scispace - formally typeset
Search or ask a question
Book ChapterDOI

Pervasive Intelligent Decision Support System – Technology Acceptance in Intensive Care Units

01 Jan 2013-pp 279-292
TL;DR: Assessment of how the users accept the PIDSS at level of usability and their importance in the Decision Making Process shows that although the users are satisfied with the offered information recognizing its importance, they demand for a faster system.
Abstract: Intensive Care Units are considered a critical environment where the decision needs to be carefully taken. The real-time recognition of the condition of the patient is important to drive the decision process efficiently. In order to help the decision process, a Pervasive Intelligent Decision Support System (PIDSS) was developed. To provide a better comprehension of the acceptance of the PIDSS it is very important to assess how the users accept the system at level of usability and their importance in the Decision Making Process. This assessment was made using the four constructs proposed by the Technology Acceptance Methodology and a questionnaire-based approach guided by the Delphi Methodology. The results obtained so far show that although the users are satisfied with the offered information recognizing its importance, they demand for a faster system.

Summary (5 min read)

1 Introduction

  • Decision making in Intensive Medicine (IM) is a crucial process because deals with critical condition patients.
  • This system can give to the ICU staff a better comprehension about the patient condition and at the same time predict future situations.
  • To implement an online data acquisition component; R2.
  • I.e., the results related to DMP.
  • The first and second sections introduce the work and make an overview of the concepts and work previous performed.

2 Background

  • During 2009 when this project started the ICU information system was composed by a set of information silos.
  • The ICU professionals need to access to more than five hospital applications to obtain important information and to make their decisions.
  • Now with the introduction of INTCare they have the most important information available in the Electronic Nursing Record (ENR) and they can obtain new knowledge automatically moments after the patient documentation.
  • This situation only was possible with the modification made by INTCare project and the introduction of new knowledge into the ICU DMP.

2.1 INTCare

  • INTCare [7, 8] is an IDSS to predict organ failure and patient outcome for the next 24 hours in real-time using online learning.
  • The research and modifications done allowed to obtain new types of data in an electronically format and in real-time [9, 10].
  • The new reality and the new environment created [11] allow for obtaining new knowledge fundamental to the decision process predicting patient condition, scoring the ICU measures and tracking critical events automatically and in real-time.
  • The data is obtained through a streaming process and the knowledge attained is disseminated in situated devices.

2.2 Decision Making Process in Intensive Care Units

  • Making decisions in ICU is a complicated and danger process, because all tasks need to be performed quickly and accurately [1].
  • The ICU professionals deal with patients in serious life-risk.
  • The use of technologies to support this type of process is welcome [2] however, normally this type of systems aren't helping, i.e., don’t present the accurate information in the right time and in the right place.
  • These types of situations complicate the decision process.
  • In order to overcome this situation some modifications were made in the ICU environment [11] and in the DMP.

2.3 Technology Acceptance Methodology and Delphi Methodology

  • One of the most used models in this area is the Technology Acceptance Methodology.
  • “TAM is adapted from the Theory of Reasoned Action (TRA) model which describes human behaviours in a specific situation” [12].
  • This model is also important because it gives an understanding about the acceptance of the decision support by the ICU staff and how can be useful in the course of their daily work.
  • The principles of the Delphi method involves the use of questionnaires being one of its key features [13] the preservation of anonymity of the participants.
  • The correlations of the answers were evaluated through the Kendall's tau (τ) coefficient.

3.1 Data Acquisition System (R1)

  • The first requirement was resolved with the implementation of a gateway.
  • The gateway is connected to the vital signs monitors, reads the patient information and stores it on a database through the data acquisition agent.
  • In this phase two problems appear: missing patient identification (PID) and the acquisition of bad values.
  • To overcome these problems two triggers were developed.
  • This second process uses the range of values pre-defined by ICU.

