Sepsis mortality prediction with Machine Learning Tecniques.

OBJECTIVE: To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU). DESIGN: Cross-sectional descriptive study. SETTING: The Intensive Care Units (ICUs) of three Hospitals from Murcia (Spain) and patients from the MIMIC III open-access database. PATIENTS: 180 patients diagnosed with sepsis in the ICUs of three hospitals and a total of 4559 patients from the MIMIC III database. MAIN VARIABLES OF INTEREST: Age, weight, heart rate, respiratory rate, temperature, lactate levels, partial oxygen saturation, systolic and diastolic blood pressure, pH, urine, and potassium levels. RESULTS: A random forest classification model was calculated using the local and MIMIC III databases. The sensitivity of the model of our database, considering all the variables classified as important by the random forest, was 95.45%, the specificity was 100%, the accuracy was 96.77%, and an AUC of 95%. . In the case of the model based on the MIMIC III database, the sensitivity was 97.55%, the specificity was 100%, and the precision was 98.28%, with an AUC of 97.3%. CONCLUSIONS: According to random forest classification in both databases, lactate levels, urine output and variables related to acid.base equilibrium were the most important variable in mortality due to sepsis in the ICU. The potassium levels were more critical in the MIMIC III database than the local database.

Filial cannibalism of Nabis pseudoferus is not evolutionarily optimal foraging strategy.

Using a recursion model with real parameters of Nabis pseudoferus, we show that its filial cannibalism is an optimal foraging strategy for life reproductive success, but it is not an evolutionarily optimal foraging strategy, since it cannot maximize the descendant's number at the end of the reproductive season. Cannibalism is evolutionarily rational, when the number of newborn offspring produced from the cannibalized offspring can compensate the following two effects: (a) The cannibalistic lineage wastes time, since the individuals hatched from eggs produced by cannibalism start to reproduce later. (b) Cannibalism eliminates not only one offspring, but also all potential descendants from the cannibalized offspring during the rest of reproductive season. In our laboratory trials, from conspecific prey Nabis pseudoferus did not produce newborn nymphs enough to compensate the above two effects.

State-controlled epidemic in a game against a novel pathogen.

The pandemic reminded us that the pathogen evolution still has a serious effect on human societies. States, however, can prepare themselves for the emergence of a novel pathogen with unknown characteristics by analysing potential scenarios. Game theory offers such an appropriate tool. In our game-theoretical framework, the state is playing against a pathogen by introducing non-pharmaceutical interventions to fulfil its socio-political goals, such as guaranteeing hospital care to all needed patients, keeping the country functioning, while the applied social restrictions should be as soft as possible. With the inclusion of activity and economic sector dependent transmission rate, optimal control of lockdowns and health care capacity management is calculated. We identify the presence and length of a pre-symptomatic infectious stage of the disease to have the greatest effect on the probability to cause a pandemic. Here we show that contrary to intuition, the state should not strive for the great expansion of its health care capacities even if its goal is to provide care for all requiring it and minimize the cost of lockdowns.

Diagnosis of Subclinical Keratoconus Based on Machine Learning Techniques.

(1) Background: Keratoconus is a non-inflammatory corneal disease characterized by gradual thinning of the stroma, resulting in irreversible visual quality and quantity decline. Early detection of keratoconus and subsequent prevention of possible risks are crucial factors in its progression. Random forest is a machine learning technique for classification based on the construction of thousands of decision trees. The aim of this study was to use the random forest technique in the classification and prediction of subclinical keratoconus, considering the metrics proposed by Pentacam and Corvis. (2) Methods: The design was a retrospective cross-sectional study. A total of 81 eyes of 81 patients were enrolled: sixty-one eyes with healthy corneas and twenty patients with subclinical keratoconus (SCKC): This initial stage includes patients with the following conditions: (1) minor topographic signs of keratoconus and suspicious topographic findings (mild asymmetric bow tie, with or without deviation; (2) average K (mean corneal curvature) < 46, 5 D; (3) minimum corneal thickness (ECM) > 490 µm; (4) no slit lamp found; and (5) contralateral clinical keratoconus of the eye. Pentacam topographic and Corvis biomechanical variables were collected. Decision tree and random forest were used as machine learning techniques for classifications. Random forest performed a ranking of the most critical variables in classification. (3) Results: The essential variable was SP A1 (stiffness parameter A1), followed by A2 time, posterior coma 0°, A2 velocity and peak distance. The model efficiently predicted all patients with subclinical keratoconus (Sp = 93%) and was also a good model for classifying healthy cases (Sen = 86%). The overall accuracy rate of the model was 89%. (4) Conclusions: The random forest model was a good model for classifying subclinical keratoconus. The SP A1 variable was the most critical determinant in classifying and identifying subclinical keratoconus, followed by A2 time.

Artiflex foldable lens for myopia correction results of 10 years of follow-up.

PURPOSE: The aim of this study was to evaluate the long-term efficacy and safety of the Artiflex® lens implant and to follow the evolution of the number of corneal endothelial cells over time. DESIGN: It was a retrospective study of an observational case series of patients who underwent surgery at "The INVISION Ophthalmic Hospital" (Almería, Spain) in 2007 and who were followed for 10 years. METHODS: Setting: Clinical practice. Study population included 53 eyes of 30 patients who underwent an Artiflex® lens implant for the correction of myopia from -4 to -14 D. Each patient included in this study had stable myopia for at least 2 years and a contraindication for corneal refractive surgery. The efficacy index was defined as the quotient between uncorrected distance visual acuity postoperative and best-corrected distance visual acuity (BCDVA) preoperative. The safety index was calculated as the quotient between BCDVA postop and BCDVA preop. RESULTS: The average efficacy and safety indices of the lenses implanted were 1.1 (SD 0.30) and 1.06 (SD 0.2) at 10 years of follow-up. In this period of time there has been a loss of 12% of the corneal endothelial cells. The postoperative complications were pigment dispersion in four eyes (7%) of four patients and decentration of phakic intraocular lens in two eyes (4%) of another two patients. CONCLUSIONS: The Artiflex® foldable phakic lens could be a safe and effective long-term alternative for myopic patients in whom laser surgery was contraindicated.