Materiały źródłowe

• #1 Enhancing sepsis management through machine learning techniques: A review | Medicina Intensiva

  https://www.medintensiva.org/en-enhancing-sepsis-management-through-machine-articulo-S2173572722000157

  Sepsis is a major public health problem and a leading cause of death in the world, where delay in the beginning of treatment, along with clinical guidelines non-adherence have been proved to be associated with higher mortality. […] To sum up, although the numbers vary, data seem to confirm that incidence and number of deaths due to sepsis increases but the case-fatality decreases. […] Different measures have shown a beneficial impact in terms of reducing mortality, and together with improvement in Intensive Care Unit (ICU) assistance, are the cause of this reduction. […] Despite the fact that adherence with management guidelines has been related with mortality reduction in several studies, sepsis bundles compliance is low. […] Recently, a new approach to the problem of sepsis has arisen, based on the application of new information technologies.

• #2 Impact of a deep learning sepsis prediction model on quality of care and survival | npj Digital Medicine

  https://www.nature.com/articles/s41746-023-00986-6

  Sepsis remains a major cause of mortality and morbidity worldwide. […] Our objective was to assess the impact of a deep-learning model (COMPOSER) for the early prediction of sepsis on patient outcomes. […] The deployment of COMPOSER was significantly associated with a 1.9% absolute reduction (17% relative decrease) in in-hospital sepsis mortality (95% CI, 0.3%3.5%), a 5.0% absolute increase (10% relative increase) in sepsis bundle compliance (95% CI, 2.4%8.0%), and a 4% (95% CI, 1.1%7.1%) reduction in 72-h SOFA change after sepsis onset in causal inference analysis. […] This study suggests that the deployment of COMPOSER for early prediction of sepsis was associated with a significant reduction in mortality and a significant increase in sepsis bundle compliance. […] In this before-and-after quasi-experimental study, we demonstrated that the implementation of a real-time deep-learning model to predict sepsis in two EDs was associated with a 5.0% absolute increase in sepsis bundle compliance and a 1.9% absolute decrease in-hospital sepsis-related mortality.

• #3 Outcome of Sepsis and Prediction of Mortality Risk | Frontiers Research Topic

  https://www.frontiersin.org/research-topics/33064/outcome-of-sepsis-and-prediction-of-mortality-risk/magazine

  Sepsis is a life-threatening condition due to a dysregulated inflammatory response of the host in response to the infection. This leads to functional failure of multiple organs resulting in a high mortality rate worldwide. It is in fact one of the principal causes of death in the intensive care unit, posing a serious public health issue endangering critically ill patients. […] Although there have been signs of progress in managing septic patients and therapeutic strategies, sepsis is still a serious problem in the intensive care unit as there are many limitations in the early identification of the diseases. Biomarkers have been recognized for the early identification of sepsis although studies are still needed in this direction. It is moreover important to monitor the different clinical indices to examine the therapeutic effects of the treatment strategies to predict the outcome of the disease.

• #4 28-day sepsis mortality prediction model from combined serial interleukin-6, lactate, and procalcitonin measurements: a retrospective cohort study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9816294/

  Sepsis is a global medical issue owing to its unacceptably high mortality rate. Therefore, an effective approach to predicting patient outcomes is critically needed. We aimed to search for a novel 28-day sepsis mortality prediction model based on serial interleukin-6 (IL-6), lactate (LAC), and procalcitonin (PCT) measurements. […] Early mortality prediction is of great importance for timely and intensive management, which is a high priority for improving the outcomes of sepsis. […] However, several biomarkers have been shown to play an important role in predicting patient outcomes, we develop a 28-day sepsis mortality prediction model, according to the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD). […] The present study was established to preliminarily develop a novel simple prediction model for the prognosis of 28-day mortality of sepsis by combining the predictive performance of the levels and clearance of IL-6, LAC, and PCT.

• #5 Understanding the complexity of sepsis mortality prediction via rule discovery and analysis: a pilot study | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01690-9

  Sepsis, defined as life-threatening organ dysfunction caused by a dysregulated host response to infection, has become one of the major causes of death in Intensive Care Units (ICUs). […] The early prediction of in-hospital mortality for sepsis patients is not only meaningful to medical decision making, but more importantly, relates to the well-being of patients. […] Prediction of clinical outcomes of patients with sepsis in ICUs is a vital research task. Length of hospital stay or ICU stay, in-hospital mortality, and readmission are often considered as the outcomes of interest. The early prediction of these outcomes are not only associated with improving the well-being of patients, but also relates to the evaluation of quality-of-care of health centers, the performance of healthcare practitioners, and the effectiveness of clinical decision making.

