Harnessing Machine Learning to Improve Patient Outcomes in Pulmonary and Critical Care Medicine.
Ontology highlight
ABSTRACT:
SUBMITTER: Levenson AR
PROVIDER: S-EPMC7528791 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The theory and computational tools developed to interpret and explore energy landscapes in molecular science are applied to the landscapes defined by local minima for neural networks. These machine learning landscapes correspond to fits of training data, where the inputs are vital signs and laboratory measurements for a database of patients, and the objective is to predict a clinical outcome. In this contribution, we test the predictions obtained by fitting to single measurements, and then to combinations of between 2 and 10 different patient medical data items. The effect of including measurements over different time intervals from the 48 h period in question is analysed, and the most recent values are found to be the most important. We also compare results obtained for neural networks as a function of the number of hidden nodes, and for different values of a regularization parameter. The predictions are compared with an alternative convex fitting function, and a strong correlation is observed. The dependence of these results on the patients randomly selected for training and testing decreases systematically with the size of the database available. The machine learning landscapes defined by neural network fits in this investigation have single-funnel character, which probably explains why it is relatively straightforward to obtain the global minimum solution, or a fit that behaves similarly to this optimal parameterization.
| S-EPMC5541539 | biostudies-other
Project description:Background: Little is known about historical and recent application trends for pulmonary critical care medicine (PCCM) or pulmonary medicine (PM) fellowship programs. Describing trends in and characteristics of PCCM and PM applications, applicants, and fellowship programs can help program directors and medical educators understand trainees' interest in and application patterns for these fellowship programs. Objective: The objective of this study was to use National Residency Match Program data to assess recent trends in PCCM and PM fellowship applications and compare characteristics of applicants and fellowship programs. Methods: In 2019, we used National Residency Match Program data to evaluate applicant ranking and matching in PCCM and PM fellowship programs and to compare applicant and fellowship program characteristics. Results: From 2008 through 2019, the majority of applicants (59.1%) matched into PCCM were graduates of U.S. allopathic or osteopathic medical schools, whereas 87% of PM fellows were non-U.S. graduates. PCCM was the preferred specialty for 90.8% of matched applicants versus only 31.6% of matched PM applicants (P < 0.001). The match rate for PCCM applicants was 67.2% versus 23.8% for PM applicants (P < 0.001). Of PCCM applicants, 36.6% matched into their top choice versus 10.8% of PM applicants (P < 0.001). There are far fewer PM fellowship positions (n = 23) and programs (n = 12) than PCCM positions (n = 450) and programs (n = 131). The mean fill rates from the 2004 through 2016 appointment years are 94.1% in PCCM and 97.4% in PM (P = 0.009). Conclusion: PCCM is a prevailing specialty choice over PM among residency graduates, with matched applicants more likely to list PCCM than PM as their preferred specialty. Further exploration into applicants' interest in critical care compared with PM may prove beneficial in guiding applicants to programs that will best meet their career goals.
| S-EPMC8043272 | biostudies-literature
Project description:Postoperative pulmonary complications (PPCs) are significant causes of postoperative morbidity and mortality. This study presents the utilization of machine learning for predicting PPCs and aims to identify the important features of the prediction models. This study used a retrospective cohort design and collected data from two hospitals. The dataset included perioperative variables such as patient characteristics, preexisting diseases, and intraoperative factors. Various algorithms, including logistic regression, random forest, light-gradient boosting machines, extreme-gradient boosting machines, and multilayer perceptrons, have been employed for model development and evaluation. This study enrolled 111,212 adult patients, with an overall incidence rate of 8.6% for developing PPCs. The area under the receiver-operating characteristic curve (AUROC) of the models was 0.699-0.767, and the f1 score was 0.446-0.526. In the prediction models, except for multilayer perceptron, the 10 most important features were obtained. In feature-reduced models, including 10 important features, the AUROC was 0.627-0.749, and the f1 score was 0.365-0.485. The number of packed red cells, urine, and rocuronium doses were similar in the three models. In conclusion, machine learning provides valuable insights into PPC prediction, significant features for prediction, and the feasibility of models that reduce the number of features.
