scholarly journals Multilingual Conversational Systems to Drive the Collection of PROs and Integration into Clinical Workflow

2021 ◽  
Vol 18 ◽  
pp. 113-118
Author(s):  
Daniel Hari ◽  
Valentino Šafran ◽  
Umut Arioz ◽  
Izidor Mlakar ◽  
Matej Rojc ◽  
...  

Collection of patient-reported outcomes (PROs) remotely and their usage in the clinical workflow provide an improvement on both patient’s quality of life and cancer care. However, adoption of collecting PROs into the clinical workflow is rare, and existing works still have a lot of issues providing a holistic approach. This paper offers enhancements in the process of collecting PROs by utilization of conversational systems that still provide quite a new but promising way to collect PROs remotely with spoken interaction. Our proposed system provides an interoperability with Fast Healthcare Interoperability Resources (FHIR) server by using a multimodal sensing network (MSN) prepared for the project PERSIST. We introduce components of multimodality while collecting PROs with the help of the mHealth App and Open Health Connect (OHC) platform. As a result, chatbots and 3D embodied conversational agents (ECA) were prepared to interact with the cancer patients in 5 different languages. The intercommunication was provided by MSN and the integration of cancer patients’ PROs into clinical workflow was satisfied. This study was part of a Horizon 2020 project and a preparation phase for clinical trials with cancer patients and clinicians

Symmetry ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1187
Author(s):  
Izidor Mlakar ◽  
Valentino Šafran ◽  
Daniel Hari ◽  
Matej Rojc ◽  
Gazihan Alankuş ◽  
...  

Patient-reported outcomes (PROs) and their use in the clinical workflow can improve cancer survivors’ outcomes and quality of life. However, there are several challenges regarding efficient collection of the patient-reported outcomes and their integration into the clinical workflow. Patient adherence and interoperability are recognized as main barriers. This work implements a cancer-related study which interconnects artificial intelligence (spoken language algorithms, conversational intelligence) and natural sciences (embodied conversational agents) to create an omni-comprehensive system enabling symmetric computer-mediated interaction. Its goal is to collect patient information and integrate it into clinical routine as digital patient resources (the Fast Healthcare Interoperability Resources). To further increase convenience and simplicity of the data collection, a multimodal sensing network is delivered. In this paper, we introduce the main components of the system, including the mHealth application, the Open Health Connect platform, and algorithms to deliver speech enabled 3D embodied conversational agent to interact with the cancer survivors in five different languages. The system integrates cancer patients’ reported information as patient gathered health data into their digital clinical record. The value and impact of the integration will be further evaluated in the clinical study.


2021 ◽  
pp. 107815522199844
Author(s):  
Abdullah M Alhammad ◽  
Nora Alkhudair ◽  
Rawan Alzaidi ◽  
Latifa S Almosabhi ◽  
Mohammad H Aljawadi

Introduction Chemotherapy-induced nausea and vomiting is a serious complication of cancer treatment that compromises patients’ quality of life and treatment adherence, which necessitates regular assessment. Therefore, there is a need to assess patient-reported nausea and vomiting using a validated scale among Arabic speaking cancer patient population. The objective of this study was to translate and validate the Functional Living Index-Emesis (FLIE) instrument in Arabic, a patient-reported outcome measure designed to assess the influence of chemotherapy-induced nausea and vomiting on patients’ quality of life. Methods Linguistic validation of an Arabic-language version was performed. The instrument was administered to cancer patients undergoing chemotherapy in a tertiary hospital's cancer center in Saudi Arabia. Results One-hundred cancer patients who received chemotherapy were enrolled. The participants’ mean age was 53.3 ± 14.9 years, and 50% were female. Half of the participants had a history of nausea and vomiting with previous chemotherapy. The Cronbach coefficient alpha for the FLIE was 0.9606 and 0.9736 for nausea and vomiting domains, respectively, which indicated an excellent reliability for the Arabic FLIE. The mean FLIE score was 110.9 ± 23.5, indicating no or minimal impact on daily life (NIDL). Conclusions The Arabic FLIE is a valid and reliable tool among the Arabic-speaking cancer population. Thus, the Arabic version of the FLIE will be a useful tool to assess the quality of life among Arabic speaking patients receiving chemotherapy. Additionally, the translated instrument will be a useful tool for future research studies to explore new antiemetic treatments among cancer patients.