3.2 Laboratory (R2)

  • Regarding to the laboratory, an effort was made to have the lab results in an open format, i.e., accessible electronically and able to be handled without restrictions.
  • The main objective was making the results available for ICU immediately after the patient exams are concluded.
  • This change gives the possibility to have the results in a comparative format during the patient stay in ICU.
  • Those exams have different types and are executed by different services and at different hours [16].

3.3 Open Access to Prescriptions (R3)

  • In this point the objective was deal with pharmacy and to study the possibility to construct an easy access to patient prescriptions.
  • These prescriptions were totally controlled by pharmacy and whenever someone needed to consult the patient therapeutic plan had to open a too slow platform.
  • Now, the interaction between the pharmaceutical system and ENR is made by an agent.
  • Periodically, the ENR agent sends a request to the pharmacy drugs system and then, the requested data is sent to a database table [16].

3.4 Electronic Nursing Record (R4 and R5)

  • Electronic Nursing Record (ENR) is a platform that it was developed with the objective to receive all medical data and put it available electronically and in real-time to the physicians and nurses in an hourly mode.
  • ENR can achieve two requirements because being it electronic can dematerialize the processes and due the interoperability mode can interoperate with all of others ICU data sources.
  • Currently the ICU staff using the ENR has more vital information about the patient in order to help to make their decisions.
  • The data is grouped by the information provenance.

3.5 Automatic Data Processing and Transformation (R6)

  • After obtain all the essential data to the decision making process it was necessary introduce new features to the transformation process.
  • The uses of intelligent agents allowed automate the whole process.
  • Now the tasks associated to data preparation process are performed automatically and in real-time without human effort.
  • These changes increase the speed in getting new knowledge being they useful and available in the right time, i.e., in the moment of the decision is taken.

4 Pervasive Intelligent Decision Support System

  • A pervasive intelligent Decision Support System is recognized as a system that helps the decision making process and it is accessible anywhere and anytime.
  • In the health care arena there are two concepts related to PIDSS as is the pervasive healthcare and the pervasive computing [17].
  • Due their pervasive features, INTCare can produce three different types of knowledge.
  • This knowledge is available anywhere and anytime.

4.1 ICU Medical Scores

  • The ISS [3] is incorporated into the Electronic Nursing Record (ENR).
  • Nowadays, the ICU professionals can record and consult the scores in real-time.
  • This application allows for the automatic calculation in real-time of a set of scores: simplified acute physiology score (SAPS) II [18], SAPSIII [19], Sequential Organ Failure Assessment score (SOFA) [20], Glasgow Coma Score (GSC) [21], Therapeutic Intervention Scoring System (TISS-28) [22] and Modified Early Warning Score (MEWS) [23].
  • The ISS proposed processes automatically the scores and adapts the results according to the new values collected generating new knowledge.
  • The main gains in using this approach can be summarized as: The data acquisition, scores calculation and results are made in real-time; All values are considered - no missing values; .

4.2 ICU Critical Events

  • Critical Events (CE) are very important to the development of Data Mining (DM) models.
  • In order to develop DM models in a real setting it was necessary to define procedures to automatically compute CE for five variables: Urine Output , Blood Pressure, Heart Rate, Respiratory and Temperature [4].
  • The procedure calculates according some rules the number and elapsed time of an event.
  • In complement it is calculated the Accumulated Critical Events (ACE) [4].
  • The implementation of this new approach allows to the physicians have better understanding of the patient’s condition.

4.3 Ensemble Based Models

  • Data Mining (DM) is the centre of the PIDSS.
  • The objective of DM system is to predict the patient organ failure (cardiovascular, hepatic, coagulation, respiratory and renal) and patient outcome for the next hour.
  • For each measure the average of 10 runs was taken.
  • The use of ensemble helps to choose the best model in the cases where more than one model presents good results.
  • From the six targets, only three satisfy the quality measures defined: outcome, cardiovascular and coagulation.

