Oxygen Prescription Research Articles

Supplemental oxygen prescriptions after hospitalization for coronavirus disease 2019

BackgroundThe role of home oxygen therapy for patients recovering from Coronavirus Disease 2019 (COVID-19) pneumonia, characterized by impaired gas exchange, is not well-defined. ObjectivesTo compare the characteristics, duration, odds of receiving, and continuing to receive home oxygen prescriptions between patients discharged home after COVID-19 pneumonia hospitalization and those discharged after non-COVID-19 pneumonia. MethodsFrom April 2020 to March 2021, 52,951 patients with COVID-19 pneumonia (53.6 % women, 64 % White) were identified, and from January 2019 to December 2019, 26,701 patients with non-COVID pneumonia (53.9 % women, 76.7 % White) were identified, using the Optum Clinformatics Data Mart Database. New oxygen prescriptions were identified through Healthcare Common Procedure Coding Systems codes. Propensity score matching adjusted for confounders, and Cox regression analysis was conducted to compare post-discharge oxygen use. ResultsFollowing hospitalization, oxygen was prescribed to 52,951 patients with COVID-19 pneumonia and 26,701 patients with non-COVID pneumonia in the United States. The COVID-19 pneumonia group were four times more likely to be prescribed supplemental oxygen compared to the non-COVID-19 pneumonia group (OR 4.22; 95 % confidence interval [CI] 3.76–4.74). This trend persisted in sensitivity analyses: ICU patients (OR 4.05; 95 % CI 3.36–4.88) and those who received both ICU admission and mechanical ventilation (OR 3.84; 95 % CI 2.32–6.37). Hispanic patients had the highest likelihood of receiving a supplemental oxygen prescription after discharge (OR 6.75; 95 % CI 5.03–9.05). ConclusionsPost-hospitalization, one in five patients with COVID-19 received prescriptions for supplemental oxygen, which was significantly higher than the proportion of patients with non-COVID-19 pneumonia.

The pregnant patient with pulmonary arterial hypertensionand her offspring in the current era. Time to take into account the vasoreactive profile

Abstract Background and aims Pregnancy impose physiological changes that may be difficult to accomplish for women with pulmonary arterial hypertension (PAH). This study evaluates the impact that pregnancy carries in a PAH population managed in a timely manner and whether patients responders to calcium channel blockers (CCB) deserve specific recommendations because of a different prognosis. Methods A retrospective, longitudinal cohort study. All PAH pregnant patients managed at our institution between February 2010 and December 2023 were included. Clinical characteristics at baseline were recorded. Mortality, major complications (maternal death and cardiogenic shock requiring mechanical circulatory support -MCS- or inotropes) and minor complications (hospital admissions for cardiac reason, PAH therapy uptitration and oxygen prescription) were evaluated over the pregnancy course. Long-term follow-up was also assessed. Gestational age, neonatal weight and complications in the new-born (invasive and non-invasive ventilation, inotropic support and neonatal death) were studied. Data were compared between vasoreactive and non-vasoreactive patients. Results 29 patients were studied (median age 31.5, 27-32.7). 8 underwent early termination of pregnancy and 21 decided to proceed. From the latter group, 7 were responders to CCB and none presented complications over the pregnancy course. From the remaining 14 non-respo nders who completed their pregnancy, 13 (92.9%) presented minor complications: 11 (79%) were started on the prostacyclin pathway, 5 (35.7%) required inotropic support, 5 (35.7%) oxygen prescription; and 5 (35.7%) experienced major complications: 2 (14.3%) required MCS, 5 (35.7%) inotropic support, and one patient died (7%). Over a median follow-up period of 5 years (1.2-8.5), 2 patients died from the non-responder cohort (1.4%); while no patient responder to CCB experienced complications; moreover, none lost her vasoreactive response. All the new-borns from non-vasoreactive patients were delivered prematurely; while those from vasoreactive patients reached week 37 in the 85,7% of the cases. One of the new-borns from the non-vasoreactive cohort died, and there was a non-significant trend towards a fewer rate of complications in the vasoreactive offspring (42.9 Vs. 84.6, p = 0.054). Conclusions In spite of the continuous advances in PAH management, pregnancy still associates high maternal and neonatal morbidity. Nevertheless, vasoreactive PAH patients presented a completely different maternal and neonatal prognosis which may prompt specific recommendations for this particular subgroupOutcomes by vasoreactivity profilePregnancy course for the 21 PAH patients

