Browse Articles

Droughts kill over 45,000 people yearly and affect the livelihoods of 55 million others worldwide, with climate change likely to worsen these effects. However, unlike other natural disasters (hurricanes, etc.), there is no early detection system that can predict droughts far enough in advance to be useful. Bora, Caulkins, and Joycutty tackle this issue by creating a drought prediction model.

The authors looked at using genetic algorithms to look at the Indian labor market and what features might best explain any variation seen. They found that features such as economic growth and household consumption, among others, best explained variation.

The authors found that SARIMAX-GARCH is more accurate than SARIMAX for load forecasting with respect to energy consumption.

In this work, the authors investigate the accuracy with which two different population growth models can predict population growth over time. They apply the Malthusian law or Logistic law to US population from 1951 until 2019. To assess how closely the growth model fits actual population data, a least-squared curve fit was applied and revealed that the Logistic law of population growth resulted in smaller sum of squared residuals. These findings are important for ensuring optimal population growth models are implemented to data as population forecasting affects a country's economic and social structure.

Did the COVID-19 pandemic and travel restrictions improve air quality? The authors investigate this question in New York City using existing pollution data and forecasting trends.

People with Type One diabetes often rely on Continuous Blood Glucose Monitors (CGMs) to track their blood glucose and manage their condition. Researchers are now working to help people with Type One diabetes more easily monitor their health by developing models that will future blood glucose levels based on CGM readings. Jalla and Ghanta tackle this issue by exploring the use of AI models to forecast blood glucose levels with CGM data.

Here, recognizing that the immune response to cancer results in biomarkers that can be used to assess the immune status of cancer patients, the authors investigated the concentrations of key cytokines (TH1 and TH2 cytokines) in healthy controls and cancer patients. They identified significant changes in resting and activated cytokine profiles, suggesting that data of biomarkers such as these could serve as a starting point for further treatment with regard to a patient's specific immune profile.

Here, the authors sought to develop a new metric to evaluate the efficacy of baseball pitchers using machine learning models. They found that the frequency of balls, was the most predictive feature for their walks/hits allowed per inning (WHIP) metric. While their machine learning models did not identify a defining trait, such as high velocity, spin rate, or types of pitches, they found that consistently pitching within the strike zone resulted in significantly lower WHIPs.

A common form of Acne is caused by a species of bacterium called Cutibacterium acnes. By using a predictive algorithm and structural analysis, the authors identified 5 small molecules with high affinity to growth factors in Catibacterium acnes. This has potential implications for supplemental skincare products.

Tertiary lymphoid structures (TLS) are lymph node-like structures that form at sites of inflammation, and their presence in cancer patients is predictive of a better clinical outcome. One significant obstacle to TLS formation is reduced immune cell infiltration into the tumor microenvironment (TME). Recent studies have shown that vasculature normalizing (VN) agents may override this defect to improve tissue perfusion and increased immune cell entry into the TME. However, their effects on immune cell and tumor cell phenotype remain understudied. Here the authors investigate whether treating tumor cells with VN would reduce their immunosuppressive phenotype and promote production of chemokine that recruit immune cells and foster TLS formation.