OBJECTIVE: To evaluate the predictive ability of mortality prediction scales in cancer patients admitted to intensive care units (ICUs).
METHODS: A systematic review of the literature was conducted using a search algorithm in October 2022. The following databases were searched: PubMed, Scopus, Virtual Health Library (BVS), and Medrxiv. The risk of bias was assessed using the QUADAS-2 scale.
METHODS: ICUs admitting cancer patients.
METHODS: Studies that included adult patients with an active cancer diagnosis who were admitted to the ICU.
METHODS: Integrative study without interventions.
METHODS: Mortality prediction, standardized mortality, discrimination, and calibration.
RESULTS: Seven mortality risk prediction models were analyzed in cancer patients in the ICU. Most models (APACHE II, APACHE IV, SOFA, SAPS-II, SAPS-III, and MPM II) underestimated mortality, while the ICMM overestimated it. The APACHE II had the SMR (Standardized Mortality Ratio) value closest to 1, suggesting a better prognostic ability compared to the other models.
CONCLUSIONS: Predicting mortality in ICU cancer patients remains an intricate challenge due to the lack of a definitive superior model and the inherent limitations of available prediction tools. For evidence-based informed clinical decision-making, it is crucial to consider the healthcare team\'s familiarity with each tool and its inherent limitations. Developing novel instruments or conducting large-scale validation studies is essential to enhance prediction accuracy and optimize patient care in this population.

BACKGROUND: The integration of artificial intelligence (AI) and machine learning (ML) in peritoneal dialysis (PD) presents transformative opportunities for optimizing treatment outcomes and informing clinical decision-making. This study aims to provide a comprehensive overview of the applications of AI/ML techniques in PD, focusing on their potential to predict clinical outcomes and enhance patient care.
METHODS: This systematic review was conducted according to PRISMA guidelines (2020), searching key databases for articles on AI and ML applications in PD. The inclusion criteria were stringent, ensuring the selection of high-quality studies. The search strategy comprised MeSH terms and keywords related to PD, AI, and ML. 793 articles were identified, with nine ultimately meeting the inclusion criteria. The review utilized a narrative synthesis approach to summarize findings due to anticipated study heterogeneity.
RESULTS: Nine studies met the inclusion criteria. The studies varied in sample size and employed diverse AI and ML techniques, reflecting the breadth of data considered. Mortality prediction emerged as a recurrent theme, demonstrating the significance of AI and ML in prognostic accuracy. Predictive modeling extended to technique failure, hospital stay prediction, and pathogen-specific immune responses, showcasing the versatility of AI and ML applications in PD.
CONCLUSIONS: This systematic review highlights the diverse applications of AI/ML in peritoneal dialysis, demonstrating their potential to enhance predictive accuracy, risk stratification, and decision support. However, limitations such as small sample sizes, single-center studies, and potential biases warrant further research and external validation. Future perspectives include integrating these AI/ML models into routine clinical practice and exploring additional use cases to improve patient outcomes and healthcare decision-making in PD.

UNASSIGNED: The purpose of our meta-analysis was to look at the impact of modified nutrition risk in the critically ill (mNUTRIC) on mortality in patients with critical illness.
UNASSIGNED: Literature relevant to this meta-analysis was searched in PubMed, Web of Science, and Cochrane Library till 26 August 2023. Prospective or retrospective studies, patients >18 years of age, studies that reported on mortality and mNUTRIC (mNUTRIC cut-off score) were included. The QUIPS tool was used to evaluate the risk for bias in prognostic factors.
UNASSIGNED: A total of 31 studies on mNUTRIC score, involving 13,271 patients were included. The summary area under the curve (sAUC) of 0.80 (95% CI: 0.76-0.83) illustrates the mNUTRIC score\'s strong discrimination. The pooled sensitivity was 0.79 (95% CI: 0.74-0.84) and pooled specificity was 0.68 (95% CI: 0.63-0.73). We found no discernible variation in the mNUTRIC\'s prediction accuracy among cut-off values of <5 and >5 in our subgroup analysis and sAUC values were 0.82 (95% CI: 0.78-0.85) and 0.78 (95% CI: 0.74-0.81), respectively.
UNASSIGNED: We observed that mNUTRIC can discriminate between critically ill individuals and predict their mortality.
UNASSIGNED: CRD42023460292.
UNASSIGNED: Prakash J, Verma S, Shrivastava P, Saran K, Kumari A, Raj K, et al. Modified NUTRIC Score as a Predictor of All-cause Mortality in Critically Ill Patients: A Systematic Review and Meta-analysis. Indian J Crit Care Med 2024;28(5):495-503.

