A machine learning contest enhances automated freezing of gait detection and reveals time-of-day effects.

Freezing of gait (FOG) is a debilitating problem that markedly impairs the mobility and independence of 38-65% of people with Parkinson's disease. During a FOG episode, patients report that their feet are suddenly and inexplicably "glued" to the floor. The lack of a widely applicable, objective FOG detection method obstructs research and treatment. To address this problem, we organized a 3-month machine-learning contest, inviting experts from around the world to develop wearable sensor-based FOG detection algorithms. 1,379 teams from 83 countries submitted 24,862 solutions. The winning solutions demonstrated high accuracy, high specificity, and good precision in FOG detection, with strong correlations to gold-standard references. When applied to continuous 24/7 data, the solutions revealed previously unobserved patterns in daily living FOG occurrences. This successful endeavor underscores the potential of machine learning contests to rapidly engage AI experts in addressing critical medical challenges and provides a promising means for objective FOG quantification.

Programmable nanowrinkle-induced room-temperature exciton localization in monolayer WSe2.

Localized states in two-dimensional (2D) transition metal dichalcogenides (TMDCs) have been the subject of intense study, driven by potential applications in quantum information science. Despite the rapidly growing knowledge surrounding these emitters, their microscopic nature is still not fully understood, limiting their production and application. Motivated by this challenge, and by recent theoretical and experimental evidence showing that nanowrinkles generate strain-localized room-temperature emitters, we demonstrate a method to intentionally induce wrinkles with collections of stressors, showing that long-range wrinkle direction and position are controllable with patterned array design. Nano-photoluminescence (nano-PL) imaging combined with detailed strain modeling based on measured wrinkle topography establishes a correlation between wrinkle properties, particularly shear strain, and localized exciton emission. Beyond the array-induced wrinkles, nano-PL spatial maps further reveal that the strain environment around individual stressors is heterogeneous due to the presence of fine wrinkles that are less deterministic. At cryogenic temperatures, antibunched emission is observed, confirming that the nanocone-induced strain is sufficiently large for the formation of quantum emitters. At 300 K, detailed nanoscale hyperspectral images uncover a wide range of low-energy emission peaks originating from the fine wrinkles, and show that the states can be tightly confined to regions <10 nm, even in ambient conditions. These results establish a promising potential route towards realizing room temperature quantum emission in 2D TMDC systems.

Toxicity of fresh and aged anthropogenic smoke particles emitted from different burning conditions.

There is substantial evidence that photochemical reactions in the atmosphere cause physico-chemical transformation of combustion smoke, but how this processing modifies potential health effects in exposed populations is not well understood. Here we utilized a new approach to simulate photochemical aging of anthropogenic smoke emissions (a mixture of plastic, plywood, and cardboard smoke) from two different burning conditions (smoldering vs. flaming) and investigated their adverse outcomes associated with mutagenic activity and the relative potencies of different polycyclic aromatic hydrocarbons (PAHs). Aging resulted in increased oxygenated volatile organic compound (VOC) emissions but largely degraded particle-bound PAH components in the smoke. Chemical transformation during aging was more dramatic for flaming versus smoldering smoke. Due to the PAH degradation, mutagenicity of the aged smoke from flaming combustion was much lower (up to 4 times) than that of the fresh smoke on per-particle mass basis. However, on the basis of particle emitted per fuel mass burned, the aged and fresh smoke particles exhibited similar mutagenic activities, which were up to 3 times higher for smoldering versus flaming smoke emissions. Similarly, the PAH toxicity equivalent (PAH-TEQ) of the aged smoldering smoke was 3 times higher than that of the aged flaming smoke particles, suggesting that some PAHs (e.g., indeno[c,d]pyrene and benzo[b]fluoranthene) in the smoldering smoke were more photochemically stable during aging. These findings increase understanding of the evolution of smoke emitted at different burning conditions and the role of photochemical transformations on mutagenicity and PAH-induced toxicity.

Development of Volatility Distributions for Organic Matter in Biomass Burning Emissions.

