Justen, L. | Search bioRxiv

bioRxiv2026

Complementing Biosafety Levels With Societal Safety Levels

Biosafety level (BSL) classifications of biological agents have succeeded at minimizing occupational risk inside laboratories, but largely neglect the potential for onward transmission. As a result, many non-transmissible pathogens that could kill at most one individual per person exposed require greater containment than 1918 influenza, a virus that killed 50-100 million and might cause a new pandemic today. Laboratory workers are consenting professionals; the public is not. We recommend complementing BSLs with explicit thresholds for expected societal harm. Here we formalize Societal Safety Levels (SSLs) based on expected public fatalities per year, which we quantify from (i) estimated probability of laboratory release, (ii) likelihood of societal transmission, and (iii) consequence. SSLs would apply specifically to laboratory research with replication-competent potential pandemic pathogens, and would not restrict field surveillance, sequencing, or countermeasure development using non-replicating systems or pandemic-incapable agents. We find that applying the 0.1 expected deaths per facility-year standard common across multiple major-hazard industries to potential pandemic pathogen research would require marked safety improvements. Complementing BSLs with SSLs would establish enforceable accident-safety thresholds for pandemic-capable pathogens, bringing high-risk biological research into alignment with the quantitative safety standards that help other hazardous industries operate with public acceptance.

microbiology↗

bioRxiv2021

Identification of public submitted tick images: a neural network approach

Ticks and tick-borne diseases represent a growing public health threat in North America and Europe. The number of ticks, their geographical distribution, and the incidence of tick-borne diseases, like Lyme disease, are all on the rise. Accurate, real-time tick-image identification through a smartphone app or similar platform could help mitigate this threat by informing users of the risks associated and by providing researchers and public health agencies with better data on tick activity and geographic range. We report the development and validation of a convolutional neural network, a type of deep learning algorithm, trained on a dataset of more than 12,000 user-generated tick images. The model, which we call "TickIDNet," is trained to identify the three most common tick species found on humans in the U.S.: Amblyomma americanum, Dermacentor variabilis, and Ixodes scapularis. At baseline, TickIDNet scores an 87.8% identification accuracy across all three species, outperforming the accuracy of identifications done by a member of the general public or healthcare professionals. However, the model fails to match the performance of experts with formal entomological training. We find that image quality, particularly the size of the tick in the image (measured in pixels), plays a significant role in the networks ability to correctly identify an image: images where the tick is small are less likely to be correctly identified because of the small object detection problem in deep learning. TickIDNets performance can be increased by using confidence thresholds to introduce an "unsure" class and building image submission pipelines that encourage better quality photos. Our findings suggest that deep learning represents a promising frontier for tick identification that should be further explored and deployed as part of the toolkit for addressing the public health consequences of tick-borne diseases.

bioinformatics↗