Supplemental Oxygen Use, Outcomes, and Spending in Patients With COPD in the Medicare Competitive Bidding Program

The Medicare Competitive Bidding Program (CBP), a policy that reduced durable medical equipment prices, was implemented starting in 2011. Legislation introduced in 2024 aims to remove supplemental oxygen from the CBP because of concerns that recent decreases in oxygen prescribing are due to lower prices set by the CBP, which may have decreased supply and, in turn, limited oxygen access for patients with chronic lung diseases. However, low-value prescribing of oxygen is also prevalent in practice, and decreased oxygen prescription rates may not have necessarily caused harm. Little is known about the association of the CBP with patient use, outcomes, or spending. To examine the association between the 2011 and 2013 implementation of the CBP and supplemental oxygen use, clinical outcomes, and supplemental oxygen spending among patients with chronic obstructive pulmonary disease (COPD). This cohort study used a difference-in-differences (DID) method to evaluate the association between implementation of the CBP and the outcomes of interest. Patients aged 65 to 100 years with COPD living in CBP areas were compared with those living in areas where the CBP was not yet or never implemented. The study included 100% fee-for-service Medicare data of beneficiaries enrolled between July 1, 2009, and December 31, 2015. The data analysis was performed between June 6, 2023, and August 16, 2024. The 2011 and 2013 implementation cycles of the Medicare CBP. The primary outcomes were new prescriptions of oxygen during a 6-month period among beneficiaries with COPD and discontinuation of oxygen during a 6-month period among beneficiaries with COPD previously prescribed oxygen. Secondary outcomes included switches between oxygen types (gas, liquid, or concentrator), all-cause mortality, all-cause unplanned hospitalizations, COPD hospitalizations, and mean monthly allowed charges (total spending) over a 6-month period. The analysis was performed using the Callaway-Sant'Anna method, a dynamic DID model for policies with staggered implementation. Among 5 753 308 Medicare beneficiaries with COPD (mean [SD] age, 79.2 [8.4] years; 55.1% female), 25.9% received supplemental oxygen for at least one 6-month period during the study. The CBP was not associated with differential changes in new oxygen prescribing (DID estimate, -0.19 percentage points; 95% CI, -2.45 to 2.08 percentage points) or oxygen discontinuations (DID estimate, -0.77 percentage points; 95% CI, -8.15 to 6.60 percentage points). Similarly, differential changes were not observed in the secondary outcomes of oxygen switches (DID estimate, -0.04 percentage points; 95% CI, -0.44 to 0.37 percentage points), all-cause mortality (DID estimate, 0.16 percentage points; 95% CI, -7.52 to 7.84 percentage points), all-cause unplanned hospitalizations (DID estimate, -0.20 percentage points; 95% CI, -10.94 to 10.53 percentage points), or COPD hospitalizations (DID estimate, -0.04 percentage points; 95% CI, -2.57 to 2.48 percentage points). Differential changes were observed for mean monthly allowed charges (DID estimate, -$326.22; 95% CI, -$434.76 to -$217.68). In this study, among beneficiaries with COPD, the Medicare CBP was associated with differentially lower spending but not differential changes in oxygen use or clinical outcomes. This study did not find evidence supporting ongoing policy efforts to remove supplemental oxygen from the CBP.

Improving Compliance With Valid Oxygen Prescriptions for Surgical Inpatients in a District General Hospital: A Single-Centre Quality Improvement Study

Improving Compliance With Valid Oxygen Prescriptions for Surgical Inpatients in a District General Hospital: A Single-Centre Quality Improvement Study

Decoding oxygen prescriptions: electronic health record documentation versus patient-reported use

BackgroundLong term oxygen therapy (LTOT) is prescribed for hypoxemia in pulmonary disease. Like other medical therapies, LTOT requires a prescription documenting the dosage (flow rate) and directions (at rest, with activity) which goes to a supplier. Communication with patients regarding oxygen prescription (flow rate, frequency, directions), monitoring (pulse oximetry) and dosage adjustment (oxygen titration) differs in comparison with medication prescriptions. We examined the communication of oxygen management plans in the electronic health record (EHR), and their consistency with patient-reported LTOT use.Study design and methodsA cross-sectional study was conducted in 71 adults with chronic lung disease on LTOT. Physician communication regarding oxygen management was obtained from the EHR. Participants were interviewed on their LTOT management plan. The information from each source was compared.ResultsThe study population was, on average, 64 years, two-thirds women, and most used oxygen for over 3 years. Only 45% of both at-rest and with-activity oxygen prescriptions were documented in the Electronic Health Record (EHR). Less than 20% of prescriptions were relayed to the patient in the after-visit summary. Of those with EHR-documented oxygen prescriptions, 44% of patients adhered to prescribed oxygen flow rates. Nearly all patients used a pulse oximeter (96%).InterpretationWe identified significant gaps in communication of oxygen management plans from provider to patient. Even when the oxygen prescription was clearly documented, there were differences in patient-reported oxygen management. Critical gaps in oxygen therapy result from the lack of consistent documentation of oxygen prescriptions in the EHR and patient-facing documents. Addressing these issues systematically may improve home oxygen management.