5 Technology Acceptance Questionnaires

  • This questionnaire was elaborated by taking into account some scientific articles that report similar processes of technological implementation and are framed in the hospital environment and the first results obtained.
  • This scale was chosen because the use of short scales (scales that goes between three and four) can better constrain results into close type of answers such as a simple yes or no; and secondly, by applying a higher scale this could fall into a dispersion of results that lead the answers to inaccurate results.
  • It allows for giving two values for each side and at the same time finding a neutrality point [24].
  • The level of results collected from this questionnaire vary by the fact of the participant answer in a properly manner (with consciousness) or not.
  • Table 1 crosses the questions with the constructs: Perceived Usefulness (PU); Perceived Ease of Use (PEOU); Behavioural Intention (BI); Use Behaviour (UB).

6 Results

  • After collecting answers from 14 questionnaires sent by email (35% total number of nurses in ICU) an analysis of the results was performed.
  • First a processing was done to avoid invalid or inconsistent answers given by the participants.
  • Then was noticed that only one participant out of the 14 nurses answered the questionnaire in an inconsistent way for the proposed questions.
  • This situation leaded to only consider 13 surveys.
  • Table 2 presents the technology experience of the respondents.

6.1 Respondent Analysis

  • For a better perception of the answers made by each respondent, one analysis (average and mode) was carried out by the person questioned and TAM construct (fig 1 to 4).
  • This means that this person is quite pleased with some aspects of the system and not with others.
  • In general the evaluations are above 3 points.
  • At same time some correlations techniques were used to understand if the users are in accordance with the answers.
  • In a global way they are in relative accordance in some of the questions, being the overall Kendall’s tau: 0,158224.

6.2 Question Analysis

  • Instead of doing an analysis by respondent, an analysis was made for each one of the question and TAM 3 construct.
  • In the Y axis they are the possible answers of the questionnaire (1-5) and in the X axis they are the questions numbers.
  • On the other hand, the average of the answers for the questions related to these constructs is situated between 2 and 4 points.
  • This happens due to hospital connectivity problems in the network.
  • This problem represents the biggest barrier to the success of INTCare.

6.3 Global Analysis by Question

  • A global analysis was done in order to understand the best features, the average, the mode and the standard deviation for each one of constructs.
  • This table shows that the ICU staffs are satisfied with the system.
  • All the constructs present positive results being the best, the Perceived Ease of Use and the worst, the Use behaviour.
  • In the opposite side they are some functional characteristics.
  • Only one question has as mode 2 points.

Did you find this useful? Give us your feedback

Content maybe subject to copyright    Report

Á. Rocha et al. (Eds.): Advances in Information Systems and Technologies, AISC 206, pp. 279–292.
DOI: 10.1007/978-3-642-36981-0_27 © Springer-Verlag Berlin Heidelberg 2013
Pervasive Intelligent Decision Support System
Technology Acceptance in Intensive Care Units
Filipe Portela
1
, Jorge Aguiar
1
, Manuel Filipe Santos
1
,
Álvaro Silva
2
, and Fernado Rua
2
1
Algoritmi Center, University of Minho, Guimarães, Portugal
cfp@dsi.uminho.pt, jorge.phena@gmail.com, mfs@dsi.uminho.pt
2
Intensive Care Unit, Centro Hospitalar do Porto, Portugal
moreirasilva@clix.pt, fernandorua.sci@hgsa.min-saude.pt
Abstract. Intensive Care Units are considered a critical environment where the
decision needs to be carefully taken. The real-time recognition of the condition
of the patient is important to drive the decision process efficiently. In order to
help the decision process, a Pervasive Intelligent Decision Support System
(PIDSS) was developed. To provide a better comprehension of the acceptance
of the PIDSS it is very important to assess how the users accept the system at
level of usability and their importance in the Decision Making Process. This
assessment was made using the four constructs proposed by the Technology
Acceptance Methodology and a questionnaire-based approach guided by the
Delphi Methodology. The results obtained so far show that although the users
are satisfied with the offered information recognizing its importance, they
demand for a faster system.
Keywords: TAM, INTCare, Technology Acceptance, Intensive Care, Decision
Support System, Pervasive, Technology Assessment.
1 Introduction
Decision making in Intensive Medicine (IM) is a crucial process because deals with
critical condition patients. Nothing can fail and if something wrong happens the
patient can die. It is a specific area of Medicine and their knowledge it is practiced in
the Intensive Care Units (ICU). ICU is recognized as a critical environment where the
decision needs to be performed fast and with a high level of accuracy [1]. In the ICU
the patient care is always the main concern and tasks like is patient documentation are
relegated for a second plane [2]. The introduction of intelligent decision support
system (IDSS) in the support of decision process is claimed by many of the nurses
and physicians which work in ICU. This type of support can be addressed by a
pervasive system which operates automatically and in real-time. This system can give
to the ICU staff a better comprehension about the patient condition and at the same
time predict future situations. INTCare is framed in this type of system. It is a system
developed by this research team and which has as main goal the prediction of the
patient organ failure and patient outcome in real-time for the next 24 hours. With the

