Introduction: Alternate Level of Care (ALC) patients are those who are kept hospitalized although they are medically well enough to be discharged. Those patients wait in acute care because they cannot access an appropriate alternative level of care outside the hospital. ALC leads to the improper consumption of valuable resources that are needed for patients waiting in other departments such as emergency rooms. This reflects poor quality outcomes of the healthcare system and represents a significant economic burden. Moreover, particularly when it concerns older adults, longer stay in hospital results in worsening their health outcomes, declining their functional status and increasing their needs for long-term care. Therefore, ALC is costly from both patient and health care system perspective. Objectives: The main objective of this study was to assess the impact of the Home First strategy on the incidence of ALC. Moreover, the study addressed both the specialized clinical needs (such as dialysis, chemotherapy and mechanical ventilation) and socioeconomic status of ALC patients in order to unveil their association with the ALC length of stay. Methods: This study involved a secondary analysis of data from the Institute for Clinical Evaluation (ICES). The analyzed dataset included a cohort of 6,059,033 hospitalization records of Ontario citizens, aged 65 years and older, who were admitted to an acute care facility between April 2004 and March 2017. The study involved descriptive analytics grouping the dataset into ALC and non-ALC subsets and examined the percentage of ALC hospitalizations, ALC days and reported odds ratios across several patients' characteristics. Results: From 2004 until 2016, ALC patients waited to access an appropriate destination for 10.7 million days. Those numbers represented 19.7% of all hospitalization days across Ontario. ALC was more likely among seniors aged 75-84 (OR 1.36, 95% CI 1.35-1.36), aged 85-94 (OR 2.16, 95% CI 2.15-2.17), aged 95+ (OR 2.46, 95% CI 2.40-2.50), females (OR 1.37, 95% CI 1.35-1.36), those who were hospitalized 90 days prior to their current admission (OR 1.22, 95% CI 1.21-1.22), and those who were admitted to hospital through Emergency Department (OR 2.64, 95% CI 2.62-2.67). Moreover, ALC was 10 times more likely in the subgroup of patients who were discharged to long-term care (LTC) (OR 9.71, 95% CI 9.66-9.77). For the socioeconomic characteristics, this study showed that patients were more likely to have ALC days when they lived in urban areas, had a lower income, and were highly unstable and dependent. Furthermore, patients with special clinical needs spent from 10% to 25% of their total hospitalization length of stay waiting to be discharged to an appropriated alternative level of care. Finally, the study revealed that although the implementation of a Home First strategy resulted in a 26% reduction of ALC hospitalizations and a 13% decrease in ALC days, the percent of patients discharged to LTC did not change. For the subgroup having the highest percentage of ALC hospitalizations (53.4%) and ALC days (40.3%), this reflects a partial failure of the Home First strategy in achieving its main objective of facilitating the discharge of patients to their homes. Conclusions: Policy makers and health care practitioners may benefit from the findings of this study by considering the needs of the ALC patients while planning, allocating resources, and developing polices for discharge, LTC and community care. However, more work is required to quantify the impact of the ALC determinants suggested in this study and assess the efficiency of the current policies and procedures. Introduction: Alternate Level of Care (ALC) patients are those who are kept hospitalized although they are medically well enough to be discharged. Those patients wait in acute care because they cannot access an appropriate alternative level of care outside the hospital. ALC leads to the improper consumption of valuable resources that are needed for patients waiting in other departments such as emergency rooms. This reflects poor quality outcomes of the healthcare system and represents a significant economic burden. Moreover, particularly when it concerns older adults, longer stay in hospital results in worsening their health outcomes, declining their functional status and increasing their needs for long-term care. Therefore, ALC is costly from both patient and health care system perspective. Objectives: The main objective of this study was to assess the impact of the Home First strategy on the incidence of ALC. Moreover, the study addressed both the specialized clinical needs (such as dialysis, chemotherapy and mechanical ventilation) and socioeconomic status of ALC patients in order to unveil their association with the ALC length of stay. Methods: This study involved a secondary analysis of data from the Institute for Clinical Evaluation (ICES). The analyzed dataset included a cohort of 6,059,033 hospitalization records of Ontario citizens, aged 65 years and older, who were admitted to an acute care facility between April 2004 and March 2017. The study involved descriptive analytics grouping the dataset into ALC and non-ALC subsets and examined the percentage of ALC hospitalizations, ALC days and reported odds ratios across several patients' characteristics. Results: From 2004 until 2016, ALC patients waited to access an appropriate destination for 10.7 million days. Those numbers represented 19.7% of all hospitalization days across Ontario. ALC was more likely among seniors aged 75-84 (OR 1.36, 95% CI 1.35-1.36), aged 85-94 (OR 2.16, 95% CI 2.15-2.17), aged 95+ (OR 2.46, 95% CI 2.40-2.50), females (OR 1.37, 95% CI 1.35-1.36), those who were hospitalized 90 days prior to their current admission (OR 1.22, 95% CI 1.21-1.22), and those who were admitted to hospital through Emergency Department (OR 2.64, 95% CI 2.62-2.67). Moreover, ALC was 10 times more likely in the subgroup of patients who were discharged to long-term care (LTC) (OR 9.71, 95% CI 9.66-9.77). For the socioeconomic characteristics, this study showed that patients were more likely to have ALC days when they lived in urban areas, had a lower income, and were highly unstable and dependent. Furthermore, patients with special clinical needs spent from 10% to 25% of their total hospitalization length of stay waiting to be discharged to an appropriated alternative level of care. Finally, the study revealed that although the implementation of a Home First strategy resulted in a 26% reduction of ALC hospitalizations and a 13% decrease in ALC days, the percent of patients discharged to LTC did not change. For the subgroup having the highest percentage of ALC hospitalizations (53.4%) and ALC days (40.3%), this reflects a partial failure of the Home First strategy in achieving its main objective of facilitating the discharge of patients to their homes. Conclusions: Policy makers and health care practitioners may benefit from the findings of this study by considering the needs of the ALC patients while planning, allocating resources, and developing polices for discharge, LTC and community care. However, more work is required to quantify the impact of the ALC determinants suggested in this study and assess the efficiency of the current policies and procedures. / Thesis / Master of Science (MSc)

In Canada, patients who occupy hospital beds but do not require that intensity of care are called Alternate Level of Care (ALC) patients. ALC has numerous negative implications on patient health and the health care system. Early identification of patients who are at risk of becoming ALC could help decision-makers better manage the situation and alleviate this problem. This thesis evaluates the use of various ML algorithms in predicting ALC at two different time points in the patient’s trajectory. Moreover, it identifies the most important predictors of ALC in each time point and provides insights on how adding more information, at the expense of time for decision-making, would improve the predictive accuracy. / Thesis / Master of Science (MSc)