Only strict quarantine measures can curb the coronavirus disease (COVID-19) outbreak in Italy, 2020.

Several Italian towns are under lockdown to contain the COVID-19 outbreak. The level of transmission reduction required for physical distancing interventions to mitigate the epidemic is a crucial question. We show that very high adherence to community quarantine (total stay-home policy) and a small household size is necessary for curbing the outbreak in a locked-down town. The larger the household size and amount of time in the public, the longer the lockdown period needed.

European projections of West Nile virus transmission under climate change scenarios.

West Nile virus (WNV), a mosquito-borne zoonosis, has emerged as a disease of public health concern in Europe. Recent outbreaks have been attributed to suitable climatic conditions for its vectors favoring transmission. However, to date, projections of the risk for WNV expansion under climate change scenarios is lacking. Here, we estimate the WNV-outbreaks risk for a set of climate change and socioeconomic scenarios. We delineate the potential risk-areas and estimate the growth in the population at risk (PAR). We used supervised machine learning classifier, XGBoost, to estimate the WNV-outbreak risk using an ensemble climate model and multi-scenario approach. The model was trained by collating climatic, socioeconomic, and reported WNV-infections data (2010-22) and the out-of-sample results (1950-2009, 2023-99) were validated using a novel Confidence-Based Performance Estimation (CBPE) method. Projections of area specific outbreak risk trends, and corresponding population at risk were estimated and compared across scenarios. Our results show up to 5-fold increase in West Nile virus (WNV) risk for 2040-60 in Europe, depending on geographical region and climate scenario, compared to 2000-20. The proportion of disease-reported European land areas could increase from 15% to 23-30%, putting 161 to 244 million people at risk.  Across scenarios, Western Europe appears to be facing the largest increase in the outbreak risk of WNV. The increase in the risk is not linear but undergoes periods of sharp changes governed by climatic thresholds associated with ideal conditions for WNV vectors. The increased risk will require a targeted public health response to manage the expansion of WNV with climate change in Europe.

Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers.

Background: In Europe, the frequency, intensity, and geographic range of West Nile virus (WNV)-outbreaks have increased over the past decade, with a 7.2-fold increase in 2018 compared to 2017, and a markedly expanded geographic area compared to 2010. The reasons for this increase and range expansion remain largely unknown due to the complexity of the transmission pathways and underlying disease drivers. In a first, we use advanced artificial intelligence to disentangle the contribution of eco-climatic drivers to WNV-outbreaks across Europe using decade-long (2010-2019) data at high spatial resolution. Methods: We use a high-performance machine learning classifier, XGBoost (eXtreme gradient boosting) combined with state-of-the-art XAI (eXplainable artificial intelligence) methodology to describe the predictive ability and contribution of different drivers of the emergence and transmission of WNV-outbreaks in Europe, respectively. Findings: Our model, trained on 2010-2017 data achieved an AUC (area under the receiver operating characteristic curve) score of 0.97 and 0.93 when tested with 2018 and 2019 data, respectively, showing a high discriminatory power to classify a WNV-endemic area. Overall, positive summer/spring temperatures anomalies, lower water availability index (NDWI), and drier winter conditions were found to be the main determinants of WNV-outbreaks across Europe. The climate trends of the preceding year in combination with eco-climatic predictors of the first half of the year provided a robust predictive ability of the entire transmission season ahead of time. For the extraordinary 2018 outbreak year, relatively higher spring temperatures and the abundance of Culex mosquitoes were the strongest predictors, in addition to past climatic trends. Interpretation: Our AI-based framework can be deployed to trigger rapid and timely alerts for active surveillance and vector control measures in order to intercept an imminent WNV-outbreak in Europe. Funding: The work was partially funded by the Swedish Research Council FORMAS for the project ARBOPREVENT (grant agreement 2018-05973).

Rapid, label-free detection of diffuse glioma recurrence using intraoperative stimulated Raman histology and deep neural networks.