• #6 Understanding the complexity of sepsis mortality prediction via rule discovery and analysis: a pilot study | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01690-9

  Improved predictions help to stratify ICU patients into different risk categories and contribute to personalized care and treatment. […] In our study, we apply a rule-based method on a sepsis data set to predict the in-hospital death events of the sepsis population. […] Both the internal validation and external validation demonstrate that the rules we discover are not only capable of mortality prediction for sepsis patients but are also informative in helping us understand the complexity of sepsis and its population. […] Our study demonstrates that, with the rule-based method, we could not only make accurate prediction on in-hospital death events of sepsis patients, but also reveal the complex relationship between sepsis-related risk factors through the rules themselves, so as to improve our understanding of the complexity of sepsis as well as its population.

• #7 Enhancing sepsis management through machine learning techniques: A review | Medicina Intensiva

  https://www.medintensiva.org/en-enhancing-sepsis-management-through-machine-articulo-S2173572722000157

  Concretely, Machine Learning (ML), a subfield of AI, has gained attention in the sector of medicine. […] The main objective of this work is to conduct a narrative review to provide an overview of how specific ML techniques can be used to improve sepsis management, focusing on the following specific tasks: detection, prediction of sepsis/shock, mortality prediction, hospital stay, costs and adherence to guides. […] Sepsis is a time-dependent syndrome, which implies that the sooner we start treatment, the better the prognosis. […] Of the 34 works covered in the present study, 12 of them explicitly deal with the task of sepsis prediction and sepsis severity prediction. […] Predicting sepsis-related mortality is important in order to both classify patients by their severity and identify those situations in which a more aggressive treatment may be necessary.

• #8 Can We Improve Mortality Prediction in Patients with Sepsis in the Emergency Department?

  https://www.mdpi.com/1648-9144/60/8/1333

  Sepsis represents a global health challenge and requires advanced diagnostic and prognostic approaches due to its elevated rate of morbidity and fatality. […] The overall mortality was 49.25%. […] The levels of IL-6 were significantly higher in the non-survival group and had higher AUC values compared to the other biomarkers. […] In our study, IL-6 and SAPS II/III were the most accurate predictors of 28 day mortality for sepsis patients in the ED. […] The rapid deterioration of patients with sepsis emphasizes the importance of early detection, continuous monitoring, and precise prognosis to improve outcomes. […] Integration of these biomarkers with clinical scoring systems may be a way to improve sepsis diagnosis and prognosis in emergency settings, which is important for the timely and effective care of patients with sepsis.

• #9 Model for predicting short-term mortality of severe sepsis

  https://pmc.ncbi.nlm.nih.gov/articles/PMC2717433/

  To establish a prognostic model for predicting 14-day mortality in ICU patients with severe sepsis overall and according to place of infection acquisition and to sepsis episode number. […] Independent predictors of death were logistic organ dysfunction (odds ratio (OR), 1.22 per point, P 10-4), septic shock (OR, 1.40; P = 0.01), rank of severe sepsis episode (1 reference, 2: OR, 1.26; P = 0.10 3: OR, 2.64; P 10-3), multiple sources of infection (OR; 1.45, P = 0.03), simplified acute physiology score II (OR, 1.02 per point; P 10-4), McCabe score ([greater than or equal to]2) (OR, 1.96; P 10-4), and number of chronic co-morbidities (1: OR, 1.75; P 10-3, 2: OR, 2.24, P 10-3). […] In ICU patients, a prognostic model based on a few easily obtained variables is effective in predicting death within 14 days after the first to fourth episode of severe sepsis complicating community-, hospital-, or ICU-acquired infection.

• #10 Model for predicting short-term mortality of severe sepsis

  https://pmc.ncbi.nlm.nih.gov/articles/PMC2717433/

  The objective of this study was to design a prognostic model for predicting death within 14 days of severe sepsis onset at any time during the first 28 days of the ICU stay. […] We found that predicting death within 14 days after the onset of severe sepsis during the first 28 days in the ICU was feasible in patients with no to three previous episodes of severe sepsis. […] We developed a model for predicting death within 14 days after the diagnosis of the first, second, third or fourth episode of severe sepsis occurring within 28 days after ICU admission. The model is based on a few readily available variables. […] This prediction model is designed to predict death directly related to severe sepsis, as opposed to co-morbidities or DNR decisions, which contribute substantially to longer-term mortality rates.

