Gender Disparity in Surgical Device Patents: A Five-year Trend From Canada and the United States.

INTRODUCTION: Despite an increasing number of women pursuing careers in science, engineering, and medicine, gender disparities in patents persist. This study sought to analyze trends in inventor's gender for surgical device patents filed and granted in Canada and the United States from 2015 to 2019. METHODS: This study analyzed patents filed and granted by the Canadian Intellectual Property Office (CIPO) in the category of "Diagnosis; Surgery; Identification" and the United States Patent and Trademark Office (USPTO) in the category of "Surgery" from 2015 to 2019. The gender of the patent applicants was determined using a gender algorithm that predicts gender based on first names. Gender matches with names having a probability of less than 95% were excluded. RESULTS: We identified 14,312 inventors on patents filed and 12,737 inventors on patents granted by the CIPO for "Diagnosis; Surgery; Identification". In the USPTO category of "Surgery," we identified 75,890 inventors on patents filed and 44,842 inventors on patents granted. Female inventors accounted for 7%-10% of inventors from 2015 to 2019 for both patents filed and granted. The proportion of female inventors on patents granted was significantly lower than for patents filed for four of the 5 y analyzed for both the USPTO and CIPO. CONCLUSIONS: Female representation in surgical device patenting has stagnated, between 7 and 10%, from 2015 to 2019 in Canada and the United States. This underrepresentation of female inventors in surgical device patenting represents sizable gender disparity.

A Soft Labeling Approach to Develop Automated Algorithms that Incorporate Uncertainty in Pulmonary Opacification on Chest CT using COVID-19 Pneumonia.

RATIONALE AND OBJECTIVES: Hard data labels for automated algorithm training are binary and cannot incorporate uncertainty between labels. We proposed and evaluated a soft labeling methodology to quantify opacification and percent well-aerated lung (%WAL) on chest CT, that considers uncertainty in segmenting pulmonary opacifications and reduces labeling burden. MATERIALS AND METHODS: We retrospectively sourced 760 COVID-19 chest CT scans from five international centers between January and June 2020. We created pixel-wise labels for >27,000 axial slices that classify three pulmonary opacification patterns: pure ground-glass, crazy-paving, consolidation. We also quantified %WAL as the total area of lung without opacifications. Inter-user hard label variability was quantified using Shannon entropy (range=0-1.39, low-high entropy/variability). We incorporated a soft labeling and modeling cycle following an initial model with hard labels and compared performance using point-wise accuracy and intersection-over-union of opacity labels with ground-truth, and correlation with ground-truth %WAL. RESULTS: Hard labels annotated by 12 radiologists demonstrated large inter-user variability (3.37% of pixels achieved complete agreement). Our soft labeling approach increased point-wise accuracy from 60.0% to 84.3% (p=0.01) compared to hard labeling at predicting opacification type and area involvement. The soft label model accurately predicted %WAL (R=0.900) compared to the hard label model (R=0.856), but the improvement was not statistically significant (p=0.349). CONCLUSION: Our soft labeling approach increased accuracy for automated quantification and classification of pulmonary opacification on chest CT. Although we developed the model on COVID-19, our intent is broad application for pulmonary opacification contexts and to provide a foundation for future development using soft labeling methods.