2021 ◽  
Vol 10 (9) ◽  
pp. 1852
Author(s):  
Gry Assam Taarnhøj ◽  
Henriette Lindberg ◽  
Christoffer Johansen ◽  
Helle Pappot

Patients with urothelial cell carcinoma (UCC) often have comorbidities, which cause trouble for the completion of oncological treatment, and little is known about their quality of life (QoL). The aim of the present study was to obtain and describe patient-reported outcomes (PRO) and QoL data from UCC patients in the treatment for locally advanced muscle-invasive or metastatic UCC. A total of 79 patients with UCC completed four questionnaires (EORTC QLQ-C30, QLQ-BLM30, HADS, and select PRO-CTCAE™ questions) once weekly during their treatment. From those, 26 patients (33%) underwent neoadjuvant treatment for local disease while 53 patients (67%) were treated for metastatic disease. Of all patients, 54% did not complete the planned treatment due to progression, nephrotoxicity, death, or intolerable symptoms during treatment. The five most prevalent PRO-CTCAE grade ≥ 2 symptoms were frequent urination (37%), fatigue (35%), pain (31%), dry mouth (23%), and swelling of the arms or legs (23%). The baseline mean overall QoL was 61 (±SD 24) for all patients (neoadjuvant (73, ±SD 19) and metastatic (54, ±SD 24)) and remained stable over the course of treatment for both groups. A stable overall QoL was observed for the patients in this study. More than half of the patients did not, however, complete the planned treatment. Further supportive care is warranted for bladder cancer patients.


2021 ◽  
Author(s):  
Fabrice Denis

UNSTRUCTURED Abstract Digital electronic patient reported outcome (ePRO) systems for symptom monitoring in cancer patients demonstrated evidence of quality of life and survival benefit in controlled trials. They are beginning to be used in routine oncology practice. Many software editors provide solutions to clinicians but how can clinician choose it? We propose a synthesis of the main questions about effectiveness, safety and functionality of ePRO system that may ask clinician to software providers to be helped in selecting a software in order to obtain the best value of these tools for their patients and their practice.


2014 ◽  
Vol 13 (4) ◽  
pp. 875-884 ◽  
Author(s):  
Kathryn A. Martinez ◽  
Claire F. Snyder ◽  
Jennifer L. Malin ◽  
Sydney M. Dy

AbstractObjective:Despite treatment availability, many cancer patients experience severe pain. Although patient assessments of care are increasingly employed to evaluate quality of care, little is known about its association with cancer symptom burden. The objective of our study was to examine the association between patient-reported quality of care and pain severity in a nationally representative cohort of cancer patients.Method:Quality of care was measured in three domains: physician communication, care coordination/responsiveness, and nursing care. Quality scores were dichotomized as optimal versus nonoptimal. Pain was measured on a scale of 0 (least) to 100 (worst). We utilized multivariable linear regression to examine the association between patient-reported quality of care and pain severity.Results:The analytic sample included 2,746 individuals. Fifty and 54% of patients, respectively, rated physician communication and care coordination/responsiveness as nonoptimal; 28% rated nursing care as nonoptimal. In adjusted models, rating physician communication as nonoptimal (versus optimal) was associated with a 1.8-point higher pain severity (p = 0.018), and rating care coordination/responsiveness as nonoptimal was associated with a 2.2-point higher pain severity (p = 0.006).Significance of results:Patient-reported quality of care was significantly associated with pain severity, although the differences were small. Interventions targeting physician communication and care coordination/responsiveness may result in improved pain control for some patients.