280 F. Portela et al.
development of the project, other types of sources were deepened and as result some
new knowledge were obtained. Currently, INTCare it is considered by the ICU staff a
very useful and complete platform, being composed by a set of pertinent information
for the Decision Making Process (DMP). To this work, a list of requirements was
defined based on the needs of ICU and the goal to make the system more suitable to
the environment. They may be summarized as:
R1. To implement an online data acquisition component;
R2. To make available the laboratory results in an open format;
R3. To allow an open access to prescriptions, interventions and therapeutics;
R4. To dematerialise the nursing records;
R5. To integrate the main systems used in ICU in a single platform;
R6. Develop an automatic system to process and transforming the data.
Taking advantage of the modifications introduced
(R1 to R6) it is possible to determine
automatically and in real-time, using online learning:
a) ICU medical scores [3];
b) ICU critical events [4];
c) Probability of occur an organ failure probability and patient die [5].
In order to assess the results achieved, the technology, the INTCare functionalities
and their importance to ICU, a questionnaire was developed. This questionnaire is
based in the Technology Acceptance Methodology (TAM) [6] and it is concerned to
the evaluation of four aspects: perceived usefulness (PU), perceived ease of use
(PEOU), behavioural intention (BI) and use behaviour (UB). Despite of the
questionnaire used be composed by a high number of questions, in this paper only are
presented the TAM results associated to the decision making process, i.e., the results
related to DMP.
This paper is divided in seven sections. The first and second sections introduce the
work and make an overview of the concepts and work previous performed. The third
section presents the improvements attained in the Intensive Care according to
INTCare features. Then the fourth section introduces the PIDSS at the level of results
achieved. The fifth and sixth sections are related to the TAM; the questionnaire
performed and results achieved. Finally, some remarks and future work are
considered.
2 Background
During 2009 when this project started the ICU information system was composed by
a set of information silos. The ICU professionals need to access to more than five
hospital applications to obtain important information and to make their decisions.
Now with the introduction of INTCare they have the most important information
available in the Electronic Nursing Record (ENR) and they can obtain new
knowledge automatically moments after the patient documentation. This situation
only was possible with the modification made by INTCare project and the
introduction of new knowledge into the ICU DMP.