• #11 28-day sepsis mortality prediction model from combined serial interleukin-6, lactate, and procalcitonin measurements: a retrospective cohort study

  https://pmc.ncbi.nlm.nih.gov/articles/PMC9816294/

  This retrospective single-center study demonstrated that combining the levels and clearance of IL-6, LAC, and PCT was valuable for predicting 28-day sepsis mortality. Specifically, the present study showed that combining IL-6D1, IL-6D3, PCTD1, PCTD3, and LACcD3 can provide a simple prediction model for 28-day sepsis mortality with good performance and good operability. […] The combination of IL-6D1, IL-6D3, PCTD1, PCTD3, and LACcD3 may be used to build a prediction model for 28-day sepsis mortality. These results still need to be verified in a larger sample size through multicenter-based research.

• #12 Can We Improve Mortality Prediction in Patients with Sepsis in the Emergency Department?

  https://www.mdpi.com/1648-9144/60/8/1333

  Despite all these advances, there is a critical lack of validated prognostic tools for assessing mortality risk in sepsis patients in the ED. […] Our study demonstrated that IL-6 could be a valuable biomarker for predicting 28 day mortality in sepsis compared with the other biomarkers. […] Of the common predictive scores, the strongest performance in predicting 28 day mortality was achieved by SAPS II and SAPS III.

• #13 Establishment and assessment of mortality risk prediction model in patients with sepsis based on early-stage peripheral lymphocyte subsets | Aging

  https://www.aging-us.com/article/205772/text

  This study is aimed to explore the value of lymphocyte subsets in evaluating the severity and prognosis of sepsis. […] The PLS index was independently and significantly associated with the 28-day mortality risk in septic patients (OR: 3.08, 95% CI: 1.18-9.67). […] Our study suggests that the decline of PLS occurred in the early stage of sepsis. The new novel PLS index can be an independent predictor of 28-day mortality in septic patients. The prediction model based on clinical parameters and the PLS index has relatively high predicting ability. […] The PLS index was significantly associated with the 28-day mortality in sepsis. […] Results demonstrate a larger PLS index will increase the mortality risk in sepsis (OR (95% CI): 3.08 (1.189.67), P=0.041). […] In conclusion, the decline of PLS occurred in the early stage of sepsis. A new novel PLS index can be used as an independent predictor of 28-day mortality in septic patients. The prediction model based on clinical parameters and the PLS index has higher predicting ability.

• #14 Extended Hematological Parameters and Short-Term Mortality in Sepsis Patients: A Retrospective Study

  https://www.mdpi.com/2077-0383/14/9/3243

  Extended Hematological Parameters and Short-Term Mortality in Sepsis Patients: A Retrospective Study […] Sepsis has a high mortality rate, with septic shock exceeding 50%. The most common score for diagnosis and prognosis in sepsis is the Sepsis-related Organ Failure Assessment (SOFA). […] The short-term mortality rate was 30%, with higher SOFA scores and significant differences in leukocyte, platelet, and erythrocyte parameters between survivors and non-survivors. […] The only reliable hematological parameter for predicting ICU mortality in sepsis patients may be the percentage of NRBCs. The presence of NRBCs in a blood smear is linked to a worse prognosis. […] Despite enormous progress being made in the management of sepsis, it is associated with high mortality, with the mortality rate in a septic shock reaching more than 50%, especially in elderly patients. […] Among different hematological parameters in sepsis patients, the only acceptable parameter for predicting ICU mortality is the percentage of NRBCs. The presence of NRBCs in a blood smear is associated with a worse prognosis in patients with sepsis.

• #15 Are there new approaches for diagnosis, therapy guidance and outcome prediction of sepsis?

  https://www.wjgnet.com/2220-315x/full/v5/i2/50.htm

  The expression of mHLA-DR represents a valid indicator for monocyte function and should be tested in more clinical trials as it could be a reliable future marker for immunosuppression. […] The multiple organ failure (MOF) is the fatal end feature in the pathophysiology of sepsis. During severe sepsis or septic shock, development of organ dysfunction dramatically increases morbidity and mortality. […] Thus, early diagnosis and a rapid treatment initiation are even more of crucial importance for the prognosis. […] However, despite some interesting trials, a promising combination is still missing.