Improving oxygen prescription: effective delivery of the treatment for the lungs

Improving oxygen prescription: effective delivery of the treatment for the lungs

‘Let him die in peace’: understanding caregiver’s refusal of medical oxygen treatment for children in Nigeria

IntroductionEfforts to improve oxygen access have focused mainly on the supply side, but it is important to understand demand barriers, such as oxygen refusal among caregivers. We therefore aimed to...

Improving oxygen prescription on the acute medical unit: a quality improvement project

Improving oxygen prescription on the acute medical unit: a quality improvement project

Clinical Audit: Oxygen Prescription with Target Saturations in Post Anesthesia Care Unit

Background: Supplemental oxygen therapy is commonly administered to the majority of postoperative surgical patients in order to prevent hypoxemia, which is one of the most common and significant respiratory problems following surgery. Furthermore, although regular supplemental oxygen administration is not advised for non-hypoxemic patients suffering from a number of acute conditions, including acute coronary syndrome and stroke, high-dose oxygen therapy is advised in a few specific situations to lower the risk of surgical site infections (SSIs) following surgery. In the proposed audit, we examine the practice of oxygen prescription related to the oxygen therapy. According to Choudhury et al. [1], the primary goal of this audit is to evaluate both the physician and nursing team follow the guidelines in the prescription, monitoring, and documentation of oxygen utilization. Its goals are to identify presently non-compliant with local hospital guidelines and provide solutions to help the hospital improve compliance. Methods: 30 patients in PACU were monitored for supplementary oxygen treatment over a month during February 2024. The oxygen prescription of all patients was analyzed using their prescription drug kardex. Result: Out of 30 total patients, there is a valid oxygen therapy prescription in main PACU of CUH (100%), oxygen prescription section in the PACU drug chart completed (3.3%), correct target oxygen saturation is prescribed for the 1 patient (3.3%), patient with a target saturation range (0%), patient have a valid oxygen delivery device prescribed on the drug chart (3.3%), valid time duration for oxygen delivery mentioned in the drug chart (0%), documentation contain observation of oxygen saturation (100%) Conclusions: This audit uncovered major gaps in tertiary care hospital oxygen prescription. As many PACU patients who use supplemental oxygen are still at risk of developing hypoxic injury due to non-complaint with local guidelines for oxygen prescription. The training of physicians and nurses in the use of oxygen should be updated regularly.

Oxygen as an abortive therapy in cluster headache: a narrative review and clinical practice aspects.

Cluster headache (International Classification of Headache Disorders third edition, ICHD-3 3.1) is a primary headache disorder affecting around 0.12% of individuals. It is characterized by severe headache attacks causing significant negative impact on the lives of patients. While administration of 100% oxygen is considered to be the first-choice acute treatment, undertreatment also exists. Reasons for undertreatment may entail problems with the correct prescription of oxygen, reimbursement issues or the practical implementation of home oxygen therapy. The aim of this manuscript is to review the scientific evidence on oxygen therapy for cluster headache and provide a practical guidance for both physicians and patients to optimize its use in an acute setting. The current evidence of the administration of 100% oxygen as a safe and effective treatment for cluster headache is strong. Based on several clinical trials and surveys, the recommended flow rates range between 12 and 15L/min via a non-rebreathing mask, for at least fifteen minutes. The frequency of cluster headache attacks and thus the need for acute treatment can be very high. Fortunately, the Belgian social security system provides a full and lifetime reimbursement of oxygen therapy for cluster headache if the diagnosis and the need for this therapy has been certified by a neurologist, neurosurgeon or neuropsychiatrist.

