Augmented intelligence to predict 30-day mortality in patients with cancer

2021 ◽  
Author(s):  
Ajeet Gajra ◽  
Marjorie E Zettler ◽  
Kelly A Miller ◽  
Sibel Blau ◽  
Swetha S Venkateshwaran ◽  
...  
Keyword(s):  
Mortality Risk ◽  
Decision Tool ◽  
Short Term ◽  
Algorithm Performance ◽  
Patients With Cancer ◽  
Care Services ◽  
Short Term Mortality ◽  
Palliative Care Services ◽  
Oncology Practice ◽  
Development And Validation

Aim: An augmented intelligence tool to predict short-term mortality risk among patients with cancer could help identify those in need of actionable interventions or palliative care services. Patients & methods: An algorithm to predict 30-day mortality risk was developed using socioeconomic and clinical data from patients in a large community hematology/oncology practice. Patients were scored weekly; algorithm performance was assessed using dates of death in patients’ electronic health records. Results: For patients scored as highest risk for 30-day mortality, the event rate was 4.9% (vs 0.7% in patients scored as low risk; a 7.4-times greater risk). Conclusion: The development and validation of a decision tool to accurately identify patients with cancer who are at risk for short-term mortality is feasible.

scholarly journals Impact of Augmented Intelligence on Utilization of Palliative Care Services in a Real-World Oncology Setting

2021 ◽  
pp. OP.21.00179
Author(s):  
Ajeet Gajra ◽  
Marjorie E. Zettler ◽  
Kelly A. Miller ◽  
John G. Frownfelter ◽  
John Showalter ◽  
...  
Keyword(s):  
Palliative Care ◽  
Mortality Risk ◽  
Real World ◽  
Short Term ◽  
Short Term Mortality ◽  
Medium Risk ◽  
Palliative Care Services ◽  
The Mean ◽  
Oncology Practice ◽  
The Impact

PURPOSE: For patients with advanced cancer, timely referral to palliative care (PC) services can ensure that end-of-life care aligns with their preferences and goals. Overestimation of life expectancy may result in underutilization of PC services, counterproductive treatment measures, and reduced quality of life for patients. We assessed the impact of a commercially available augmented intelligence (AI) tool to predict 30-day mortality risk on PC service utilization in a real-world setting. METHODS: Patients within a large hematology-oncology practice were scored weekly between June 2018 and October 2019 with an AI tool to generate insights into short-term mortality risk. Patients identified by the tool as being at high or medium risk were assessed for a supportive care visit and further referred as appropriate. Average monthly rates of PC and hospice referrals were calculated 5 months predeployment and 17 months postdeployment of the tool in the practice. RESULTS: The mean rate of PC consults increased from 17.3 to 29.1 per 1,000 patients per month (PPM) pre- and postdeployment, whereas the mean rate of hospice referrals increased from 0.2 to 1.6 per 1,000 PPM. Eliminating the first 6 months following deployment to account for user learning curve, the mean rate of PC consults nearly doubled over baseline to 33.0 and hospice referrals increased 12-fold to 2.4 PPM. CONCLUSION: Deployment of an AI tool at a hematology-oncology practice was found to be feasible for identifying patients at high or medium risk for short-term mortality. Insights generated by the tool drove clinical practice changes, resulting in significant increases in PC and hospice referrals.

Outcomes among patients with cancer previously identified as being at risk for 30-day mortality using augmented intelligence.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 12031-12031
Author(s):  
Ajeet Gajra ◽  
Marjorie E. Zettler ◽  
Amy R. Ellis ◽  
Kelly A. Miller ◽  
John G. Frownfelter ◽  
...  
Keyword(s):  
At Risk ◽  
High Risk ◽  
Hospital Admissions ◽  
Short Term ◽  
Patients With Cancer ◽  
Short Term Mortality ◽  
Medium Risk ◽  
Ed Visits ◽  
Oncology Practice

