Forecasting transitions in the state of food security with machine learning using transferable features.

Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

Quantification of lethargy in the neuro-ICU: the 60-Second Test.

The authors evaluated the 60-Second Test (SST), a brief test of mental concentration, as a supplement to the Glasgow Coma Scale (GCS) for monitoring verbally responsive patients in the neuro-intensive care unit. The SST demonstrated excellent reliability and was abnormal in 79% of patients assigned a top GCS score of 15. However, both tests had poor responsiveness to clinically identified changes in level of consciousness (LOC). The SST is sensitive to subtle alterations in LOC but, like the GCS, may have limitations as a monitoring tool in the neurocritical care setting.

Diagnosis and management of increased intracranial pressure.

Increased intracranial pressure (ICP) is a pathological state common to a variety of neurological diseases, all of which are characterized by the addition of volume to the skull contents. Elevated ICP may lead to brain damage or death by two principle mechanisms: 1) global hypoxic-ischemic injury, as a consequence of reduced cerebral perfusion pressure (CPP) and cerebral blood flow; and 2) mechanical distortion and compression of brain tissue as a result of intracranial mass effect and ICP compartmentalization. All ICP therapies have as a goal, reduction of intracranial volume. In unmonitored patients with acute neurological deterioration, head elevation, hyperventilation, and mannitol (1g/kg) can rapidly lower ICP. Fluid-coupled ventricular catheters and fiberoptic transducers are the most accurate and reliable instruments for measuring ICP. In monitored patients, the treatment of critically raised ICP should proceed in an orderly step-wise fashion: 1) consideration of neuroimaging to exclude a new surgically operable lesion; 2) intravenous sedation to attain a quiet motionless state; 3) manipulation of blood pressure to keep CPP >70 and <120; 4) mannitol infusion; 5) moderate hyperventilation (P(CO2) 26 to 30 mmHg); and 6) high-dose pentobarbital therapy. Application of moderate hypothermia (32 to 33 degrees C) shows promise as a newer method for treating refractory ICP. Placement of an ICP monitor is the critical first step in management of ICP. Treatment is best done using a stepwise protocol, with careful attention to sedation and CPP control prior to using mannitol and hyperventilation.