Pervasive Intelligent Decision Support System 281
2.1 INTCare
INTCare [7, 8] is an IDSS to predict organ failure and patient outcome for the next 24
hours in real-time using online learning. This system is result of a research project.
The research and modifications done allowed to obtain new types of data in an
electronically format and in real-time [9, 10]. The new reality and the new
environment created [11] allow for obtaining new knowledge fundamental to the
decision process predicting patient condition, scoring the ICU measures and tracking
critical events automatically and in real-time. The data is obtained through a
streaming process and the knowledge attained is disseminated in situated devices.
2.2 Decision Making Process in Intensive Care Units
Making decisions in ICU is a complicated and danger process, because all tasks need
to be performed quickly and accurately [1]. The ICU professionals deal with patients
in serious life-risk. The use of technologies to support this type of process is welcome
[2] however, normally this type of systems aren't helping, i.e., don’t present the
accurate information in the right time and in the right place. These types of situations
complicate the decision process. At the same time, there is a problem associated to the
patient documentation because it is always relegated to a second place. In order to
overcome this situation some modifications were made in the ICU environment [11]
and in the DMP.
2.3 Technology Acceptance Methodology and Delphi Methodology
The evaluation of a technology application is crucial to comprehend its suitability in a
specific environment and also to measure the satisfaction level of its users. One of the
most used models in this area is the Technology Acceptance Methodology. “TAM is
adapted from the Theory of Reasoned Action (TRA) model which describes human
behaviours in a specific situation” [12]. The main purpose of TAM is to present an
approach to study the effects of external variables towards people’s internal beliefs,
attitudes, and intentions [6]. This model is also important because it gives an
understanding about the acceptance of the decision support by the ICU staff and how
can be useful in the course of their daily work. The goals of TAM can be achieved by
using methodologies based on questionnaires. As a support tool it is important to use
some aspects/characteristic of the Delphi method. The principles of the Delphi
method involves the use of questionnaires being one of its key features [13] the
preservation of anonymity of the participants. A questionnaire was prepared by a
coordination team, composed by professionals of ICU and Information System, and
sent to a set of participants (a group of experts from the ICU nurses team). The
questionnaire was prepared taking into account the constructs of TAM [14, 15]. The
correlations of the answers were evaluated through the Kendall's tau (τ) coefficient.
Kendall's tau is a measure of rank correlation. The values range from −1 (inversion) to
+1 (perfect agreement). A value of zero indicates the absence of association.

282 F. Portela et al.
2.4 Related Work – Results Obtained in the First Approach
In order to make a first assessment of the technology, a quick and short questionnaire
was produced [16]. The main goal was to have a first idea about the usefulness and
ease of use of the system in superficial way. This questionnaire was the starting point
of the second questionnaire (with tam) and it had a short scope. The questions were
divided into two groups: Functional characteristics (data registration, information
access and proactive performance) and Technical characteristics (efficient consulting,
response time, system security, usability, and interoperability). Finally, a last question
evaluate if the system suits the needs. The questionnaire was answered using a five-
scale metric: Does not meet / in complete disagreement (<20% of cases) (1) until fully
meet / fully agree (> 80%) (5) [16]. In terms of results only two questions were
answered with less than 4 points: one question about the registration system and other
question about the understanding of the system and their benefits.
Concluding, in the first phase of assessment the users revealed to be comfortable
with the system. These results motivated: i) to continue the development of the
project; and ii) perform a more extensive and deep questionnaire having the objective
to understand the technology acceptance by the ICU users.
3 Research Propose – Improvements Introduced in ICU
The improvements made are according to the INTCare requirements (R1 to R6)
defined in the introduction and can be summarized as:
3.1 Data Acquisition System (R1)
The first requirement was resolved with the implementation of a gateway. The
gateway is connected to the vital signs monitors, reads the patient information and
stores it on a database through the data acquisition agent. This is an autonomous
process and it is always in a continuous collecting process (streaming).
In this phase two problems appear: missing patient identification (PID) and the
acquisition of bad values. To overcome these problems two triggers were developed.
One trigger to verify on the Electronic Health Record (EHR) system the PID of the
patient admitted in bed where the values are provided and other trigger to validate the
values. This second process uses the range of values pre-defined by ICU. Both
the procedures are executed in the moment of the values are collected.
3.2 Laboratory (R2)
Regarding to the laboratory, an effort was made to have the lab results in an open
format, i.e., accessible electronically and able to be handled without restrictions. The
main objective was making the results available for ICU immediately after the patient
exams are concluded. This change gives the possibility to have the results in a
comparative format during the patient stay in ICU. Those exams have different types
and are executed by different services and at different hours [16].