12031 Background: An augmented intelligence (AI) tool using a machine learning algorithm was developed and validated to generate insights into risk for short-term mortality among patients with cancer. The algorithm, which scores patients every week as being at low, medium or high risk for death within 30 days, allowing providers to potentially intervene and modify care of those at medium to high risk based on established practice pathways. Deployment of the algorithm increased palliative care referrals in a large community hematology/oncology practice in the United States (Gajra et al, JCO 2020). The objective of this retrospective analysis was to evaluate the differences in survival and healthcare utilization (HCU) outcomes of patients previously scored as medium or high risk by the AI tool. Methods: Between 6/2018 – 10/2019, the AI tool scored patients on a weekly basis at the hematology/oncology practice. In 9/2020, a chart review was conducted for the 886 patients who had been identified by the algorithm as being at medium or high risk for 30-day mortality during the index period, to determine outcomes (including death, emergency department [ED] visits, and hospital admissions). Data are presented using descriptive statistics. Results: Of the 886 at-risk patients, 450 (50.8%) were deceased at the time of follow-up. Of these, 244 (54.2%) died within the first 180 days of scoring as at-risk, with median time to death 68 days (IQR 99). Among the 255 patients scored as high risk, 171 (67.1%) had died, vs. 279 (44.2%) of the 631 patients who were scored as medium risk (p < 0.001). Of the 601 patients who were scored more than once during the index period as medium or high risk, 342 (56.9%) had died, vs. 108 (37.9%) of the 285 who were scored as at risk only once (p < 0.001). A total of 363 patients (43.1%) had at least 1 ED visit, and 346 patients (41.1%) had at least 1 hospital admission. There was no difference in the proportion of patients scored as high risk compared with those scored as medium risk in ED visits (104 of 237 [43.9%] vs. 259 of 605 [42.8%], p = 0.778) or hospital admissions (100 of 237 [42.2%] vs. 246 of 605 [40.7%], p = 0.684, respectively). Compared with patients scored as medium or high risk only once during the index period, patients who were scored as at-risk more than once had more ED visits (282 of 593 [47.6%] vs. 81 of 249 [32.5%], p < 0.001) and hospital admissions (269 of 593 [45.4%] vs. 77 of 249 [30.9%], p < 0.001). Conclusions: This follow-up study found that half of the patients identified as at-risk for short-term mortality during the index period were deceased, with greater likelihood associated with high risk score and being scored more than once. Over 40% had visited an ED or were admitted to hospital. These findings have important implications for the use of the algorithm to guide treatment discussions, prevent acute HCU and to plan ahead for end of life care in patients with cancer.

scholarly journals Trajectories of mortality risk among patients with cancer and associated end-of-life utilization

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Ravi B. Parikh ◽  
Manqing Liu ◽  
Eric Li ◽  
Runze Li ◽  
Jinbo Chen
Keyword(s):  
Machine Learning ◽  
End Of Life ◽  
Mortality Risk ◽  
Machine Learning Algorithms ◽  
Short Term ◽  
Patients With Cancer ◽  
All Cause Mortality ◽  
Short Term Mortality ◽  
Patients At Risk ◽  
To Receive

AbstractMachine learning algorithms may address prognostic inaccuracy among clinicians by identifying patients at risk of short-term mortality and facilitating earlier discussions about hospice enrollment, discontinuation of therapy, or other management decisions. In the present study, we used prospective predictions from a real-time machine learning prognostic algorithm to identify two trajectories of all-cause mortality risk for decedents with cancer. We show that patients with an unpredictable trajectory, where mortality risk rises only close to death, are significantly less likely to receive guideline-based end-of-life care and may not benefit from the integration of prognostic algorithms in practice.

scholarly journals A machine learning approach to predicting short-term mortality risk in patients starting chemotherapy

2017 ◽  
Author(s):  
Aymen A. Elfiky ◽  
Maximilian J. Pany ◽  
Ravi B. Parikh ◽  
Ziad Obermeyer
Keyword(s):  
Machine Learning ◽  
Mortality Risk ◽  
Palliative Chemotherapy ◽  
Learning Algorithm ◽  
Cancer Center ◽  
Short Term ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Short Term Mortality ◽  
And Performance

