ABSTRACT
In this paper we propose a fuzzy logic-based approach to analyze UK National Health Service (NHS) public administrative data related to pre-and post-pandemic claims filed by patients, analyzing the legal and ethical issues connected to the use of Artificial Intelligence systems, including our own, to take critical decisions having a significant impact on patients, such as employing computational intelligence to justify the management choices related to Intensive Care Unit (ICU) bed allocation. Differently from previous papers, in this work we follow an unsupervised approach and, specifically, we perform an analysis of UK hospitals by means of a computational intelligence algorithm integrating Fuzzy C-Means and swarm intelligence. The dataset that we analyse allows us to compare pre-and post-pandemic data, to analyze the ethical and legal challenges of the use of computational intelligence for critical decision-making in the health care field. © 2022 IEEE.
ABSTRACT
Background: Many patients fail to achieve a clinical benefit from ICI. Several scores have been developed to improve ICI candidates selection but it is uncertain which one better predicts patients’ outcome. Here, we performed a direct comparison of the most successful scores. Methods: This is a sub-analysis of the immunoblood prospective observational study that enrolled patients diagnosed with advanced solid tumors treated with ICI. Main clinicopathological data were retrieved from medical records and responses assessed according to RECIST 1.1 criteria. LIPI, RMH, PMH, dNLR, NLR, PIPO and GRIm scores were calculated. Receiving operator characteristics (ROC) curves and their area under curve (AUC) were used to predict PFS and durable clinical benefit (DCB;stable disease≥6 months or better). Associations with PFS, OS and DCB, where assessed with Cox and logistic regressions. Scores’ correlation was assessed with Spearman rho. Significance was set at p<0.05. Results: We recruited 155 patients (65% male, mean age 63). NSCLC (28%), colorectal (20%) breast (9%) H&N (6%) cancer and melanoma (6%) were the most frequent tumor types. Frequency of the high risk/bad outcome group of each score were: LIPI 13%, RMH 36%, PMH 54%, GRIm 14%, PIPO 6%, NLR 32% and dNRL 27%. Fair accuracy in identifying patients at higher risk of progression or mild accuracy in predicting DCB were observed for the RMH (AUC PFS: 0.7, 95%CI: 0.6-0.8;AUC DCB: 0.6, 0.5-0.8) and LIPI (AUC PFS: 0.7, 95%CI: 0.6-0.8;AUC: 0.6, 0.5-0.7) scores. All other scores provided poor/no accuracy. No significant difference was observed between RMH and LIPI AUC for PFS and DCB (both p>0.05). Additionally, only LIPI and RMH were associated with PFS (p=0.001;p<0.001), OS (p<0.001;p=0.001) and DCB (p=0.034;p=0.010) at univariate analyses. At multivariate analyses RMH and LIPI remained significantly associated with PFS (p=0.030;p=0.021) and OS (p=0.012;p<0.001). A strong correlation between both scores (rho=0.72, p<0.001) was observed. Conclusions: RMH and LIPI scores were sufficiently reliable in assessing the prognosis of patients with advanced solid tumors treated with ICI. They were superior to other analyzed scores in our population and highly correlated. Legal entity responsible for the study: Hospital Clinic y Provincial de Barcelona, Medical Oncology Department. Funding: Has not received any funding. Disclosure: J. Garcia-Corbacho: Financial Interests, Personal, Advisory Board, FGFR inhibitors implementation in clinical practice: Johnson & Johnson Pharmaceutical;Financial Interests, Institutional, Invited Speaker, Participation in clinical trials of the company as PI: Johnson and Johnson Pharmaceutical, Boehringer Ingelheim, Astellas, Cytomx, Incyte, Lilly, Menarini, Merck, Bayer, AstraZeneca, Amgen, Daiichi Sankyo. L. Mezquita: Financial Interests, Personal, Advisory Board: Takeda, AstraZeneca, Roche;Financial Interests, Personal, Invited Speaker: Roche, BMS, AstraZeneca, Takeda;Financial Interests, Personal, Research Grant, SEOM Beca Retorno 2019: BI;Financial Interests, Personal, Research Grant, ESMO TR Research Fellowship 2019: BMS;Financial Interests, Institutional, Research Grant, COVID research Grant: Amgen;Financial Interests, Institutional, Invited Speaker: Inivata, Stilla. N. Baste Rotllan: Non-Financial Interests, Advisory Role: Eisai, MSD, Merck Serono, BioNTech, Roche, BMS, Exelixis. A. Prat: Financial Interests, Personal, Invited Speaker: Roche;Financial Interests, Personal, Invited Speaker, Lecture fees: Novartis, Daiichi Sankyo;Financial Interests, Personal, Advisory Board, Advisory role/consultancy: Novartis, Pfizer, BMS, Puma, Oncolytics Biotech, MSD, Guardant Health, Peptomyc;Financial Interests, Institutional, Invited Speaker, Clinical trials: Daiichi Sankyo;Financial Interests, Institutional, Other, Contracted research: Boehringer, Medica Scientia Inno. Research;Financial Interests, Personal, Advisory Board: AstraZeneca;Financial Interests, Personal, Invited Speaker, Leadership role: Reveal Genomics, SL.;Financial I terests, Personal, Stocks/Shares: Reveal Genomics, Oncolytics Biotech;Financial Interests, Personal, Royalties: Reveal Genomics;Financial Interests, Institutional, Invited Speaker: Roche, AstraZeneca, Novartis;Financial Interests, Personal and Institutional, Invited Speaker: Daiichi Sankyo;Non-Financial Interests, Institutional, Other, Leadership roles: Patronage committee: SOLTI Foundation, Actitud Frente al Cáncer Foundation. All other authors have declared no conflicts of interest.