Pervasive Intelligent Decision Support System 283
3.3 Open Access to Prescriptions (R3)
In this point the objective was deal with pharmacy and to study the possibility to
construct an easy access to patient prescriptions. These prescriptions were totally
controlled by pharmacy and whenever someone needed to consult the patient
therapeutic plan had to open a too slow platform. Now, the interaction between the
pharmaceutical system and ENR is made by an agent. Periodically, the ENR agent
sends a request to the pharmacy drugs system and then, the requested data is sent to a
database table [16].
3.4 Electronic Nursing Record (R4 and R5)
Electronic Nursing Record (ENR) is a platform that it was developed with the
objective to receive all medical data and put it available electronically and in real-time
to the physicians and nurses in an hourly mode. ENR can achieve two
requirements because being it electronic can dematerialize the processes and due the
interoperability mode can interoperate with all of others ICU data sources. Currently
the ICU staff using the ENR has more vital information about the patient in order to
help to make their decisions. ENR is a touch and web-based platform and it is
composed by different screens. The data is grouped by the information provenance.
3.5 Automatic Data Processing and Transformation (R6)
After obtain all the essential data to the decision making process it was necessary
introduce new features to the transformation process. The uses of intelligent agents
allowed automate the whole process. Now the tasks associated to data preparation
process are performed automatically and in real-time without human effort. These
changes increase the speed in getting new knowledge being they useful and available
in the right time, i.e., in the moment of the decision is taken.
4 Pervasive Intelligent Decision Support System
A pervasive intelligent Decision Support System (PIDSS) is recognized as a system
that helps the decision making process and it is accessible anywhere and anytime. In
the health care arena there are two concepts related to PIDSS as is the pervasive
healthcare and the pervasive computing [17]. Due their pervasive features, INTCare
can produce three different types of knowledge. This knowledge is available
anywhere and anytime.
4.1 ICU Medical Scores
The objective of PIDSS component is to behave as an Intelligent Scoring System
(ISS). The ISS [3] is incorporated into the Electronic Nursing Record (ENR).
Nowadays, the ICU professionals can record and consult the scores in real-time.

Citations
More filters
Journal ArticleDOI
TL;DR: A conceptual model of HIT acceptance in developing countries is proposed and some available HIT systems are reviewed in order to have an idea on their availability.

102 citations


Cites background from "Pervasive Intelligent Decision Supp..."

  • ...But then they want the systems to perform faster [46]....

    [...]

Journal ArticleDOI
TL;DR: An integrated model that predicts usage and satisfaction with Web-based information services (WIS) and merges the strengths from the fields of information systems and communications is created.

83 citations

Book ChapterDOI
02 Sep 2014
TL;DR: This paper is focused in presenting the system architecture and the knowledge obtained by each one of the decision modules: Patient Vital Signs, Critical Events, ICU Medical Scores and Ensemble Data Mining.
Abstract: In the Intensive Care Units (ICU) it is notorious the high number of data sources available. This situation brings more complexity to the way of how a professional makes a decision based on information provided by those data sources. Normally, the decisions are based on empirical knowledge and common sense. Often, they don’t make use of the information provided by the ICU data sources, due to the difficulty in understanding them. To overcome these constraints an integrated and pervasive system called INTCare has been deployed. This paper is focused in presenting the system architecture and the knowledge obtained by each one of the decision modules: Patient Vital Signs, Critical Events, ICU Medical Scores and Ensemble Data Mining. This system is able to make hourly predictions in terms of organ failure and outcome. High values of sensitivity where reached, e.g. 97.95% for the cardiovascular system, 99.77% for the outcome. In addition, the system is prepared for tracking patients’ critical events and for evaluating medical scores automatically and in real-time.

48 citations


Cites background from "Pervasive Intelligent Decision Supp..."

  • ...The questionnaires results [25] showed that the information generated (knowledge) and the system deployed are very important to the ICU professionals, being them suitable and framed in the decision making process....