The volatility distribution of organic emissions from biomass burning and other combustion sources can determine their atmospheric evolution due to partitioning/aging. The gap between measurements and models predicting secondary organic aerosol has been partially attributed to the absence of semi- and intermediate volatility organic compounds (S/I-VOC) in models and measurements. However, S/I-VOCs emitted from these sources and typically quantified using the volatility basis framework (VBS) are not well understood. For example, the amount and composition of S/I-VOCs and their variability across different biomass burning sources such as residential woodstoves, open field burns, and laboratory simulated open burning are uncertain. To address this, a novel filter-in-tube sorbent tube sampling method collected S/I-VOC samples from biomass burning experiments for a range of fuels and combustion conditions. Filter-in-tube samples were analyzed using thermal desorption-gas chromatography-mass spectrometry (TD/GC/MS) for compounds across a wide range of volatilities (saturation concentrations; -2 ≤ logC* ≤ 6). The S/I-VOC measurements were used to calculate volatility distributions for each emissions source. The distributions were broadly consistent across the sources with IVOCs accounting for 75% - 90% of the total captured organic matter, while SVOCs and LVOCs were responsible for 6% - 13% and 1% - 12%, respectively. The distributions and predicted partitioning were generally consistent with literature. Particulate matter emission factors spanned two orders of magnitude across the sources. This work highlights the potential of inferring gas-particle partitioning behavior of biomass burning emissions using filter-in-tube sorbent samples analyzed offline. This simplifies both sampling and analysis of S/I-VOCs for studies focused on capturing the full range of organics emitted.

Radiographic factors associated with inferior alveolar nerve exposure during mandibular third molar surgery and their influence on neurosensory deficit: A prospective study.

Introduction: The inferior alveolar nerve (IAN) can occasionally be observed in the extraction socket of the mandibular third molar (M3M) intraoperatively. Exposure of inferior alveolar neurovascular bundle during surgery primarily depends upon the absence of bony cortex between the canal and root of impacted third molar or either by existence of a very thin cortical lining between two which gets broken during luxation of tooth. Accurate anatomical relationship of inferior alveolar canal with root apex of impacted (M3M) and the location of canal can be determined by Cone beam computed tomography (CBCT). Material and methods: Initially 200 patients evaluated by Orthopantomogram (OPG) for anatomical relationship of IAN with impacted (M3M) and various radiographic risk factors for nerve injury. Among these 200, 75 showed the presence of two or more than two risk factors for IAN injury which then were further evaluated by using CBCT for presence or absence of cortex of canal and location of canal on buccal, lingual, inferior, and interradicular position. Conclusion: Cortex of canal is an important barrier between the root apex and inferior alveolar neurovascular bundle. Interruption of cortex on CBCT, the interradicularly and lingually positioned neurovascular bundle become a strong affirmation for intra operative nerve exposure during (M3M) surgery. Although its exposure is affected by various factors such as bone density, sex and age of patient, surgeon's expertise, operative tissue damage, post operative edema, surgical procedure, but neurosensory deficit do not occur simply after the exposure of neurovascular bundle.

Validation of Machine Learning-Based Automated Surgical Instrument Annotation Using Publicly Available Intraoperative Video.

BACKGROUND: Intraoperative tool movement data have been demonstrated to be clinically useful in quantifying surgical performance. However, collecting this information from intraoperative video requires laborious hand annotation. The ability to automatically annotate tools in surgical video would advance surgical data science by eliminating a time-intensive step in research. OBJECTIVE: To identify whether machine learning (ML) can automatically identify surgical instruments contained within neurosurgical video. METHODS: A ML model which automatically identifies surgical instruments in frame was developed and trained on multiple publicly available surgical video data sets with instrument location annotations. A total of 39 693 frames from 4 data sets were used (endoscopic endonasal surgery [EEA] [30 015 frames], cataract surgery [4670], laparoscopic cholecystectomy [2532], and microscope-assisted brain/spine tumor removal [2476]). A second model trained only on EEA video was also developed. Intraoperative EEA videos from YouTube were used for test data (3 videos, 1239 frames). RESULTS: The YouTube data set contained 2169 total instruments. Mean average precision (mAP) for instrument detection on the YouTube data set was 0.74. The mAP for each individual video was 0.65, 0.74, and 0.89. The second model trained only on EEA video also had an overall mAP of 0.74 (0.62, 0.84, and 0.88 for individual videos). Development costs were $130 for manual video annotation and under $100 for computation. CONCLUSION: Surgical instruments contained within endoscopic endonasal intraoperative video can be detected using a fully automated ML model. The addition of disparate surgical data sets did not improve model performance, although these data sets may improve generalizability of the model in other use cases.