| S-EPMC10488713 | biostudies-literature
Project description:GDF-15 (growth differentiation factor 15) acts both as a stress-induced cytokine with diverse actions at different body sites and as a cell-autonomous regulator linked to cellular senescence and apoptosis. For multiple reasons, this divergent transforming growth factor-β molecular superfamily member should be better known to pulmonary researchers and clinicians. In ambulatory individuals, GDF-15 concentrations in peripheral blood are an established predictive biomarker of all-cause mortality and of adverse cardiovascular events. Concentrations upon admission of critically ill patients (without or with sepsis) correlate with organ dysfunction and independently predict short- and long-term mortality risk. GDF-15 is a major downstream mediator of p53 activation, but it can also be induced independently of p53, notably by nonsteroidal antiinflammatory agents. GDF-15 blood concentrations are markedly elevated in adults and children with pulmonary hypertension. Concentrations are also increased in chronic obstructive pulmonary disease, in which they contribute to mucus hypersecretion, airway epithelial cell senescence, and impaired antiviral defenses, which together with murine data support a role for GDF-15 in chronic obstructive pulmonary disease pathogenesis and progression. This review summarizes biological and clinical data on GDF-15 relevant to pulmonary and critical care medicine. We highlight the recent discovery of a central nervous system receptor for GDF-15, GFRAL (glial cell line-derived neurotrophic factor family receptor-α-like), an important advance with potential for novel treatments for obesity and cachexia. We also describe limitations and controversies in the existing literature, and we delineate research questions that must be addressed to determine whether GDF-15 can be therapeutically manipulated in other clinical settings.
| S-EPMC6543753 | biostudies-literature
Project description:BackgroundEndotracheal intubation in the intensive care unit (ICU) is a high-risk procedure. Competence in endotracheal intubation is a requirement for Pulmonary and Critical Care Medicine (PCCM) training programs, but fellow experience as the primary operator in intubating ICU patients has not been described on a large scale.ObjectiveWe hypothesized that significant variation surrounding endotracheal intubation practices in medical ICUs exists in United States (US) PCCM training programs.MethodsWe administered a survey to a convenience sample of US PCCM fellows to elicit typical intubation practices in the medical ICU.Results89 discrete US PCCM and Internal Medicine CCM training programs (77% response rate) were represented. At 43% of programs, the PCCM fellow was "always or almost always" designated the primary operator for intubation of a medical ICU patient, whereas at 21% of programs, the PCCM fellow was "rarely or never" the primary operator responsible for intubating in the ICU. Factors influencing this variation included time of day, hospital policies, attending skill or preference, ICU census and acuity, and patient factors. There was an association between location of the training program, but not program size, and whether the PCCM fellow was the primary operator.ConclusionThere is significant variation in whether PCCM fellows are the primary operators to intubate medical ICU patients during training. Further work should explore how this variation affects fellow career development and competence in intubation.
| S-EPMC7959255 | biostudies-literature
Project description:BackgroundPatient-reported outcome measures (PROMs) and patient-reported experience measures (PREMs) are self-reporting tools that can measure important information about patients, such as health priorities, experience, and perception of outcome. The use of traditional objective measures such as vital signs and lab values can be supplemented with these self-reported patient measures to provide a more complete picture of a patient's health status. Machine learning, the use of computer algorithms that improve automatically through experience, is a powerful tool in health care that often does not use subjective information shared by patients. However, machine learning has largely been based on objective measures and has been developed without patient or public input. Algorithms often do not have access to critical information from patients and may be missing priorities and measures that matter to patients. Combining objective measures with patient-reported measures can improve the ability of machine learning algorithms to assess patients' health status and improve the delivery of health care.ObjectiveThe objective of this scoping review is to identify gaps and benefits in the way machine learning is integrated with patient-reported outcomes for the development of improved public and patient partnerships in research and health care.MethodsWe reviewed the following 3 questions to learn from existing literature about the reported gaps and best methods for combining machine learning and patient-reported outcomes: (1) How are the public engaged as involved partners in the development of artificial intelligence in medicine? (2) What examples of good practice can we identify for the integration of PROMs into machine learning algorithms? (3) How has value-based health care influenced the development of artificial intelligence in health care? We searched Ovid MEDLINE(R), Embase, PsycINFO, Science Citation Index, Cochrane Library, and Database of Abstracts of Reviews of Effects in addition to PROSPERO and the ClinicalTrials website. The authors will use Covidence to screen titles and abstracts and to conduct the review. We will include systematic reviews and overviews published in any language and may explore additional study types. Quantitative, qualitative, and mixed methods studies are included in the reviews.ResultsThe search is completed, and Covidence software will be used to work collaboratively. We will report the review using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and Critical Appraisal Skills Programme for systematic reviews.ConclusionsFindings from our review will help us identify examples of good practice for how to involve the public in the development of machine learning systems as well as interventions and outcomes that have used PROMs and PREMs.International registered report identifier (irrid)DERR1-10.2196/36395.