ABSTRACTBackgroundCancer patients who die soon after starting chemotherapy incur costs of treatment without benefits. Accurately predicting mortality risk from chemotherapy is important, but few patient data-driven tools exist. We sought to create and validate a machine learning model predicting mortality for patients starting new chemotherapy.MethodsWe obtained electronic health records for patients treated at a large cancer center (26,946 patients; 51,774 new regimens) over 2004-14, linked to Social Security data for date of death. The model was derived using 2004-11 data, and performance measured on non-overlapping 2012-14 data.Findings30-day mortality from chemotherapy start was 2.1%. Common cancers included breast (21.1%), colorectal (19.3%), and lung (18.0%). Model predictions were accurate for all patients (AUC 0.94). Predictions for patients starting palliative chemotherapy (46.6% of regimens), for whom prognosis is particularly important, remained highly accurate (AUC 0.92). To illustrate model discrimination, we ranked patients initiating palliative chemotherapy by model-predicted mortality risk, and calculated observed mortality by risk decile. 30-day mortality in the highest-risk decile was 22.6%; in the lowest-risk decile, no patients died. Predictions remained accurate across all primary cancers, stages, and chemotherapies—even for clinical trial regimens that first appeared in years after the model was trained (AUC 0.94). The model also performed well for prediction of 180-day mortality (AUC 0.87; mortality 74.8% in the highest risk decile vs. 0.2% in the lowest). Predictions were more accurate than data from randomized trials of individual chemotherapies, or SEER estimates.InterpretationA machine learning algorithm accurately predicted short-term mortality in patients starting chemotherapy using EHR data. Further research is necessary to determine generalizability and the feasibility of applying this algorithm in clinical settings.

The effects of temperature on short-term mortality risk in Kuwait: A time-series analysis

2019 ◽  
Vol 171 ◽  
pp. 278-284 ◽  
Author(s):  
Barrak Alahmad ◽  
Ahmed Shakarchi ◽  
Mohammad Alseaidan ◽  
Mary Fox
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Mortality Risk ◽  
Short Term ◽  
Series Analysis ◽  
Short Term Mortality ◽  
Effects Of Temperature

scholarly journals Mortality of Adult Patients With Cancer Admitted to an Intensive Care Unit in Chile: A Prospective Cohort Study

2018 ◽  
pp. 1-9 ◽  
Author(s):  
Sergio Panay ◽  
Carolina Ruiz ◽  
Marcelo Abarca ◽  
Bruno Nervi ◽  
Ignacio Salazar ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Prospective Cohort ◽  
Admission Policy ◽  
Short Term ◽  
Assessment Scores ◽  
Patients With Cancer ◽  
Failure Assessment ◽  
Short Term Mortality ◽  
The Mean

Purpose Increasing numbers of reports have shown acceptable short-term mortality of patients with cancer admitted into the intensive care unit (ICU). The aim of this study was to determine the mortality of critically ill patients with cancer admitted to the ICU in a general hospital in Chile. Materials and Methods This was a prospective cohort trial in which we included all patients with cancer admitted to the ICU between July 2015 and September 2016. Demographic, physiologic, and treatment data were registered, and survival at 30 days and 6 months was evaluated. A prespecified subgroup analysis considering the admission policy was performed. These subgroups were (1) ICU admission for full code management and (2) ICU trial (IT). Results During the study period, 109 patients with cancer were included. Seventy-nine patients were considered in the full code management group and 30 in the IT. The mean age of patients was 60 years (standard deviation [SD], 15), and 56% were male. Lymphoma was the most frequent malignancy (17%), and 59% had not received cancer treatment because of a recent diagnosis. The mean Acute Physiology and Chronic Health Evaluation and Sequential-Related Organ Failure Assessment scores were 22.2 (SD, 7.3) and 7 (SD, 3), respectively. There were no differences in vasopressor, fluid, or transfusion requirements between subgroups. Lactate levels, Sequential-Related Organ Failure Assessment scores (day 1, 3, and 5), complications, and ICU length of stay were similar. In the entire cohort, 30-day and 6-month mortality was 47% and 66%, respectively. There was no difference in mortality between subgroups according to the admission policy. Conclusion Patients admitted to the ICU in a developing country are at high risk for short-term mortality. However, there is a relevant subgroup that achieves 6-month survival, even among patients who undergo an IT.

Integration of palliative care services into standard oncology practice at diagnosis of metastatic lung cancer at VA New York Harbor Healthcare System.