• #16 Are there new approaches for diagnosis, therapy guidance and outcome prediction of sepsis?

  https://www.wjgnet.com/2220-315x/full/v5/i2/50.htm

  Beside many efforts to improve outcome, sepsis is still one of the most frequent causes of death in critically ill patients. It is the most common condition with high mortality in intensive care units. […] Since there is no typical risk profile, early diagnosis and risk stratification remain difficult, which hinders rapid and effective treatment initiation. […] The key to successful therapy remains the early detection of septic patients. Biomarkers may provide help for clinical decision-making and predicting sepsis-related outcome. […] Although CRP assessment does not sufficiently allow to discriminate between infectious and non-infectious stimuli, a secondary rise in CRP level after 3 to 4 d after infection, surgery or trauma could be helpful for diagnosing septic complications. […] Despite the association of high PCT and CRP levels in the onset of sepsis with poor outcome, the prognostic value of PCT is limited.

• #17 Understanding the complexity of sepsis mortality prediction via rule discovery and analysis: a pilot study | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01690-9

  The mean AUC of rule-based method is higher than all other models except SAPS-II, which demonstrates that rule-based method is able to yield a comparable or even better prediction result on the sepsis population compared with most common scoring systems. […] The top 10 rules identified by the method have found that GCS, serum potassium and serum bilirubin are among the most important risk factors for mortality prediction of the population in our study, and the interactions between these risk factors may change or influence what we have known about the effect of a risk factor on the patient outcome.

• #18 Sepsis mortality prediction with Machine Learning Tecniques | Medicina Intensiva

  https://www.medintensiva.org/en-sepsis-mortality-prediction-with-machine-articulo-S2173572724001310

  The most critical variables in our database have been the average lactate level, diuresis (urine output), pH, and systolic pressure. […] The study’s second objective was calculating the random forest obtained from the public database MIMIC III. The study population was 4559 patients, of which 741 patients died from sepsis. The sensitivity of the classification model was 97.55%, the specificity was 100%, and the accuracy was 98.28% with an AUC of 97.3%. […] The main conclusion is the importance of the variables urine output, satO2, Sisbp mean, lactate levels, and variables related to acid-base equilibrium, such as pH and anion gap. Another conclusion is that despite the difference in the number of variables, the machine learning models calculated with the local database and the MIMIC III database have similar accuracies, sensitivities, and specificities. […] In both databases, lactate levels, average urine production, and variables related to acid-base equilibrium are critical variables in the prognosis of sepsis.

• #19 Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest) | BMC Emergency Medicine | Full Text

  https://bmcemergmed.biomedcentral.com/articles/10.1186/s12873-022-00582-z

  The calibration curve further confirmed that the newly constructed RFS model could be used to predict 30-day mortality in elderly patients with sepsis. […] In short, we use RSF to overcome the weaknesses of traditional survival analysis methods to build a model with high predictive performance. […] We constructed a prognostic model for predicting 30-day mortality risk in elderly patients with sepsis based on the machine learning (RSF algorithm), and it proved superior to the traditional scoring system. The risk factors affecting the patients were also ranked. In addition to the common risk factors of vasopressors, ventilator use, and urine output. Newly added factors such as RDW, type of ICU unit, malignant cancer, and metastatic solid tumor also significantly influence prognosis.

• #20 Enhancing sepsis management through machine learning techniques: A review | Medicina Intensiva

  https://www.medintensiva.org/en-enhancing-sepsis-management-through-machine-articulo-S2173572722000157

  To sum up, different works have shown a relatively good performance predicting long and short-term sepsis related mortality, usually employing more variables than in previous tasks. […] Despite the fact that it is difficult to assess how sepsis detection (and especially, sepsis prediction) will change sepsis treatment, in this work we have tried to elucidate if ML techniques could improve, by themselves, sepsis treatment. […] In the future, application of ML systems to sepsis diagnosis and management could change our way of dealing with this pathology. […] However, ML-based health care is far from ideal. […] ML is a very promising tool to improve sepsis detection and management, but there is probably a long way in front of us and to go along it, we will need to work as a team with partners unknown until now, like AI experts.

• #21 Sepsis mortality prediction with Machine Learning Tecniques | Medicina Intensiva

  https://www.medintensiva.org/en-sepsis-mortality-prediction-with-machine-articulo-S2173572724001310

  Sepsis mortality prediction with Machine Learning Tecniques […] To develop a sepsis death classification model based on machine learning techniques for patients admitted to the Intensive Care Unit (ICU). […] 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%. […] 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.

