Machine learning can guide food security efforts when primary data are not available.

Estimating how many people are food insecure and where they are is of fundamental importance for governments and humanitarian organizations to make informed and timely decisions on relevant policies and programmes. In this study, we propose a machine learning approach to predict the prevalence of people with insufficient food consumption and of people using crisis or above-crisis food-based coping when primary data are not available. Making use of a unique global dataset, the proposed models can explain up to 81% of the variation in insufficient food consumption and up to 73% of the variation in crisis or above food-based coping levels. We also show that the proposed models can nowcast the food security situation in near real time and propose a method to identify which variables are driving the changes observed in predicted trends-which is key to make predictions serviceable to decision-makers.

Alarming Drop in Early Stage Colorectal Cancer Diagnoses After COVID-19 Outbreak: A Real-World Analysis from the Italian COVID-DELAY Study.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has triggered the disruption of health care on a global scale. With Italy tangled up in the pandemic response, oncology care has been largely diverted and cancer screenings suspended. Our multicenter Italian study aimed to evaluate whether COVID-19 has impacted access to diagnosis, staging, and treatment for patients newly diagnosed with colorectal cancer (CRC), compared with pre-pandemic time. METHODS: All consecutive new CRC patients referred to 8 Italian oncology institutions between March and December 2020 were included. Access rate and temporal intervals between date of symptoms onset, radiological and cytohistological diagnosis, treatment start and first radiological evaluation were analyzed and compared with the same months of 2019. RESULTS: A reduction (29%) in newly diagnosed CRC cases was seen when compared with 2019 (360 vs 506). New CRC patients in 2020 were less likely to be diagnosed with early stage (stages I-II-III) CRC (63% vs 78%, P < .01). Gender and sidedness were similar regardless of the year. The percentage of tumors with any mutation among BRAF, NRAS, and KRAS genes were significantly different between the 2 years (61% in 2020 vs 50% in 2019, P = .04). Timing of access to cancer diagnosis, staging, and treatment for patients with CRC has not been negatively affected by the pandemic. Significantly shorter temporal intervals were observed between symptom onset and first oncological appointment (69 vs 79 days, P = .01) and between histological diagnosis and first oncological appointment (34 vs 42 days, P < .01) during 2020 compared with 2019. Fewer CRC cases were discussed in multidisciplinary meetings during 2020 (38% vs 50%, P = .01). CONCLUSIONS: Our data highlight a significant drop in CRC diagnosis after COVID-19, especially for early stage disease. The study also reveals a remarkable setback in the multidisciplinary management of patients with CRC. Despite this, Italian oncologists were able to ensure diagnostic-therapeutic pathways proper operation after March 2020.

Liquid Biopsy at Home: Delivering Precision Medicine for Patients with Cancer During the COVID-19 Pandemic.

CoronaVirus disease-2019 has changed the delivery of health care worldwide and the pandemic has challenged oncologists to reorganize cancer care. Recently, progress has been made in the field of precision medicine to provide to patients with cancer the best therapeutic choice for their individual needs. In this context, the Foundation Medicine (FMI)-Liquid@Home project has emerged as a key weapon to deal with the new pandemic situation. FoundationOne Liquid Assay (F1L) is a next-generation sequences-based liquid biopsy service, able to detect 324 molecular alterations and genomic signatures, from May 2020 available at patients' home (FMI-Liquid@Home). We analyzed time and costs saving for patients with cancer, their caregivers and National Healthcare System (NHS) with FMI-Liquid@Home versus F1L performed at our Department. Different variables have been evaluated. Between May 2020 and August 2021, 218 FMI-Liquid@Home were performed for patients with cancer in Italy. Among these, our Department performed 153 FMI-Liquid@Home with the success rate of 98% (vs. 95% for F1L in the hospital). Time saving for patients and their caregivers was 494.86 and 427.36 hours, respectively, and costs saving was 13 548.70€. Moreover, for working people these savings were 1084.71 hours and 31 239.65€, respectively. In addition, the total gain for the hospital was 163.5 hours and 6785€, whereas for NHS was 1084.71 hours and 51 573.60€, respectively. FMI-Liquid@Home service appears to be useful and convenient allowing time and costs saving for patients, caregivers, and NHS. Born during the COVID-19 pandemic, it could be integrated in oncological daily routine in the future. Therefore, additional studies are needed to better understand the overall gain and how to integrate this service in different countries.