Natural language processing (NLP) applications such as named entity recognition (NER) for low-resource corpora do not benefit from recent advances in the development of large language models (LLMs) where there is still a need for larger annotated datasets. This research article introduces a methodology for generating translated versions of annotated datasets through crosslingual annotation projection and is freely available on GitHub (link: https://github.com/JamilProg/crosslingual_bert_annotation_projection). Leveraging a language agnostic BERT-based approach, it is an efficient solution to increase low-resource corpora with few human efforts and by only using already available open data resources. Quantitative and qualitative evaluations are often lacking when it comes to evaluating the quality and effectiveness of semi-automatic data generation strategies. The evaluation of our crosslingual annotation projection approach showed both effectiveness and high accuracy in the resulting dataset. As a practical application of this methodology, we present the creation of French Annotated Resource with Semantic Information for Medical Entities Detection (FRASIMED), an annotated corpus comprising 2’051 synthetic clinical cases in French. The corpus is now available for researchers and practitioners to develop and refine French natural language processing (NLP) applications in the clinical field (https://zenodo.org/record/8355629), making it the largest open annotated corpus with linked medical concepts in French.

BACKGROUND: The large increase in the size of patent collections has led to the need of efficient search strategies. But the development of advanced text-mining applications dedicated to patents of the biomedical field remains rare, in particular to address the needs of the pharmaceutical & biotech industry, which intensively uses patent libraries for competitive intelligence and drug development. METHODS: We describe here the development of an advanced retrieval engine to search information in patent collections in the field of medicinal chemistry. We investigate and combine different strategies and evaluate their respective impact on the performance of the search engine applied to various search tasks, which covers the putatively most frequent search behaviours of intellectual property officers in medical chemistry: 1) a prior art search task; 2) a technical survey task; and 3) a variant of the technical survey task, sometimes called known-item search task, where a single patent is targeted. RESULTS: The optimal tuning of our engine resulted in a top-precision of 6.76% for the prior art search task, 23.28% for the technical survey task and 46.02% for the variant of the technical survey task. We observed that co-citation boosting was an appropriate strategy to improve prior art search tasks, while IPC classification of queries was improving retrieval effectiveness for technical survey tasks. Surprisingly, the use of the full body of the patent was always detrimental for search effectiveness. It was also observed that normalizing biomedical entities using curated dictionaries had simply no impact on the search tasks we evaluate. The search engine was finally implemented as a web-application within Novartis Pharma. The application is briefly described in the report. CONCLUSIONS: We have presented the development of a search engine dedicated to patent search, based on state of the art methods applied to patent corpora. We have shown that a proper tuning of the system to adapt to the various search tasks clearly increases the effectiveness of the system. We conclude that different search tasks demand different information retrieval engines' settings in order to yield optimal end-user retrieval.

Background: Primary Healthcare (PHC) reforms are presently addressing chronic-disease management. It is of importance to science and society to understand how eHealth services could be developed and used to address the challenges of health services integration like community pharmacies within PHC. Method: Focusing on the two initial steps of Design Science Research Methodology, a mixed methods approach was used with an online survey to collect data on use of Information Technologies (IT) in community pharmacy, followed by an exploratory observational time and business processes study, using the shadowing method. Results: The current state of IT usage in Portuguese community pharmacies is mainly focused on medicine dispensing. Pharmacists spend 50% of their time in patients' interactions, 38% on administrative tasks. Patterns of used time reflect a need to internal reorganization of pharmacies in order to enable eHealth pharmaceutical services provision.

