From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.

Pancreatic cancer is a highly aggressive and difficult-to-detect cancer with a poor prognosis. Late diagnosis is common due to a lack of early symptoms, specific markers, and the challenging location of the pancreas. Imaging technologies have improved diagnosis, but there is still room for improvement in standardizing guidelines. Biopsies and histopathological analysis are challenging due to tumor heterogeneity. Artificial Intelligence (AI) revolutionizes healthcare by improving diagnosis, treatment, and patient care. AI algorithms can analyze medical images with precision, aiding in early disease detection. AI also plays a role in personalized medicine by analyzing patient data to tailor treatment plans. It streamlines administrative tasks, such as medical coding and documentation, and provides patient assistance through AI chatbots. However, challenges include data privacy, security, and ethical considerations. This review article focuses on the potential of AI in transforming pancreatic cancer care, offering improved diagnostics, personalized treatments, and operational efficiency, leading to better patient outcomes.

Conditions of Confinement in U.S. Carceral Facilities During COVID-19: Individuals Speak-Incarcerated During the COVID-19 Epidemic.

Objectives: We aimed to describe conditions of confinement among people incarcerated in the United States during the coronavirus disease 2019 (COVID-19) pandemic using a community-science data collection approach. Methods: We developed a web-based survey with community partners to collect information on confinement conditions (COVID-19 safety, basic needs, support). Formerly incarcerated adults released after March 1, 2020, or nonincarcerated adults in communication with an incarcerated person (proxy) were recruited through social media from July 25, 2020 to March 27, 2021. Descriptive statistics were estimated in aggregate and separately by proxy or formerly incarcerated status. Responses between proxy and formerly incarcerated respondents were compared using Chi-square or Fisher's exact tests based on α=0.05. Results: Of 378 responses, 94% were by proxy, and 76% reflected state prison conditions. Participants reported inability to physically distance (≥6 ft at all times; 92%), inadequate access to soap (89%), water (46%), toilet paper (49%), and showers (68%) for incarcerated people. Among those receiving prepandemic mental health care, 75% reported reduced care for incarcerated people. Responses were consistent between formerly incarcerated and proxy respondents, although responses by formerly incarcerated people were limited. Conclusions: Our findings suggest that a web-based community-science data collection approach through nonincarcerated community members is feasible; however, recruitment of recently released individuals may require additional resources. Our data obtained primarily through individuals in communication with an incarcerated person suggest COVID-19 safety and basic needs were not sufficiently addressed within some carceral settings in 2020-2021. The perspectives of incarcerated individuals should be leveraged in assessing crisis-response strategies.

Machine Learning Improves the Prediction of Responses to Immune Checkpoint Inhibitors in Metastatic Melanoma.

Pretreatment LDH is a standard prognostic biomarker for advanced melanoma and is associated with response to ICI. We assessed the role of machine learning-based radiomics in predicting responses to ICI and in complementing LDH for prognostication of metastatic melanoma. From 2008-2022, 79 patients with 168 metastatic hepatic lesions were identified. All patients had arterial phase CT images 1-month prior to initiation of ICI. Response to ICI was assessed on follow-up CT at 3 months using RECIST criteria. A machine learning algorithm was developed using radiomics. Maximum relevance minimum redundancy (mRMR) was used to select features. ROC analysis and logistic regression analyses evaluated performance. Shapley additive explanations were used to identify the variables that are the most important in predicting a response. mRMR selection revealed 15 features that are associated with a response to ICI. The machine learning model combining both radiomics features and pretreatment LDH resulted in better performance for response prediction compared to models that included radiomics or LDH alone (AUC of 0.89 (95% CI: [0.76-0.99]) vs. 0.81 (95% CI: [0.65-0.94]) and 0.81 (95% CI: [0.72-0.91]), respectively). Using SHAP analysis, LDH and two GLSZM were the most predictive of the outcome. Pre-treatment CT radiomic features performed equally well to serum LDH in predicting treatment response.

Drosophila insulin receptor regulates diabetes-induced mechanical nociceptive hypersensitivity.

Painful diabetic neuropathy (PDN) is one of the predominant complications of diabetes that causes numbness, tingling, and extreme pain sensitivity. Understanding the mechanisms of PDN pathogenesis is important for patient treatments. Here we report Drosophila models of diabetes-induced mechanical nociceptive hypersensitivity. Type 2 diabetes-like conditions and loss of insulin receptor function in multidendritic sensory neurons lead to mechanical nociceptive hypersensitivity. Furthermore, we also found that restoring insulin signaling in multidendritic sensory neurons can block diabetes-induced mechanical nociceptive hypersensitivity. Our work highlights the critical role of insulin signaling in nociceptive sensory neurons in the regulation of diabetes-induced nociceptive hypersensitivities.