22 June 2023 in PLOS Digital Health
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.
28 April 2017 in The Canadian Journal of Hospital Pharmacy
Health Care and Pharmacy Practice in Jordan
10 October 2022 in Supportive Care in Cancer
18 July 2018 in Annals of Pharmacotherapy
Objective: To review the clinical data on the effectiveness and safety of double carbapenem therapy (DCT) in patients infected with carbapenemase-producing Klebsiella pneumoniae (CP-Kp). Data Sources: A literature search was performed utilizing PubMed and EMBASE (from 1966 to May 2018); bibliographies of the retrieved articles were also searched. Study Selection and Data Extraction: Articles were included if they evaluated patients with infections caused by CP-Kp and were treated with DCT. Meeting abstracts, editorials, and animal and in vitro studies were excluded. Data Synthesis: The search strategy revealed 8 case reports and 6 clinical studies (total of 171 patients) that evaluated the administration of ertapenem followed by prolonged infusions of meropenem or doripenem. Most patients were critically ill and commonly had infections in the blood, lungs, and urine. Clinical and microbiological success were reported in 70% of the patients and mortality in 24%. Adverse events, which included mostly seizures, sodium disorders, and gastrointestinal symptoms, were reported in 16 patients; none required interruption of treatment. Relevance to Patient Care and Clinical Practice: This review evaluated the clinical experience of DCT in the treatment of CP-Kp infections, based on case reports and clinical studies, for the potential role of DCT as a therapeutic option. Conclusion: Despite the limited studies, current data suggest that DCT may be an effective and safe strategy to treat CP-Kp. However, large randomized controlled trials are necessary to clearly define the role of DCT.
1 January 2025 in NEJM AI
6 December 2013 in Journal of Pharmacy Practice
Objective: To determine the incidence, characteristics, and outcomes of adverse drug events (ADEs) in critically ill patients with cancer. Methods: This was a 5-month prospective observational study. Patients who were admitted to the adult medical/surgical oncology intensive care unit (ICU) were evaluated for any drug-related adverse events during their ICU stay. An ADE was defined as injury or patient harm resulting from medical intervention related to a drug. Results: The incidence rate of ADEs was 96.5 per 1000 patient days and 35.3 per 100 ICU admissions. Of the reported ADEs, 57 (64.8%) were serious/life threatening, 30 (34.1%) were significant, 1 (1.1%) was fatal, and 14 (15.9%) of all ADEs were considered preventable. The most common drug classes associated with ADEs were antidiabetics, antibiotics, and analgesics/sedatives. The length of stay and presence of renal or respiratory failure were significantly associated with an increased number of ADEs. The length of stay and female sex were significantly associated with the likelihood of developing an ADE. Conclusion: Critically ill patients with cancer are at high risk of developing ADEs. Strategies that reduce the incidence and severity of ADEs are essential to improve the outcomes of this patient population.