BACKGROUND: Detection of glioma recurrence remains a challenge in modern neuro-oncology. Noninvasive radiographic imaging is unable to definitively differentiate true recurrence versus pseudoprogression. Even in biopsied tissue, it can be challenging to differentiate recurrent tumor and treatment effect. We hypothesized that intraoperative stimulated Raman histology (SRH) and deep neural networks can be used to improve the intraoperative detection of glioma recurrence. METHODS: We used fiber laser-based SRH, a label-free, nonconsumptive, high-resolution microscopy method (<60 sec per 1 × 1 mm2) to image a cohort of patients (n = 35) with suspected recurrent gliomas who underwent biopsy or resection. The SRH images were then used to train a convolutional neural network (CNN) and develop an inference algorithm to detect viable recurrent glioma. Following network training, the performance of the CNN was tested for diagnostic accuracy in a retrospective cohort (n = 48). RESULTS: Using patch-level CNN predictions, the inference algorithm returns a single Bernoulli distribution for the probability of tumor recurrence for each surgical specimen or patient. The external SRH validation dataset consisted of 48 patients (recurrent, 30; pseudoprogression, 18), and we achieved a diagnostic accuracy of 95.8%. CONCLUSION: SRH with CNN-based diagnosis can be used to improve the intraoperative detection of glioma recurrence in near-real time. Our results provide insight into how optical imaging and computer vision can be combined to augment conventional diagnostic methods and improve the quality of specimen sampling at glioma recurrence.

COVID-19 healthcare demand and mortality in Sweden in response to non-pharmaceutical mitigation and suppression scenarios.

BACKGROUND: While the COVID-19 outbreak in China now appears suppressed, Europe and the USA have become the epicentres, both reporting many more deaths than China. Responding to the pandemic, Sweden has taken a different approach aiming to mitigate, not suppress, community transmission, by using physical distancing without lockdowns. Here we contrast the consequences of different responses to COVID-19 within Sweden, the resulting demand for care, intensive care, the death tolls and the associated direct healthcare related costs. METHODS: We used an age-stratified health-care demand extended SEIR (susceptible, exposed, infectious, recovered) compartmental model for all municipalities in Sweden, and a radiation model for describing inter-municipality mobility. The model was calibrated against data from municipalities in the Stockholm healthcare region. RESULTS: Our scenario with moderate to strong physical distancing describes well the observed health demand and deaths in Sweden up to the end of May 2020. In this scenario, the intensive care unit (ICU) demand reaches the pre-pandemic maximum capacity just above 500 beds. In the counterfactual scenario, the ICU demand is estimated to reach ∼20 times higher than the pre-pandemic ICU capacity. The different scenarios show quite different death tolls up to 1 September, ranging from 5000 to 41 000, excluding deaths potentially caused by ICU shortage. Additionally, our statistical analysis of all causes excess mortality indicates that the number of deaths attributable to COVID-19 could be increased by 40% (95% confidence interval: 0.24, 0.57). CONCLUSION: The results of this study highlight the impact of different combinations of non-pharmaceutical interventions, especially moderate physical distancing in combination with more effective isolation of infectious individuals, on reducing deaths, health demands and lowering healthcare costs. In less effective mitigation scenarios, the demand on ICU beds would rapidly exceed capacity, showing the tight interconnection between the healthcare demand and physical distancing in the society. These findings have relevance for Swedish policy and response to the COVID-19 pandemic and illustrate the importance of maintaining the level of physical distancing for a longer period beyond the study period to suppress or mitigate the impacts from the pandemic.

Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks.

Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery1. The existing workflow for intraoperative diagnosis based on hematoxylin and eosin staining of processed tissue is time, resource and labor intensive2,3. Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed, pathology workforce4. In the present study, we report a parallel workflow that combines stimulated Raman histology (SRH)5-7, a label-free optical imaging method and deep convolutional neural networks (CNNs) to predict diagnosis at the bedside in near real-time in an automated fashion. Specifically, our CNNs, trained on over 2.5 million SRH images, predict brain tumor diagnosis in the operating room in under 150 s, an order of magnitude faster than conventional techniques (for example, 20-30 min)2. In a multicenter, prospective clinical trial (n = 278), we demonstrated that CNN-based diagnosis of SRH images was noninferior to pathologist-based interpretation of conventional histologic images (overall accuracy, 94.6% versus 93.9%). Our CNNs learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors. In addition, we implemented a semantic segmentation method to identify tumor-infiltrated diagnostic regions within SRH images. These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complementary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.