2015 ◽  
Vol 33 (29_suppl) ◽  
pp. 165-165
Author(s):  
Felix Manuel Rivera Mercado ◽  
Carol Luhrs ◽  
Alice Beal ◽  
Maura Langdon ◽  
Joan Secrest ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Palliative Care ◽  
Stage Iv ◽  
Major Advance ◽  
Metastatic Lung Cancer ◽  
Care Services ◽  
National Quality ◽  
Metastatic Lung ◽  
Palliative Care Services ◽  
Oncology Practice

165 Background: The 2012 ASCO provisional clinical opinion addressed the integration of palliative care into standard oncology practice at the time a person is diagnosed with metastatic or advanced cancer. The inclusion of Palliative Care among the National Quality Forum (NQF) framework represented a major advance in palliative care. NQF metrics include chemotherapy administered in the last 14 days of life, hospice less than 3 days before death, ICU or hospital admission, more than one Emergency Room visit in the last 30 days, and death in hospital. Although the use of hospice and other palliative care services has increased, many are enrolled in hospice less than 3 weeks before death. By improving quality of life, cost, and survival in patients with metastatic cancer, palliative care has increasing relevance for the care of patients with cancer. Methods: Retrospective chart review study of lung cancer patients diagnosed at VA from 2010-2013. Inclusion criteria: > 18 years of age with new diagnosis of metastatic lung cancer. Exclusion criteria: < 18 years of age, Stage I-III lung cancer. Results: Total of 125 patients were diagnosed with Stage IV lung cancer. The mean time from diagnosis to death was only 185 days (6.1 months). The VA NYHHS patients were more likely to visit the ED, be admitted to the hospital and ICU in the last 30 days of life, and subsequently die in the hospital. Conclusions: Several confounders were identified, including climate related closure of facilities (2012 Sandy storm), lack of social support, low ICU admission criteria, burial benefits for patients dying in a VA, and delay in transition to Hospice. Currently 392 patients with stage IV solid tumors diagnosed 2010-2014 are being studied. [Table: see text]

Using a supportive care framework to understand and improve palliative care among cancer patients in Africa

2015 ◽  
Vol 14 (3) ◽  
pp. 284-301 ◽  
Author(s):  
David S. Busolo ◽  
Roberta L. Woodgate
Keyword(s):  
Palliative Care ◽  
Supportive Care ◽  
Cancer Patients ◽  
Care Needs ◽  
African Countries ◽  
Research Education ◽  
Patients With Cancer ◽  
Care Services ◽  
Incidence And Mortality ◽  
Palliative Care Services

ABSTRACTObjective:Cancer incidence and mortality are increasing in Africa, which is leading to greater demands for palliative care. There has been little progress in terms of research, pain management, and policies related to palliative care. Palliative care in Africa is scarce and scattered, with most African nations lacking the basic services. To address these needs, a guiding framework that identifies care needs and directs palliative care services could be utilized. Therefore, using the supportive care framework developed by Fitch (Fitch, 2009), we here review the literature on palliative care for patients diagnosed with cancer in Africa and make recommendations for improvement.Method:The PubMed, Scopus, CINAHL, Web of Science, Embase, PsycINFO, Social Sciences Citation Index, and Medline databases were searched. Some 25 English articles on research from African countries published between 2004 and 2014 were selected and reviewed. The reviewed literature was analyzed and presented using the domains of the supportive care framework.Results:Palliative care patients with cancer in Africa, their families, and caregivers experience increasing psychological, physical, social, spiritual, emotional, informational, and practical needs. Care needs are often inadequately addressed because of a lack of awareness as well as deficient and scattered palliative care services and resources. In addition, there is sparse research, education, and policies that address the dire situation in palliative care.Significance of Results:Our review findings add to the existing body of knowledge demonstrating that palliative care patients with cancer in Africa experience disturbing care needs in all domains of the supportive care framework. To better assess and address these needs, holistic palliative care that is multidomain and multi-professional could be utilized. This approach needs to be individualized and to offer better access to services and information. In addition, research, education, and policies around palliative care for cancer patients in Africa could be more comprehensive if they were based on the domains of the supportive care framework.

Sign in / Sign up

Export Citation Format

Share Document