Objective: To summarize the available literature on using machine learning (ML) for palliative care practice as well as research and to assess the adherence of the published studies to the most important ML best practices. Methods: The MEDLINE database was searched for the use of ML in palliative care practice or research, and the records were screened according to PRISMA guidelines. Results: In total, 22 publications using machine learning for mortality prediction (n = 15), data annotation (n = 5), predicting morbidity under palliative therapy (n = 1), and predicting response to palliative therapy (n = 1) were included. Publications used a variety of supervised or unsupervised models, but mostly tree-based classifiers and neural networks. Two publications had code uploaded to a public repository, and one publication uploaded the dataset. Conclusions: Machine learning in palliative care is mainly used to predict mortality. Similarly to other applications of ML, external test sets and prospective validations are the exception.

Accurate prognostication of stroke may help in appropriate therapy and rehabilitation planning. In the past few years, several machine learning (ML) algorithms were applied for prediction of stroke outcomes. We aimed to examine the performance of machine learning-based models for the prediction of mortality after stroke, as well as to identify the most prominent factors for mortality.
We searched MEDLINE/PubMed and Web of Science databases for original publications on machine learning applications in stroke mortality prediction, published between January 1, 2011, and October 27, 2022. Risk of bias and applicability were evaluated using the tailored QUADAS-2 tool.
Of the 1015 studies retrieved, 28 studies were included. Twenty-Five studies were retrospective. The ML models demonstrated a favorable range of AUC for mortality prediction (0.67-0.98). In most of the articles, the models were applied for short-term post stroke mortality. The number of explanatory features used in the models to predict mortality ranged from 5 to 200, with substantial overlap in the variables included. Age, high BMI and high NIHSS score were identified as important predictors for mortality. Almost all studies had a high risk of bias in at least one category and concerns regarding applicability.
Using machine learning, data available at the time of admission may aid in stroke mortality prediction. Notwithstanding, current research is based on few preliminary works with high risk of bias and high heterogeneity. Thus, future prospective, multicenter studies with standardized reports are crucial to firmly establish the usefulness of the algorithms in stroke prognostication.

The medical complexity and high acuity of patients in the cardiac intensive care unit make for a unique patient population with high morbidity and mortality. While there are many tools for predictions of mortality in other settings, there is a lack of robust mortality prediction tools for cardiac intensive care unit patients. The ongoing advances in artificial intelligence and machine learning also pose a potential asset to the advancement of mortality prediction. Artificial intelligence algorithms have been developed for application of electrocardiogram interpretation with promising accuracy and clinical application. Additionally, artificial intelligence algorithms applied to electrocardiogram interpretation have been developed to predict various variables such as structural heart disease, left ventricular systolic dysfunction, and atrial fibrillation. These variables can be used and applied to new mortality prediction models that are dynamic with the changes in the patient\'s clinical course and may lead to more accurate and reliable mortality prediction. The application of artificial intelligence to mortality prediction will fill the gaps left by current mortality prediction tools.