New score to predict COVID-19 progression in vaccine and early treatment era: the COVID-19 Sardinian Progression Score (CSPS)

BackgroundSeveral scores aimed at predicting COVID-19 progression have been proposed. As the variables vaccination and early SARS-CoV-2 treatment were systematically excluded from the prognostic scores, the present study's objective was to develop a new model adapted to the current epidemiological scenario.MethodsWe included all patients evaluated by the Infectious Disease Unit in Sassari, with SARS-CoV-2 infection and without signs of respiratory failure at the first evaluation (P/F > 300). Disease progression was defined by the prescription of supplemental oxygen. In addition, variables related to demographics, vaccines, comorbidities, symptoms, CT scans, blood tests, and therapies were collected. Multivariate logistic regression modelling was performed to determine factors associated with progression; any variable with significant univariate test or clinical relevance was selected as a candidate for multivariate analysis. Hosmer–Lemeshow (HL) goodness of fit statistic was calculated. Odds ratio values were used to derive an integer score for developing an easy-to-use progression risk score. The discrimination performance of the risk index was determined using the AUC, and the best cut-off point, according to the Youden index, sensitivity, specificity, predictive value, and likelihood ratio, was chosen.Results1145 patients [median (IQR) age 74 (62–83) years; 53.5% males] were enrolled; 336 (29.3%) had disease progression. Patients with a clinical progression were older and showed more comorbidities; furthermore, they were less vaccinated and exposed to preventive therapy. In the multivariate logistic regression analysis, age ≥ 60 years, COPD, dementia, haematological tumours, heart failure, exposure to no or one vaccine dose, fever, dyspnoea, GGO, consolidation, ferritin, De Ritis ≥ 1.2, LDH, and no exposure to early anti-SARS-CoV-2 treatment were associated with disease progression. The final risk score ranged from 0 to 45. The ROC curve analysis showed an AUC of 0.92 (95% CI 0.90–0.93) with a 93.7% specificity and 72.9% sensitivity. Low risk was defined when the cut-off value was less than 23. Three risk levels were identified: low (0–23 points), medium (24–35), and high (≥ 36).ConclusionsThe proportion of patients with progression increases with high scores: the assessment of the risk could be helpful for clinicians to plan appropriate therapeutic strategies.

Effect of a lower target oxygen saturation range on the risk of hypoxaemia and elevated NEWS2 scores at a university hospital: a retrospective study

BackgroundThe optimal target oxygen saturation (SpO2) range for hospital inpatients not at risk of hypercapnia is unknown. The objective of this study was to assess the impact on oxygen usage...

Automated audit of hospital oxygen use devised during the COVID-19 pandemic

BackgroundThe British Thoracic Society (BTS) has organised intermittent audits of hospital oxygen use in UK hospitals since 2008. Manual audits are time-consuming and subject to human errors. Oxygen prescribing and...

104 Oxygen prescription on a specialist geriatric Ward

Abstract Background Oxygen delivery is an extremely useful tool in treating hypoxaemia. While it has beneficial effects when administered at correct doses it can also lead to serious adverse outcomes when not delivered correctly. Given this, oxygen should be treated as any other drug we use in practice and prescribed accordingly. Studies done around the world show very poor rates of appropriate oxygen prescription. This is particularly important on a ward which specialises in care for the older adult, where neurocognitive disorders, delirium and multi-morbidity is common. Methods An audit was carried out on all patients admitted to the specialist geriatric ward over a two week period, documenting whether the patient was receiving oxygen therapy and if so whether it was charted appropriately. Following this education was provided to staff on the ward and posters were hung at the oxygen ports as a reminder to ensure oxygen was prescribed in the Kardex. A re-audit was then carried out, measuring any change in practice. Results Following the initial audit, 120 new patients were admitted to the ward, 25 of which were receiving oxygen therapy (21%). Of the 25, only 7 had oxygen prescribed (28%). Following staff education and the introduction of reminder posters at the oxygen ports a reaudit was carried out. 103 new patients were admitted to the ward, 18 of which were receiving oxygen therapy (17%). Of the 18, 17 had oxygen prescribed appropriately (94%). Conclusion Simple reminders can influence behaviour greatly. Appropriate oxygen prescription improved three-fold with an inexpensive, simple intervention.

Supplemental Oxygen Therapy in Interstitial Lung Disease: A Narrative Review.