    [...]

Book ChapterDOI
28 Aug 2013
TL;DR: An ensemble strategy was experimented in the context of INTCare system, a pervasive IDSS to automatically predict the organ failure and the outcome of the patients throughout next 24 hours, combining real-time data processing with ensemble approach in the intensive care unit of the Centro Hospitalar do Porto.
Abstract: Critical health care is one of the most difficult areas to make decisions. Every day new situations appear and doctors need to decide very quickly. Moreover, it is difficult to have an exact perception of the patient situation and a precise prediction on the future condition. The introduction of Intelligent Decision Support Systems (IDSS) in this area can help the doctors in the decision making process, giving them an important support based in new knowledge. Previous work has demonstrated that is possible to use data mining models to predict future situations of patients. Even so, two other problems arise: i) how fast; and ii) how accurate? To answer these questions, an ensemble strategy was experimented in the context of INTCare system, a pervasive IDSS to automatically predict the organ failure and the outcome of the patients throughout next 24 hours. This paper presents the results obtained combining real-time data processing with ensemble approach in the intensive care unit of the Centro Hospitalar do Porto, Porto, Portugal.

29 citations

Journal ArticleDOI
TL;DR: Using the data provided by INTCare system it was possible to induce models with a very good sensitivity (95%) in order to predict the probability of a patient be discharged in the next hour and contribute to improve the decision making process providing new knowledge in real time.
Abstract: The length of stay (LOS) is an important metric to manage hospital units since a correct prevision of the LOS can contribute to reduce costs and optimize resources. This metric become more fundamental in intensive care units (ICU) where controlling patient condition and predict clinical events is very difficult. A set of experiences was made using data mining techniques in order to predict something more ambitious than LOS. Using the data provided by INTCare system it was possible to induce models with a very good sensitivity (95%) in order to predict the probability of a patient be discharged in the next hour. The results achieved also allow for predicting the bed occupancy rate in ICU for the next hour. The work done represents a novelty in this area and contributes to improve the decision making process providing new knowledge in real time.

23 citations

References
More filters
Book
01 Jun 1975

36,032 citations


Additional excerpts

  • ...“TAM is adapted from the Theory of Reasoned Action (TRA) model which describes human behaviours in a specific situation” [12]....

    [...]

Journal ArticleDOI
TL;DR: In this paper, the authors developed and tested a theoretical extension of the TAM model that explains perceived usefulness and usage intentions in terms of social influence and cognitive instrumental processes, which was tested using longitudinal data collected regarding four different systems at four organizations (N = 156), two involving voluntary usage and two involving mandatory usage.
Abstract: The present research develops and tests a theoretical extension of the Technology Acceptance Model (TAM) that explains perceived usefulness and usage intentions in terms of social influence and cognitive instrumental processes. The extended model, referred to as TAM2, was tested using longitudinal data collected regarding four different systems at four organizations ( N = 156), two involving voluntary usage and two involving mandatory usage. Model constructs were measured at three points in time at each organization: preimplementation, one month postimplementation, and three months postimplementation. The extended model was strongly supported for all four organizations at all three points of measurement, accounting for 40%--60% of the variance in usefulness perceptions and 34%--52% of the variance in usage intentions. Both social influence processes (subjective norm, voluntariness, and image) and cognitive instrumental processes (job relevance, output quality, result demonstrability, and perceived ease of use) significantly influenced user acceptance. These findings advance theory and contribute to the foundation for future research aimed at improving our understanding of user adoption behavior.