2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Johann Frick ◽  
Daniel Schindel ◽  
Pimrapat Gebert ◽  
Ulrike Grittner ◽  
Liane Schenk

Abstract Background Cancer patients experience psychological and social distress due to their medical treatment and social issues. However, continuous and specialized social support is still lacking. In Germany, a group of company health insurance funds has developed an approach to support cancer patients with monthly structured interviews conducted by specially trained Social Care Nurses. The nurses will identify patient needs in order to provide help with medical, personal, and social matters. One aim of the scientific evaluation is to analyze the effect of the consultations on various patient-reported outcomes, especially quality of life. The evaluation concept will be described in this study protocol. Methods/design The evaluation is a non-randomized, controlled, multi-center intervention study with a mixed-method design. It consists of three research modules which include primary data from questionnaires, and claims data from the health insurance funds. In Module 1, cancer patients will be recruited to form an intervention group (OSCAR, n = 150) and a control group (n = 200) in four study centers for a period of 1 year. One baseline and three follow-up questionnaires will be conducted to survey the patient-reported outcomes. Relevant secondary outcomes are health literacy, participation, and physician-patient communication. In Module 2, claims data will be used to analyze cost effects and thereby assess effectivity and hospitalization. Module 3 will involve a qualitative analysis of project diaries kept by the Social Care Nurses. The diaries will record the nurses’ practical experiences and the benefits of deploying OSCAR across the German healthcare system. Discussion OSCAR is an innovative way of providing cancer patients with continuous support to improve their quality of life. The evaluation concept aims to assess the effects of the monthly consultations by the Social Care Nurses on the patients, and will use a mixed-method design. The results are important for assessing the transferability of OSCAR to the healthcare system as a whole. Trial registration German Clinical Trials Register (DRKS-ID: DRKS00013640). Registered 29 December 2017.


2013 ◽  
Vol 31 (15_suppl) ◽  
pp. e20565-e20565
Author(s):  
Gabrielle Betty Rocque ◽  
Toby Christopher Campbell ◽  
Anne Elizabeth Barnett ◽  
Renae M Quale ◽  
Jens C. Eickhoff ◽  
...  

e20565 Background: Patients with advanced cancer who are hospitalized have high symptom burden and a short life expectancy, which may warrant PCC. Methods: Using sequential cohorts, we prospectively assessed implementation of automatic PCC for hospitalized cancer patients. The primary outcome was hospice utilization. Secondary outcomes included evaluation of changes in quality of life (FACIT-PAL), symptoms (ESAS), satisfaction (FAMCARE), and anxiety and depression (HADS). Surveys were administered at baseline, 2 weeks and 3 months post-hospitalization. Chart abstraction was utilized to assess demographics, resource use, and survival information. Results: Patients were evaluated consecutively (65 in the control group, 70 in the intervention). At admission, 91% reported uncontrolled symptoms: 52% pain; 15% dyspnea. 60% of intervention patients received PCC during their first admission. 54 patients completed surveys (29 control group, 25 PCC group), 64 patients declined or were unable to complete surveys, 16 patients were excluded due to language barriers, physician preference, or not receiving surveys. Using an intent-to-treat analysis, there was no difference between patients in the control and the intervention group in FACIT-PAL (119 ± 29 vs 123 ± 30, p = 0.68 ), ESAS (28 ± 14 vs 26 ± 15, p = 0.74) HADS (13 ± 6.6 vs. 12.± 4.7, p = 0.58), or FAMCARE (58 ± 9.1 vs 59 ± 8.6, p = 0.61). In both groups, patients had modest worsening of symptoms and quality of life over the course of the study. Survival and Health Services data analysis, including hospice referral, is proceeding. Conclusions: Automatic PPC had little impact on patient-reported symptoms and quality of life. Limitations included: small patient population; high rate of incomplete surveys, likely due to illness burden; penetration of the PCC was limited to 60% by patient or provider preference and consultant availability. Our primary outcome analysis (hospice utilization) is forthcoming, as are data on survival and Health Services outcomes.


Sign in / Sign up

Export Citation Format

Share Document