ABSTRACT
Objectives: To investigate the costs related to COVID-19 patients’ hospital management (from positivity confirmation to discharge, including rehabilitation activities), defining overall resources’ absorption with regard to both the COVID-19 per day and the COVID-19 clinical pathway costs, based on the patients’ clinical condition. Methods: A time-driven activity-based costing approach was implemented to define the costs related to the hospital management of COVID-19 positive patients, according to real-word data derived from six Italian Hospitals, in 2020. The average per-day cost and the average most frequent clinical pathways (considering the internal transfers between wards, based on the patient’s clinical improvement or deterioration), were valorised according to: 1) low-complexity hospitalizations;2) medium-complexity hospitalizations, with presence of hospital beds equipped with C-PAP or non-invasive ventilation;3) high-complexity hospitalizations. Results: The higher the complexity of care, the higher the hospitalization cost per day (low-complexity=€475.86;medium-complexity=€700.20;high-complexity=€1,401.65). Focusing on the entire clinical pathway (ER access, ward transfer, and rehabilitation): i) 29% spent 18.6 days between a medium and a low-complexity hospitalization (€10,778);ii) 16% spent 17.7 days between a low and a medium-complexity hospitalization (€13,902);iii) 12% spent 22.6 days between a high and a medium-complexity hospitalization (€25,817);iv) 8% spent 23.4 days between a medium and a high-complexity hospitalization (€32,141) and v) 5% spent 18.4 days between a low and a high-complexity hospitalization (€23,431). 30% of patients did not experience any ward’s transfer: 17% spent 10.2 within a medium-complexity hospitalization, 9% spent 13 days within a low-complexity hospitalization and 4% spent 11 days within a high-complexity hospitalization, requiring on average €10,113, €6,198 and €21,346 respectively for their management. Conclusions: The study reported the economic evaluation of COVID-19 pandemic in Italy, providing real-world data for an adequate healthcare resources’ allocation, being useful for the further development of proper reimbursement tariffs devoted to COVID-19 positive hospitalized patients.
ABSTRACT
The COVID-19 pandemic has generated an overall slowdown in hospital activities that might lead to delays in healthcare interventions, and the scarcity of resources can raise concerns about ventilators allocation criteria. These circumstances could lead to lawsuits against hospitals and healthcare professionals: together with Regions and States, they may be vulnerable to legal actions, due to the breach of right to health, to physical integrity and right to life, to the manifestation of the informed consent in the medical field or on the basis of contractual or Aquilian obligations. In this context, predicting the litigation rate could be useful to assess the economic impact of a dispute at a local and national level, so that hospital managers and public institutions can perform multi-dimensional and cost/benefit evaluations to decide whether to invest resources to increase critical care surge capacity. In this work we present CLIP (COVID-19 LItigation Prediction), a modeling approach supported by swarm intelligence designed to forecast the occupancy of intensive care units using COVID-19 time-series. CLIP fits a logistic model of COVID-19 patients admission in order to estimate the future number of patients, and then exploits a probabilistic model to predict the number of occupied intensive care beds, whose parameters are calibrated by means of Fuzzy Self-Tuning Particle Swarm Optimization. We assume that each individual rejected from an intensive care unit due to the lack of resources should be considered a potential plaintiff. The development and the availability of such a predictive model, that could further be used within other clinical conditions and important diseases, could help policy-makers in taking decisions under conditions of uncertainty. © 2020 IEEE.