• #22 Early prediction of onset of sepsis in Clinical Setting

  https://arxiv.org/html/2402.03486v1

  The normalized utility score is a comprehensive metric that considers various factors, including sensitivity, specificity, and prediction time. […] The model achieved a normalized utility score of 0.494 on test data and 0.378 on prospective data with threshold of 0.3, demonstrating its ability to identify sepsis at an early stage accurately. […] Overall, this ML/DL technique enable us to use a collection of different scoring techniques, lab values, demographic information and derived features to help prognosis of sepsis.

• #23 Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest) | BMC Emergency Medicine | Full Text

  https://bmcemergmed.biomedcentral.com/articles/10.1186/s12873-022-00582-z

  Elderly patients with sepsis have many comorbidities, and the clinical reaction is not obvious. Thus, clinical treatment is difficult. […] We constructed a prognostic model to predict a 30-day mortality risk in elderly patients with sepsis based on machine learning (RSF algorithm), and it proved superior to the traditional scoring systems. […] The new model provided a better C-index (0.731 in the validation cohort). […] The calibration curve described the agreement between the predicted probability of RSF model and the observed 30-day survival. […] Our model is unique, it ranked clinically common laboratory examinations and comorbidities according to the variable importance through RSF, and selected the top 30 variables to build the final RSF model, which is not done in traditional scoring systems.

• #24 Survival prediction of patients with sepsis from age, sex, and septic episode number alone | Scientific Reports

  https://www.nature.com/articles/s41598-020-73558-3

  Sepsis is a life-threatening condition caused by an exaggerated reaction of the body to an infection, that leads to organ failure or even death. Since sepsis can kill a patient even in just one hour, survival prediction is an urgent priority among the medical community: even if laboratory tests and hospital analyses can provide insightful information about the patient, in fact, they might not come in time to allow medical doctors to recognize an immediate death risk and treat it properly. […] Our results can have a huge impact on clinical settings, allowing physicians to forecast the survival of patients by sex, age, and septic episode number alone. […] Our findings show that machine learning applied to minimal clinical records of patients diagnosed with sepsis, containing only age, sex, and number of septic episode, is sufficient to predict the survival outcome of the patients themselves.

• #25 Survival prediction of patients with sepsis from age, sex, and septic episode number alone | Scientific Reports

  https://www.nature.com/articles/s41598-020-73558-3

  If validated, hospitals will be able to quickly and reliably predict a patients survival in few seconds, allowing for quicker action from the doctors, which is crucial for a quick-to-kill illness like sepsis. […] These results show, additionally, the level of generalizability of our approach, that is able to correctly predict survived patients just from sex, age, and septic episode even when our models are trained and tested on two different cohorts.

• #26 False hope of a single generalisable AI sepsis prediction model: bias and proposed mitigation strategies for improving performance based on a retrospective multisite cohort study | BMJ Quality & Safety

  https://qualitysafety.bmj.com/cgi/content/short/bmjqs-2024-018328v1?rss=1

  Objective To identify bias in using a single machine learning (ML) sepsis prediction model across multiple hospitals and care locations; evaluate the impact of six different bias mitigation strategies and propose a generic modelling approach for developing best-performing models. […] Implementing a single sepsis prediction model across all sites and care locations within multihospital systems may be unacceptable given large variances in NNE across multiple sites. Bias mitigation methods can identify models demonstrating improved performance across most sites in reducing alert burden but with no impact on the length of the prediction window.

• #27 Impact of a deep learning sepsis prediction model on quality of care and survival | npj Digital Medicine

  https://www.nature.com/articles/s41746-023-00986-6

  Our findings also suggest that the utilization of such models in clinical care was also associated with improvements in intermediate outcomes, such as less organ injury at 72h from the time of sepsis and improvements in elements of sepsis bundles which may explain the mortality benefit described. […] To our knowledge, this is the first time that the improvement of patient outcomes due to the use of a deep-learning model for sepsis prediction has been reported.

• #28 Outcome of Sepsis and Prediction of Mortality Risk | Frontiers Research Topic

  https://www.frontiersin.org/research-topics/33064/outcome-of-sepsis-and-prediction-of-mortality-risk/magazine

  With this Research Topic, we want to collect the recent advances in septic patients management, new technologies, and treatments that can predict the outcome of this condition, and new biomarkers which can lead to early identification of the disease. […] Prognostic biomarkers and factors of sepsis.

Zobacz więcej