN-RNN (0.752) was significantly greater than that of the CNN with cross-sectional image data (0.712) (difference, -0.040; 95% CI, -0.049 to -0.033) and the CNN-RNN with images and instrument labels (0.737) (difference, 0.016; 95% CI, 0.014 to 0.018). While specificity was uniformly high for all phases with all 5 algorithms (range, 0.877 to 0.999), sensitivity ranged between 0.005 (95% CI, 0.000 to 0.015) for the support vector machine for wound closure (corneal hydration) and 0.974 (95% CI, 0.957 to 0.991) for the RNN for main incision. Precision ranged between 0.283 and 0.963. Conclusions and Relevance: Time series modeling of instrument labels and video images using deep learning techniques may yield potentially useful tools for the automated detection of phases in cataract surgery procedures.

Supersymmetric exotic decays of the 125 GeV Higgs boson.

We reveal a set of novel decay topologies for the 125 GeV Higgs boson in supersymmetry which are initiated by its decay into a pair of neutralinos, and discuss their collider search strategies. This category of exotic Higgs decays is characterized by the collider signature: visible objects+E_{T}, with E_{T} dominantly arising from escaping dark matter particles. Their benchmark arises naturally in the Peccei-Quinn symmetry limit of the minimal supersymmetric standard model singlet extensions, which is typified by the coexistence of three light particles: singletlike scalar h_{1} and pseudoscalar a_{1}, and singlinolike neutralino χ_{1}, all with masses of ≲10 GeV, and the generic suppression of the exotic decays of the 125 GeV Higgs boson h_{2}→h_{1}h_{1}, a_{1}a_{1} and χ_{1}χ_{1}, however. As an illustration, we study the decay topology: h_{2}→χ_{1}χ_{2}, where the binolike χ_{2} decays to h_{1}χ_{1} or a_{1}χ_{1}, and h_{1}/a_{1}→ff[over ¯], with ff[over ¯]=µ^{+}µ^{-}, bb[over ¯]. In the dimuon case (m_{h_{1}/a_{1}}∼1 GeV), a statistical sensitivity of S/sqrt[B]>6σ can be achieved easily at the 8 TeV LHC, assuming σ(pp→Wh_{2})/σ(pp→Wh_{SM})Br(h_{2}→µ^{+}µ^{-}χ_{1}χ_{1})=0.1. In the bb[over ¯] case (m_{h_{1}/a_{1}}∼45 GeV), 600 fb^{-1} data at the 14 TeV LHC can lead to a statistical sensitivity of S/sqrt[B]>5σ, assuming σ(pp→Zh_{2})/σ(pp→Zh_{SM})Br(h_{2}→bb[over ¯]χ_{1}χ_{1})=0.5. These exotic decays open a new avenue for exploring new physics couplings with the 125 GeV Higgs boson at colliders.

The effects of whole body vibration therapy on bone mineral density and leg muscle strength in older adults: a systematic review and meta-analysis.

OBJECTIVE: A systematic review and meta-analysis of randomized controlled trials was undertaken to determine whether whole body vibration improves bone mineral density and leg muscle strength in older adults. DATA SOURCES: Sources included MEDLINE, CINAHL, EMBASE, PEDro, PubMed, Science Citation Index and the reference list of each eligible article. REVIEW METHODS: Article search and selection was performed independently by two researchers. The methodological quality of each selected article was rated by the PEDro scale. RESULTS: Thirteen randomized trials (18 articles) totalling 896 subjects fulfilled the selection criteria. Four were considered to have good or excellent methodological quality and the rest were rated as fair. Meta-analyses revealed that whole body vibration has no significant effect on hip or lumbar spine bone mineral density in older women when compared with no intervention or active exercise (P > 0.05). Whole body vibration, however, had a significant treatment effect on knee extension dynamic strength (standardized mean difference = 0.63, P = 0.006), leg extension isometric strength (standardized mean difference = 0.57, P = 0.003), and functional measures of leg muscle strength such as jumping height (standardized mean difference = 0.51, P = 0.010) and performance in sit-to-stand (standardized mean difference = 0.72, P < 0.001) among older adults compared with no intervention. CONCLUSION: Whole body vibration is beneficial for enhancing leg muscle strength among older adults. However, the review suggests that whole body vibration has no overall treatment effect on bone mineral density in older women. No randomized trial has examined the effects of whole body vibration on bone mineral density in older men.

Effects of whole-body vibration on sensorimotor performance in people with Parkinson disease: a systematic review.

BACKGROUND: Earlier studies show that whole-body vibration (WBV) has beneficial effects on neuromuscular performance in older adults and may be a viable treatment option for people with Parkinson disease (PD). PURPOSE: This systematic review was aimed at determining whether WBV improves sensorimotor performance in people with PD. DATA SOURCES: The sources used in this review were MEDLINE, the Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Excerpta Medica database (EMBASE), the Cochrane Database of Systematic Reviews, and the Physiotherapy Evidence Database (PEDro) (last searched in April 2010). STUDY SELECTION: Randomized and nonrandomized controlled studies examining the effects of WBV in people with PD were selected. Six studies fulfilled the selection criteria and were included in this review. DATA EXTRACTION: The PEDro score was used to evaluate methodological quality. The effects of WBV on various sensorimotor outcomes were noted. DATA SYNTHESIS: Methodological quality was rated as good for 1 study (PEDro score of 6), fair for 4 studies (PEDro score of 4 or 5), and poor for 1 study (PEDro score of 2). Two studies showed that, compared with no intervention, WBV treatment led to significant reductions in tremor and rigidity, as measured with the Unified Parkinson Disease Rating Scale (UPDRS). The findings for other UPDRS cluster scores were conflicting, however. Two studies showed that longer-term WBV (3-5 weeks) did not result in better sensorimotor outcomes than conventional exercise training. LIMITATIONS: The studies reviewed here are limited by their methodological weaknesses and small, heterogeneous samples. CONCLUSIONS: There is insufficient evidence to prove or refute the effectiveness of WBV in enhancing sensorimotor performance in people with PD (ie, grade D recommendations). More good-quality trials are needed to establish the clinical efficacy of WBV in improving sensorimotor function in people with PD.