RESUMO
The adoption of artificial intelligence (AI) algorithms is rapidly increasing in healthcare. Such algorithms may be shaped by various factors such as social determinants of health that can influence health outcomes. While AI algorithms have been proposed as a tool to expand the reach of quality healthcare to underserved communities and improve health equity, recent literature has raised concerns about the propagation of biases and healthcare disparities through implementation of these algorithms. Thus, it is critical to understand the sources of bias inherent in AI-based algorithms. This review aims to highlight the potential sources of bias within each step of developing AI algorithms in healthcare, starting from framing the problem, data collection, preprocessing, development, and validation, as well as their full implementation. For each of these steps, we also discuss strategies to mitigate the bias and disparities. A checklist was developed with recommendations for reducing bias during the development and implementation stages. It is important for developers and users of AI-based algorithms to keep these important considerations in mind to advance health equity for all populations.
RESUMO
OBJECTIVES: To characterize the association between the use of physiologic assessment (central venous pressure, pulmonary artery occlusion pressure, stroke volume variation, pulse pressure variation, passive leg raise test, and critical care ultrasound) with fluid and vasopressor administration 24 hours after shock onset and with in-hospital mortality. DESIGN: Multicenter prospective cohort study between September 2017 and February 2018. SETTINGS: Thirty-four hospitals in the United States and Jordan. PATIENTS: Consecutive adult patients requiring admission to the ICU with systolic blood pressure less than or equal to 90 mm Hg, mean arterial blood pressure less than or equal to 65 mm Hg, or need for vasopressor. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Of 1,639 patients enrolled, 39% had physiologic assessments. Use of physiologic assessment was not associated with cumulative fluid administered within 24 hours of shock onset, after accounting for baseline characteristics, etiology and location of shock, ICU types, Acute Physiology and Chronic Health Evaluation III, and hospital (beta coefficient, 0.04; 95% CI, -0.07 to 0.15). In multivariate analysis, the use of physiologic assessment was associated with a higher likelihood of vasopressor use (adjusted odds ratio, 1.98; 95% CI, 1.45-2.71) and higher 24-hour cumulative vasopressor dosing as norepinephrine equivalent (beta coefficient, 0.37; 95% CI, 0.19-0.55). The use of vasopressor was associated with increased odds of in-hospital mortality (adjusted odds ratio, 1.88; 95% CI, 1.27-2.78). In-hospital mortality was not associated with the use of physiologic assessment (adjusted odds ratio, 0.86; 95% CI, 0.63-1.18). CONCLUSIONS: The use of physiologic assessment in the 24 hours after shock onset is associated with increased use of vasopressor but not with fluid administration.
Assuntos
Hidratação/estatística & dados numéricos , Mortalidade Hospitalar/tendências , Choque/mortalidade , Choque/terapia , Vasoconstritores/uso terapêutico , APACHE , Adulto , Idoso , Idoso de 80 Anos ou mais , Pressão Sanguínea , Pressão Venosa Central , Relação Dose-Resposta a Droga , Feminino , Hidratação/métodos , Humanos , Unidades de Terapia Intensiva/estatística & dados numéricos , Masculino , Pessoa de Meia-Idade , Escores de Disfunção Orgânica , Estudos Prospectivos , Choque/diagnóstico , Choque/tratamento farmacológico , Vasoconstritores/administração & dosagemAssuntos
Antibacterianos/economia , Colistina/economia , Análise Custo-Benefício/métodos , Farmacorresistência Bacteriana Múltipla/efeitos dos fármacos , Pneumonia Bacteriana/tratamento farmacológico , Pneumonia Bacteriana/economia , Antibacterianos/administração & dosagem , Colistina/administração & dosagem , Relação Dose-Resposta a Droga , Farmacorresistência Bacteriana Múltipla/fisiologia , Humanos , Pneumonia Bacteriana/epidemiologia , Estudos Retrospectivos , Arábia Saudita/epidemiologia , Resultado do TratamentoRESUMO
PURPOSE: Describe the incidence, characteristics and cost of adverse drug events that necessitate admission to the intensive care unit in oncology patients. METHODS: This was a prospective observational 5-months study at a medical/surgical intensive care unit of a comprehensive teaching cancer center. Patients admitted to the intensive care unit were screened to determine whether the admission was due to an adverse drug event. The adverse drug events were characterized based on the suspected medication, system involved and preventability. Patient demographics, length of stay, mortality and the total patient charges during their intensive care unit stay were recorded. RESULTS: During the study period, 249 patients were screened and an adverse drug event was the primary cause of 57 (22.9%) admissions. The most common medications associated with an adverse drug event requiring intensive care unit admission were antineoplastics (n = 37), analgesics (n = 9) and anticoagulants (n = 4). Ten adverse drug events were considered preventable. The average length of stay for patients with adverse drug events resulting in intensive care unit admission was 6.2 days ±9.8 (SD) and the mortality rate was 28.1%. Hematological malignancy was independently associated with adverse drug events resulting in intensive care unit admission. The average patient charges for the intensive care unit stay was US$11,692 ± 17,529 (SD), which corresponded to about US$1.5 million in annual patient charges for a 12-bed intensive care unit at a cancer institution. CONCLUSIONS: Adverse drug events resulting in intensive care unit admission in oncology patients are common and often associated with significant morbidity, mortality, and cost.