Expert surgeons and deep learning models can predict the outcome of surgical hemorrhage from 1 min of video.

Major vascular injury resulting in uncontrolled bleeding is a catastrophic and often fatal complication of minimally invasive surgery. At the outset of these events, surgeons do not know how much blood will be lost or whether they will successfully control the hemorrhage (achieve hemostasis). We evaluate the ability of a deep learning neural network (DNN) to predict hemostasis control ability using the first minute of surgical video and compare model performance with human experts viewing the same video. The publicly available SOCAL dataset contains 147 videos of attending and resident surgeons managing hemorrhage in a validated, high-fidelity cadaveric simulator. Videos are labeled with outcome and blood loss (mL). The first minute of 20 videos was shown to four, blinded, fellowship trained skull-base neurosurgery instructors, and to SOCALNet (a DNN trained on SOCAL videos). SOCALNet architecture included a convolutional network (ResNet) identifying spatial features and a recurrent network identifying temporal features (LSTM). Experts independently assessed surgeon skill, predicted outcome and blood loss (mL). Outcome and blood loss predictions were compared with SOCALNet. Expert inter-rater reliability was 0.95. Experts correctly predicted 14/20 trials (Sensitivity: 82%, Specificity: 55%, Positive Predictive Value (PPV): 69%, Negative Predictive Value (NPV): 71%). SOCALNet correctly predicted 17/20 trials (Sensitivity 100%, Specificity 66%, PPV 79%, NPV 100%) and correctly identified all successful attempts. Expert predictions of the highest and lowest skill surgeons and expert predictions reported with maximum confidence were more accurate. Experts systematically underestimated blood loss (mean error - 131 mL, RMSE 350 mL, R2 0.70) and fewer than half of expert predictions identified blood loss > 500 mL (47.5%, 19/40). SOCALNet had superior performance (mean error - 57 mL, RMSE 295 mL, R2 0.74) and detected most episodes of blood loss > 500 mL (80%, 8/10). In validation experiments, SOCALNet evaluation of a critical on-screen surgical maneuver and high/low-skill composite videos were concordant with expert evaluation. Using only the first minute of video, experts and SOCALNet can predict outcome and blood loss during surgical hemorrhage. Experts systematically underestimated blood loss, and SOCALNet had no false negatives. DNNs can provide accurate, meaningful assessments of surgical video. We call for the creation of datasets of surgical adverse events for quality improvement research.

Deep Neural Networks Can Accurately Detect Blood Loss and Hemorrhage Control Task Success From Video.

BACKGROUND: Deep neural networks (DNNs) have not been proven to detect blood loss (BL) or predict surgeon performance from video. OBJECTIVE: To train a DNN using video from cadaveric training exercises of surgeons controlling simulated internal carotid hemorrhage to predict clinically relevant outcomes. METHODS: Video was input as a series of images; deep learning networks were developed, which predicted BL and task success from images alone (automated model) and images plus human-labeled instrument annotations (semiautomated model). These models were compared against 2 reference models, which used average BL across all trials as its prediction (control 1) and a linear regression with time to hemostasis (a metric with known association with BL) as input (control 2). The root-mean-square error (RMSE) and correlation coefficients were used to compare the models; lower RMSE indicates superior performance. RESULTS: One hundred forty-three trials were used (123 for training and 20 for testing). Deep learning models outperformed controls (control 1: RMSE 489 mL, control 2: RMSE 431 mL, R2 = 0.35) at BL prediction. The automated model predicted BL with an RMSE of 358 mL (R2 = 0.4) and correctly classified outcome in 85% of trials. The RMSE and classification performance of the semiautomated model improved to 260 mL and 90%, respectively. CONCLUSION: BL and task outcome classification are important components of an automated assessment of surgical performance. DNNs can predict BL and outcome of hemorrhage control from video alone; their performance is improved with surgical instrument presence data. The generalizability of DNNs trained on hemorrhage control tasks should be investigated.

Utility of the Simulated Outcomes Following Carotid Artery Laceration Video Data Set for Machine Learning Applications.