The Sequential Organ Failure Assessment (SOFA) score is commonly used in the Intensive Care Unit (ICU) to evaluate, prognosticate and assess patients. Since its validation, the SOFA score has served in various settings, including medical, trauma, surgical, cardiac, and neurological ICUs. It has been a strong mortality predictor and literature over the years has documented the ability of the SOFA score to accurately distinguish survivors from non-survivors on admission. Over the years, multiple variations have been proposed to the SOFA score, which have led to the evolution of alternate validated scoring models replacing one or more components of the SOFA scoring system. Various SOFA based models have been used to evaluate specific clinical populations, such as patients with cardiac dysfunction, hepatic failure, renal failure, different races and public health illnesses, etc. This study is aimed to conduct a review of modifications in SOFA score in the past several years. We review the literature evaluating various modifications to the SOFA score such as modified SOFA, Modified SOFA, modified Cardiovascular SOFA, Extra-renal SOFA, Chronic Liver Failure SOFA, Mexican SOFA, quick SOFA, Lactic acid quick SOFA (LqSOFA), SOFA in hematological malignancies, SOFA with Richmond Agitation-Sedation scale and Pediatric SOFA. Various organ systems, their relevant scoring and the proposed modifications in each of these systems are presented in detail. There is a need to incorporate the most recent literature into the SOFA scoring system to make it more relevant and accurate in this rapidly evolving critical care environment. For future directions, we plan to put together most if not all updates in SOFA score and probably validate it in a large database a single institution and validate it in multisite data base.

BACKGROUND: The use of primary endocrine therapy (PET) in managing breast cancer in the elderly has become common practice. Whilst there appears to be no difference in overall survival in comparison with surgery, PET has been found to be inferior in local disease control with a limited duration of efficacy (2-3 years). The International Society of Geriatric Oncology (SIOG) state that PET may be considered in patients with a short life expectancy (<2 years) or considered unfit for surgery. Frequently, decision making for PET allocation is a subjective process by the clinician.
METHODS: A systematic literature review was performed to establish what prediction models are available for all-cause mortality in the elderly, and what breast-specific models have been produced.
RESULTS: 18 prognostic models were deemed eligible from 15 papers. 1 breast-specific model was found, 2 nursing home related and 15 for community-dwelling elders. Accuracy (as defined by discrimination; c-statistic or AUROC) ranged from 0.69 (moderate) to 0.86 (very good).
CONCLUSIONS: This review highlighted a variety of validated prognostic indexes. Several models with very good accuracy were identified but most were validated in US-populations and relied on information from administrative datasets. One breast specific model by Stotter et al. was identified, specifically to aid treatment planning for frail elderly patients but had limited accuracy. The strength of an index will ultimately be on its clinical impact and influence on treatment decisions rather than its accuracy and as of yet no trials exploring this have been carried out.

BACKGROUND: To date, there are no reviews on machine learning (ML) in burn care. Considering the growth of ML in medicine and the complexities and challenges of burn care, this review specializes on ML applications in burn care. The objective was to examine the features and impact of applications in targeting various aspects of burn care and research.
METHODS: MEDLINE, the Cochrane Database of Systematic Reviews, ScienceDirect, and citation review of relevant primary and review articles were searched for studies involving burn care/research and machine learning. Data were abstracted on study design, study size, year, population, application of burn care/research, ML technique(s), and algorithm performance.
RESULTS: 15 retrospective observational studies involving burn patients met inclusion criteria. In total 5105 patients with acute thermal injury, 171 clinical burn wounds, 180 9-mer peptides, and 424 12-mer peptides were included in the studies. Studies focused on burn diagnosis (n=5), aminoglycoside response (n=3), hospital length of stay (n=2), survival/mortality (n=4), burn healing time (n=1), and antimicrobial peptides in burn patients (n=1). Of these 15 studies, 11 used artificial neural networks. Importantly, all studies demonstrated the benefits of ML in burn care/research and superior performance over traditional statistical methods. However, algorithm performance was assessed differently by different authors. Feature selection varied among studies, but studies with similar applications shared specific features including age, gender, presence of inhalation injury, total body surface area burned, and when available, various degrees of burns, infections, and previous histories/conditions of burn patients.
CONCLUSIONS: A common feature base may be determined for ML in burn care/research, but the impact of ML will require further validation in prospective observational studies and randomized clinical trials, establishment of common performance metrics, and high quality evidence about clinical and economic impacts. Only then can ML applications be advanced and accepted widely in burn care/research.