Patients with interstitial lung diseases (ILD) often have hypoxemia at rest and/or with exertion for which supplemental oxygen is commonly prescribed. The number of patients with ILD who require supplemental oxygen is unknown though estimates suggest it could be as much as 40%, many of whom may require high flow support (>4 L/min). Despite its frequent use, there is limited evidence for supplemental oxygen's impact on clinical outcomes in ILD with recommendations for its use primarily based on older studies in patients with chronic obstructive pulmonary disease (COPD). Oxygen use in ILD is rarely included as an outcome in clinical trials. Available evidence suggests that supplemental oxygen in ILD may improve quality of life and some exercise parameters in patients whose hypoxemia is a limiting factor; however, oxygen therapy also places new burdens and barriers on some patients that may counter its beneficial effects. The cost of supplemental oxygen in ILD is also unknown but likely represents a significant portion of overall healthcare costs in these patients. Current Centers for Medicare and Medicaid (CMS) reimbursement policies provides only modest increase in payment for high oxygen flows which may negatively impact access to oxygen services and equipment for some ILD patients. Future studies should examine clinical and quality of life outcomes for oxygen use in ILD. In the meantime, given the current limited evidence for supplemental oxygen and considering cost factors and other barriers, providers should take a patient-focused approach when considering supplemental oxygen prescriptions in patients with ILD.

A Quality Improvement Study to Improve Oxygen Prescription in the PICU of a Tertiary Care Centre in Delhi, India.

Introduction Oxygen has been gravely misused since its inception as a therapeutic agent. There is a deficit of audits and baseline data for the Indianpopulation, especially in the pediatric age group, which doesn't allow for standardization of protocols and guidelines. Objective Our study aimed at increasing valid prescription rates to 90% by implementation of quality improvement interventions, and assessing knowledge and perception of healthcare workers towards oxygen therapy. Methodology It followed a before-and-after prospective observational study model where baseline audit data was compared with data observed after the implementation of quality improvement strategies. The data was collected through an audit of the medical records of all pediatric patients receiving oxygen therapy in the PICU. Knowledge and perception of healthcare workers about oxygen therapy were assessed via a self-designed questionnaire. The study was undertaken in three phases, including Quality Improvement (QI) team formation and data collection, root cause analysis, and implementation of Plan-Do-Study-Act (PDSA) cycles. Observations and results In the baseline audit, 1.4% of the prescriptions were complete and valid. Subsequently, over the course of four PDSA cycles, valid prescription rates increased; 62.07% in the first, 79.51% in the second, 81.81% in the third, and 91.42% in the fourth cycle respectively. After applying the chi-square test to compare PDSA4 and baseline data, the p-values for written prescriptions and target saturation were found to be statistically significant. In the healthcare worker survey, we found that 100% of them were aware of indications of oxygen prescription, FiO2, and side effects of excessive usage of oxygen therapy, 95% were aware of conditions affecting pulse-oximetry in the pediatric age group, and 75% knew about target saturation and its significance and the procedure to change alarm settings on the monitor. Conclusion Currently, there exists a lack of effective oxygen prescription audits, especially in India, which can be attributed to a lack of awareness and partly, a lack of initiative. Quality improvement initiatives are effective in improving the valid oxygen prescription rate. However, sustained goals can be achieved through regular audits only.

Clinical Practices Surrounding the Prescription of Home Oxygen in Patients With COPD and Desaturation.

While home oxygen therapy increases survival in patients with chronic obstructive pulmonary disease (COPD) who have severe resting hypoxemia, recent evidence suggests that there is no survival benefit of home oxygen for patients with COPD who have isolated exertional desaturation. We aimed to understand clinician practice patterns surrounding the prescription of home oxygen for patients with COPD. We conducted semi-structured qualitative interviews via videoconference with 15 physicians and 3 nurse practitioners who provide care for patients with COPD. Clinicians were recruited through the American Lung Association Airways Clinical Research Centers. Interview guides were created with the assistance of patient investigators and included questions regarding clinician practices surrounding the prescription of oxygen for patients with COPD and the use of clinical guidelines. Interviews were recorded, transcribed, and coded for themes. Of the 18 clinician interviewees, one-third were women, with most participants (n=11) being < 50 years old. Results of the semi-structured interviews suggested research evidence, clinical experience, and patient preferences contributed to clinician decision-making. Most clinicians described a shared decision-making process for prescribing home oxygen for patients, including discussion of risks and benefits, and developing an understanding of patient values and preferences. Clinicians did not use a structured tool to conduct these conversations. Clinicians consider a number of patient and clinical factors when prescribing home oxygen therapy, often using a shared decision-making process. Tools to support shared decision-making about the use of home oxygen are needed.

Doctors' and Nurses' Knowledge and Perceived Barriers Regarding Acute Oxygen Therapy in a Tertiary Care Hospital in Nigeria.