Importance: Surgical data scientists lack video data sets that depict adverse events, which may affect model generalizability and introduce bias. Hemorrhage may be particularly challenging for computer vision-based models because blood obscures the scene. Objective: To assess the utility of the Simulated Outcomes Following Carotid Artery Laceration (SOCAL)-a publicly available surgical video data set of hemorrhage complication management with instrument annotations and task outcomes-to provide benchmarks for surgical data science techniques, including computer vision instrument detection, instrument use metrics and outcome associations, and validation of a SOCAL-trained neural network using real operative video. Design, Setting, and Participants: For this quailty improvement study, a total of 75 surgeons with 1 to 30 years' experience (mean, 7 years) were filmed from January 1, 2017, to December 31, 2020, managing catastrophic surgical hemorrhage in a high-fidelity cadaveric training exercise at nationwide training courses. Videos were annotated from January 1 to June 30, 2021. Interventions: Surgeons received expert coaching between 2 trials. Main Outcomes and Measures: Hemostasis within 5 minutes (task success, dichotomous), time to hemostasis (in seconds), and blood loss (in milliliters) were recorded. Deep neural networks (DNNs) were trained to detect surgical instruments in view. Model performance was measured using mean average precision (mAP), sensitivity, and positive predictive value. Results: SOCAL contains 31 443 frames with 65 071 surgical instrument annotations from 147 trials with associated surgeon demographic characteristics, time to hemostasis, and recorded blood loss for each trial. Computer vision-based instrument detection methods using DNNs trained on SOCAL achieved a mAP of 0.67 overall and 0.91 for the most common surgical instrument (suction). Hemorrhage control challenges standard object detectors: detection of some surgical instruments remained poor (mAP, 0.25). On real intraoperative video, the model achieved a sensitivity of 0.77 and a positive predictive value of 0.96. Instrument use metrics derived from the SOCAL video were significantly associated with performance (blood loss). Conclusions and Relevance: Hemorrhage control is a high-stakes adverse event that poses unique challenges for video analysis, but no data sets of hemorrhage control exist. The use of SOCAL, the first data set to depict hemorrhage control, allows the benchmarking of data science applications, including object detection, performance metric development, and identification of metrics associated with outcomes. In the future, SOCAL may be used to build and validate surgical data science models.

Use of surgical video-based automated performance metrics to predict blood loss and success of simulated vascular injury control in neurosurgery: a pilot study.

OBJECTIVE: Experts can assess surgeon skill using surgical video, but a limited number of expert surgeons are available. Automated performance metrics (APMs) are a promising alternative but have not been created from operative videos in neurosurgery to date. The authors aimed to evaluate whether video-based APMs can predict task success and blood loss during endonasal endoscopic surgery in a validated cadaveric simulator of vascular injury of the internal carotid artery. METHODS: Videos of cadaveric simulation trials by 73 neurosurgeons and otorhinolaryngologists were analyzed and manually annotated with bounding boxes to identify the surgical instruments in the frame. APMs in five domains were defined-instrument usage, time-to-phase, instrument disappearance, instrument movement, and instrument interactions-on the basis of expert analysis and task-specific surgical progressions. Bounding-box data of instrument position were then used to generate APMs for each trial. Multivariate linear regression was used to test for the associations between APMs and blood loss and task success (hemorrhage control in less than 5 minutes). The APMs of 93 successful trials were compared with the APMs of 49 unsuccessful trials. RESULTS: In total, 29,151 frames of surgical video were annotated. Successful simulation trials had superior APMs in each domain, including proportionately more time spent with the key instruments in view (p < 0.001) and less time without hemorrhage control (p = 0.002). APMs in all domains improved in subsequent trials after the participants received personalized expert instruction. Attending surgeons had superior instrument usage, time-to-phase, and instrument disappearance metrics compared with resident surgeons (p < 0.01). APMs predicted surgeon performance better than surgeon training level or prior experience. A regression model that included APMs predicted blood loss with an R2 value of 0.87 (p < 0.001). CONCLUSIONS: Video-based APMs were superior predictors of simulation trial success and blood loss than surgeon characteristics such as case volume and attending status. Surgeon educators can use APMs to assess competency, quantify performance, and provide actionable, structured feedback in order to improve patient outcomes. Validation of APMs provides a benchmark for further development of fully automated video assessment pipelines that utilize machine learning and computer vision.

A systematic review of virtual reality for the assessment of technical skills in neurosurgery.