16,513 citations

Journal ArticleDOI
22 Dec 1993-JAMA
TL;DR: The SAPS II, based on a large international sample of patients, provides an estimate of the risk of death without having to specify a primary diagnosis, and is a starting point for future evaluation of the efficiency of intensive care units.
Abstract: Objective. —To develop and validate a new Simplified Acute Physiology Score, the SAPS II, from a large sample of surgical and medical patients, and to provide a method to convert the score to a probability of hospital mortality. Design and Setting. —The SAPS II and the probability of hospital mortality were developed and validated using data from consecutive admissions to 137 adult medical and/or surgical intensive care units in 12 countries. Patients. —The 13 152 patients were randomly divided into developmental (65%) and validation (35%) samples. Patients younger than 18 years, burn patients, coronary care patients, and cardiac surgery patients were excluded. Outcome Measure. —Vital status at hospital discharge. Results. —The SAPS II includes only 17 variables: 12 physiology variables, age, type of admission (scheduled surgical, unscheduled surgical, or medical), and three underlying disease variables (acquired immunodeficiency syndrome, metastatic cancer, and hematologic malignancy). Goodness-of-fit tests indicated that the model performed well in the developmental sample and validated well in an independent sample of patients (P=.883 andP=.104 in the developmental and validation samples, respectively). The area under the receiver operating characteristic curve was 0.88 in the developmental sample and 0.86 in the validation sample. Conclusion. —The SAPS II, based on a large international sample of patients, provides an estimate of the risk of death without having to specify a primary diagnosis. This is a starting point for future evaluation of the efficiency of intensive care units. (JAMA. 1993;270:2957-2963)

5,836 citations

Journal ArticleDOI
TL;DR: This work draws from the vast body of research on the technology acceptance model (TAM) to develop a comprehensive nomological network of the determinants of individual level IT adoption and use and present a research agenda focused on potential pre- and postimplementation interventions that can enhance employees' adopted and use of IT.
Abstract: Prior research has provided valuable insights into how and why employees make a decision about the adoption and use of information technologies (ITs) in the workplace. From an organizational point of view, however, the more important issue is how managers make informed decisions about interventions that can lead to greater acceptance and effective utilization of IT. There is limited research in the IT implementation literature that deals with the role of interventions to aid such managerial decision making. Particularly, there is a need to understand how various interventions can influence the known determinants of IT adoption and use. To address this gap in the literature, we draw from the vast body of research on the technology acceptance model (TAM), particularly the work on the determinants of perceived usefulness and perceived ease of use, and: (i) develop a comprehensive nomological network (integrated model) of the determinants of individual level (IT) adoption and use; (ii) empirically test the proposed integrated model; and (iii) present a research agenda focused on potential pre- and postimplementation interventions that can enhance employees' adoption and use of IT. Our findings and research agenda have important implications for managerial decision making on IT implementation in organizations.

5,246 citations


"Pervasive Intelligent Decision Supp..." refers methods in this paper

  • ...For a better perception of the answers made by each respondent, one analysis (average and mode) was carried out by the person questioned and TAM construct (fig 1 to 4)....

    [...]

  • ...The fifth and sixth sections are related to the TAM; the questionnaire performed and results achieved....

    [...]

  • ...In this sub-section, instead of doing an analysis by respondent, an analysis was made for each one of the question and TAM 3 construct....

    [...]

  • ...The goals of TAM can be achieved by using methodologies based on questionnaires....

    [...]

  • ...For this study it was elaborated a questionnaire based on the four constructs of TAM 3....

    [...]

Journal ArticleDOI
TL;DR: In this paper, the authors evaluated the use of the Sequential Organ Failure Assessment (SOFA) score in assessing the incidence and severity of organ dysfunction in critically ill patients in ICU.
Abstract: ObjectiveTo evaluate the use of the Sequential Organ Failure Assessment (SOFA) score in assessing the incidence and severity of organ dysfunction in critically ill patients.DesignProspective, multicenter study.SettingForty intensive care units (ICUs) in 16 countries.PatientsPatients admitted to the

2,958 citations

Frequently Asked Questions (1)
Q1. What are the contributions in "Pervasive intelligent decision support system – technology acceptance in intensive care units" ?

This assessment was made using the four constructs proposed by the Technology Acceptance Methodology and a questionnaire-based approach guided by the Delphi Methodology.