Modeling protective action decision-making in earthquakes by using explainable machine learning and video data

Earthquakes pose substantial threats to communities worldwide. Understanding how people respond to the fast-changing environment during earthquakes is crucial for reducing risks and saving lives. This study aims to study people's protective action decision-making in earthquakes by leveraging explainable machine learning and video data. Specifically, this study first collected real-world CCTV footage and video postings from social media platforms, and then identified and annotated changes in the environment and people's behavioral responses during the M7.1 2018 Anchorage earthquake. By using the fully annotated video data, we applied XGBoost, a widely-used machine learning method, to model and forecast people's protective actions (e.g., drop and cover, hold on, and evacuate) during the earthquake. Then, explainable machine learning techniques were used to reveal the complex, nonlinear relationships between different factors and people's choices of protective actions. Modeling results confirm that social and environmental cues played critical roles in affecting the probability of different protective actions. Certain factors, such as the earthquake shaking intensity and number of people shown in the environment, displayed evident nonlinear relationships with the probability of choosing to evacuate. These findings can help emergency managers and policymakers design more effective protective action recommendations during earthquakes.

Acute kidney injury requiring dialysis secondary to adenovirus nephritis in renal transplant recipient

Disseminated adenoviral infection is a serious problem, especially in an immunocompromised host. The disease carries a mortality rate reaching as high as 80%. It is seen most frequently in bone marrow transplant recipients, where it causes pneumonia and disseminated disease. In solid organ transplant recipients it causes graft infection. We report the case of a renal transplant recipient with disseminated adenoviral infection and acute kidney failure requiring dialysis. Reduction of immunosuppression and 1 dose of cidofovir were associated with resolution of viremia and viruria and return of kidney function to near baseline.

Visualizing levels of osteoblast differentiation by a two-color promoter-GFP strategy: Type I collagen-GFPcyan and osteocalcin-GFPtpz

A 3.9 kb DNA fragment of human osteocalcin promoter and 3.6 kb DNA fragment of the rat collagen type1a1 promoter linked with visually distinguishable GFP isomers, topaz and cyan, were used for multiplex analysis of osteoblast lineage progression. Three patterns of dual transgene expression can be appreciated in primary bone cell cultures derived from the transgenic mice and by histology of their corresponding bones. Our data support the interpretation that strong pOBCol3.6GFPcyan alone is found in newly formed osteoblasts, while strong pOBCol3.6GFPcyan and hOC-GFPtpz are present in osteoblasts actively making a new matrix. Osteoblasts expressing strong hOC-GFPtpz and weak pOBCol3.6GFPcyan are also present and may or may not be producing mineralized matrix. This multiplex approach reveals the heterogeneity within the mature osteoblast population that cannot be appreciated by current histological methods. It should be useful to identify and isolate populations of cells within an osteoblast lineage as they progress through stages of differentiation.

Low dose perphenazine and levodopa/carbidopa therapy in a patient with Parkinsonism and a psychotic illness

Psychological morbidity is a common consequence of both Parkinson's disease and its treatment with antiparkinsonian agents. The authors describe an unusual case of a patient with Parkinson's disease and a psychosis who was treated with levodopa/carbidopa and very low dose perphenazine. The case raises the issue whether patients with profound psychological reactions to antiparkinson agents may be maintained on antiparkinsonian therapy by the addition of phenothiazines.