OBJECTIVE: Virtual reality (VR) and augmented reality (AR) systems are increasingly available to neurosurgeons. These systems may provide opportunities for technical rehearsal and assessments of surgeon performance. The assessment of neurosurgeon skill in VR and AR environments and the validity of VR and AR feedback has not been systematically reviewed. METHODS: A systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines was conducted through MEDLINE and PubMed. Studies published in English between January 1990 and February 2021 describing the use of VR or AR to quantify surgical technical performance of neurosurgeons without the use of human raters were included. The types and categories of automated performance metrics (APMs) from each of these studies were recorded. RESULTS: Thirty-three VR studies were included in the review; no AR studies met inclusion criteria. VR APMs were categorized as either distance to target, force, kinematics, time, blood loss, or volume of resection. Distance and time were the most well-studied APM domains, although all domains were effective at differentiating surgeon experience levels. Distance was successfully used to track improvements with practice. Examining volume of resection demonstrated that attending surgeons removed less simulated tumor but preserved more normal tissue than trainees. More recently, APMs have been used in machine learning algorithms to predict level of training with a high degree of accuracy. Key limitations to enhanced-reality systems include limited AR usage for automated surgical assessment and lack of external and longitudinal validation of VR systems. CONCLUSIONS: VR has been used to assess surgeon performance across a wide spectrum of domains. The VR environment can be used to quantify surgeon performance, assess surgeon proficiency, and track training progression. AR systems have not yet been used to provide metrics for surgeon performance assessment despite potential for intraoperative integration. VR-based APMs may be especially useful for metrics that are difficult to assess intraoperatively, including blood loss and extent of resection.

Primary and Photochemically Aged Aerosol Emissions from Biomass Cookstoves: Chemical and Physical Characterization.

Secondary organic aerosol (SOA) formation during photo-oxidation of primary emissions from cookstoves used in developing countries may make important contributions to their climate and air quality impacts. We present results from laboratory experiments with a field portable oxidation flow reactor (F-OFR) to study the evolution of emissions over hours to weeks of equivalent atmospheric aging. Lab tests, using dry red oak, measured fresh and aged emissions from a 3 stone fire (TSF), a "rocket" natural draft stove (NDS), and a forced draft gasifier stove (FDGS), in order of increasing modified combustion efficiency (MCE) and decreasing particulate matter emission factors (EF). SOA production was observed for all stoves/tests; organic aerosol (OA) enhancement factor ranged from 1.2 to 3.1, decreasing with increased MCE. In primary emissions, OA mass spectral fragments associated with oxygenated species (primary biomass burning markers) increased (decreased) with MCE; fresh OA from FDGS combustion was especially oxygenated. OA oxygenation increased with further oxidation for all stove emissions, even where minimal enhancement was observed. More efficient stoves emit particles with greater net direct specific warming than TSFs, with the difference increasing with aging. Our results show that the properties and evolution of cookstove emissions are a strong function of combustion efficiency and atmospheric aging.

Antibiotics in periodontal surgeries: A prospective randomised cross over clinical trial.

AIMS AND OBJECTIVES: (1) To evaluate the need of antibiotics in periodontal surgeries in reducing postsurgical infections and explore if antibiotics have any key role in reducing or eliminating inflammatory complications. (2) To establish the incidence of postoperative infections in relation to type of surgery and determine those factors, which may affect infection rates. MATERIALS AND METHODS: A prospective randomized double-blind cross over clinical study was carried out for a period of 1-year with predefined inclusion and exclusion criteria. All the patients included in the study for any periodontal surgery were randomly divided into three categories: Group A (prophylactic), Group B (therapeutic), and Group C (no antibiotics). Patients were followed up for 1-week after surgery on the day of suture removal and were evaluated for pain, swelling, fever, infection, delayed wound healing and any other significant findings. Appropriate statistical analysis was carried out to evaluate the objectives and P < 0.05 was considered as statistically significant. RESULTS: No infection was reported in any of 90 sites. Patients reported less pain and postoperative discomfort when prophylactic antibiotics were given. However, there were no statistical significant differences between the three groups. SUMMARY AND CONCLUSION: There was no postoperative infection reported in all the 90 sites operated in this study. The prevalence of postoperative infections following periodontal surgery is <1% and this low risk does not justify the routine use of systemic antimicrobials just to prevent infections. Use of prophylactic antibiotics may have role in prevention of inflammatory complication, but again not infection.