| S-EPMC9345029 | biostudies-literature
Project description: Not available
| S-EPMC8357065 | biostudies-literature
Project description: Not available
| S-EPMC7706163 | biostudies-literature
Project description:Degradation of intracellular proteins in Gram-negative bacteria regulates various cellular processes and serves as a quality control mechanism by eliminating damaged proteins. To understand what causes the proteolytic machinery of the cell to degrade some proteins while sparing others, we employed a quantitative pulsed-SILAC (Stable Isotope Labeling with Amino acids in Cell culture) method followed by mass spectrometry analysis to determine the half-lives for the proteome of exponentially growing Escherichia coli, under standard conditions. We developed a likelihood-based statistical test to findactively degraded proteins, and identified dozens of novel proteins that are fast-degrading. Finally, we used structural, physicochemical and protein-protein interaction network descriptorsto train a machine-learning classifier to discriminate fast-degrading proteins from the rest of the proteome. Our combined computational-experimental approach provides means for proteomic-based discovery of fast degrading proteins in bacteria and the elucidation of the factors determining protein half-livesand have implications for protein engineering. Moreover, as rapidly degraded proteins may play an important role in pathogenesis, our findings could identify new potential antibacterial drug targets
2021-01-13 | PXD022112 | Pride
Project description:BACKGROUND:Like other scientific fields, such as cosmology, high-energy physics, or even the life sciences, medicine and healthcare face the challenge of an extremely quick transformation into data-driven sciences. This challenge entails the daunting task of extracting usable knowledge from these data using algorithmic methods. In the medical context this may for instance realized through the design of medical decision support systems for diagnosis, prognosis and patient management. The intensive care unit (ICU), and by extension the whole area of critical care, is becoming one of the most data-driven clinical environments. RESULTS:The increasing availability of complex and heterogeneous data at the point of patient attention in critical care environments makes the development of fresh approaches to data analysis almost compulsory. Computational Intelligence (CI) and Machine Learning (ML) methods can provide such approaches and have already shown their usefulness in addressing problems in this context. The current study has a dual goal: it is first a review of the state-of-the-art on the use and application of such methods in the field of critical care. Such review is presented from the viewpoint of the different subfields of critical care, but also from the viewpoint of the different available ML and CI techniques. The second goal is presenting a collection of results that illustrate the breath of possibilities opened by ML and CI methods using a single problem, the investigation of septic shock at the ICU. CONCLUSION:We have presented a structured state-of-the-art that illustrates the broad-ranging ways in which ML and CI methods can make a difference in problems affecting the manifold areas of critical care. The potential of ML and CI has been illustrated in detail through an example concerning the sepsis pathology. The new definitions of sepsis and the relevance of using the systemic inflammatory response syndrome (SIRS) in its diagnosis have been considered. Conditional independence models have been used to address this problem, showing that SIRS depends on both organ dysfunction measured through the Sequential Organ Failure (SOFA) score and the ICU outcome, thus concluding that SIRS should still be considered in the study of the pathophysiology of Sepsis. Current assessment of the risk of dead at the ICU lacks specificity. ML and CI techniques are shown to improve the assessment using both indicators already in place and other clinical variables that are routinely measured. Kernel methods in particular are shown to provide the best performance balance while being amenable to representation through graphical models, which increases their interpretability and, with it, their likelihood to be accepted in medical practice.
| S-EPMC6245501 | biostudies-other