Oxygen may cause serious consequences when administered wrongly. This study aimed to assess doctors' and nurses' knowledge of acute oxygen therapy and perceived delivery barriers. We conducted a cross sectional study among 202 healthcare providers (134 doctors and 68 nurses) in a Nigerian hospital. The validated Acute Oxygen Therapy Questionnaire (AOTQ), which consisted of 21 knowledge assessment questions, was self administered by participants. Provider's knowledge was classified as good if the score was≥80% and poor if < 60%. Overall, 26.7% (37.3% doctors and 5.9% nurses) had good knowledge of acute oxygen therapy (AOT), 35.9% were aware, and 19.3% used the AOT guidelines. The commonest source of knowledge on oxygen therapy was medical /nursing school (75.2%). The participants' mean knowledge score was 14.75 ± 2.83(possible score of 0-21). Doctors in postgraduate (PG) training obtained the highest score (15.96±2.48) among the participants (F=12.45, df=4, p<0.001). Most doctors (62%) and 23.5% of nurses considered oxygen as a drug. More doctors (52.2%) than nurses (14.7%) believed that a doctor's order was mandatory before oxygen administration, contrary to guidelines recommendations. Most nurses did not know that breathlessness does not always signify hypoxemia and that asymptomatic anemia was not an indication for oxygen. Concerning oxygen prescription, 39.7% of nurses and 64.2% of doctors knew that it should be prescribed to achieve a target saturation range rather than a fixed dose. In acute oxygen delivery in COPD, doctors and nurses exhibited poor knowledge of the appropriate device and flow rate. The reported barriers to oxygen delivery were: a shortage of oxygen supply, inadequate delivery devices, power outages and out of pocket costs. A significant proportion of doctors and nurses had poor knowledge of acute oxygen therapy, poor awareness and infrequently used AOT guidelines, and reported pertinent delivery barriers that warrant educational and administrative interventions.

Use of Palliative Oxygen in Cancer Patients.

Background: Despite the lack of evidence to support the use of palliative oxygen to relieve dyspnea at the end of life, its prescription is widespread and often supported by local and national practice guidelines. Objectives: The objectives of this study were (1) to determine to what extent oxygen prescriptions meet the proposed prescription criteria in our institution, (2) to examine the indication of individual prescriptions in relation to the severity of dyspnea and (3) to review the utilization of opioids in patients receiving palliative oxygen. Methods: Retrospective chart review of cancer patients who were prescribed palliative oxygen between April 2015 and January 2020 through a respiratory home care program in Quebec City, Canada. According to provincial prescription guidelines, palliative oxygen was provided and reimbursed in case of severe hypoxemia (pulse oximetry saturation at rest < 88%) in cancer patients with an estimated prognosis of less than 3months. Results: 134 patients receiving palliative oxygen were included; 25 (19%) did not fulfill reimbursement criteria. Median survival was 44 days. At initiation of palliative oxygen, 48 patients (36%) had only mild or moderate dyspnea (Medical Research Council dyspnea score 1-3), 26 (19%) did not receive opioids, and 9 (7%) were prescribed palliative oxygen without being dyspneic or receiving opioids. Conclusion: Most prescriptions of palliative oxygen met the proposed prescription criteria in our institution. Half of those who received palliative oxygen were only mildly dyspneic and/or were not receiving opioids at the time of the prescription.

Developing an AI-assisted clinical decision support system to enhance in-patient holistic health care.

Holistic health care (HHC) is a synonym for complete patient care, and as such an efficient clinical decision support system (CDSS) for HHC is critical to support the judgement of physician's decision in response of patient's physical, emotional, social, economic, and spiritual needs. The field of artificial intelligence (AI) has evolved considerably in the past decades and many AI applications have been deployed in various contexts. Therefore, this study aims to propose an AI-assisted CDSS model that predicts patients in need of HHC and applies an improved recurrent neural network (RNN) model, long short-term memory (LSTM) for the prediction. The data sources include in-patient's comorbidity status and daily vital sign attributes such as blood pressure, heart rate, oxygen prescription, etc. A two-year dataset consisting of 121 thousand anonymized patient cases with 890 thousand physiological medical records was obtained from a medical center in Taiwan for system evaluation. Comparing with the rule-based expert system, the proposed AI-assisted CDSS improves sensitivity from 26.44% to 80.84% and specificity from 99.23% to 99.95%. The experimental results demonstrate that an AI-assisted CDSS could efficiently predict HHC patients.