OBJECTIVE: To compare users' speed, number of entry errors and satisfaction in using two current devices for electronic data collection in clinical research: handheld and laptop computers. DESIGN: The authors performed a randomized cross-over trial using 160 different paper-based questionnaires and representing altogether 45,440 variables. Four data coders were instructed to record, according to a random predefined and equally balanced sequence, the content of these questionnaires either on a laptop or on a handheld computer. Instructions on the kind of device to be used were provided to data-coders in individual sealed and opaque envelopes. Study conditions were controlled and the data entry process performed in a quiet environment. MEASUREMENTS: The authors compared the duration of the data recording process, the number of errors and users' satisfaction with the two devices. The authors divided errors into two separate categories, typing and missing data errors. The original paper-based questionnaire was used as a gold-standard. RESULTS: The overall duration of the recording process was significantly reduced (2.0 versus 3.3 min) when data were recorded on the laptop computer (p < 0.001). Data accuracy also improved. There were 5.8 typing errors per 1,000 entries with the laptop compared to 8.4 per 1,000 with the handheld computer (p < 0.001). The difference was even more important for missing data which decreased from 22.8 to 2.9 per 1,000 entries when a laptop was used (p < 0.001). Users found the laptop easier, faster and more satisfying to use than the handheld computer. CONCLUSIONS: Despite the increasing use of handheld computers for electronic data collection in clinical research, these devices should be used with caution. They double the duration of the data entry process and significantly increase the risk of typing errors and missing data. This may become a particularly crucial issue in studies where these devices are provided to patients or healthcare workers, unfamiliar with computer technologies, for self-reporting or research data collection processes.

OBJECTIVES: Quantitative evaluation of safety after the implementation of a computerized provider order entry (CPOE) system, stratification of residual risks to drive future developments. DESIGN: Comparative risk analysis of the drug prescription process before and after the implementation of CPOE system, according to the Failure Modes, Effects and Criticality Analysis (FMECA) method. MEASUREMENTS: The failure modes were defined and their criticality indices calculated on the basis of the likelihood of occurrence, potential severity for patients, and detection probability. Criticality indices of handwritten and electronic prescriptions were compared, the acceptability of residual risks was discussed. Further developments were proposed and their potential impact on the safety was estimated. RESULTS: The sum of criticality indices of 27 identified failure modes was 3813 for the handwritten prescription, 2930 (-23%) for CPOE system, and 1658 (-57%) with 14 enhancements. The major safety improvements were observed for errors due to ambiguous, incomplete or illegible orders (-245 points), wrong dose determination (-217) and interactions (-196). Implementation of targeted pop-ups to remind treatment adaptation (-189), vital signs (-140), and automatic edition of documents needed for the dispensation (-126) were the most promising proposed improvements. CONCLUSION: The impact of a CPOE system on patient safety strongly depends on the implemented functions and their ergonomics. The use of risk analysis helps to quantitatively evaluate the relationship between a system and patient safety and to build a strategy for continuous quality improvement, by selecting the most appropriate improvements to the system.

Advances in information technology (IT) have introduced new design approaches that support health care delivery and patient education. Such advances enable a fundamental redesign of health care processes based on the use and integration of electronic communication at all levels. Healthcare IT has the potential to empower patients and support a transition from a role in which the patient is the passive recipient of care services to an active role in which the patient is informed, has choices, and is involved in the decision-making process. New IT tools can enhance and supplement communication between health care professionals and patients. As a result, many informatics researchers and system designers who previously focused on designing IT applications that addressed the needs of health care providers and institutions are shifting toward patient-centered applications. Previous data models included episodic patient encounters as one type of health care transaction but did not capture the life course of the individual patient or consistently take an approach to ensure continuity of care. New technologies and advances in informatics research will enable support of patients as active consumers in a health care delivery system that is evolving from an institution-centric to a patient-centric model.1 Information technology tools can support interventions focusing on disease management and wellness. A disease management intervention is defined as “a set of coordinated health care interventions and communications for populations with conditions in which patient self-care efforts are significant.”2 Disease management programs aim to support patient-specific care plans and the provider-patient relationship via evidence-based guidelines. They focus on prevention of deterioration and/or complications. In the context of consumer empowerment, the paradigm of disease management can be extended to wellness management, where the focus is on the maintenance and improvement of the health status of any individual. Patient-centered applications are defined as systems that enable a partnership among practitioners, patients, and their families (when appropriate) to ensure that procedures and decisions respect patients' needs and preferences. Developers should solicit patients' input regarding the education and support that patients require to make decisions and participate in their own care.3 Such applications bridge clinical and nonclinical sectors and include both individual and population health-oriented tools. They encompass different communication channels such as web-based systems, portable monitoring tools, and mobile devices. The Knowledge in Motion Working Group of the American Medical Informatics Association coalesced from the merger of three previous working groups: Internet, Telehealth, and Mobile Computing. The working group produced this white paper to define the key principles and challenges for designers, policy makers, and evaluators of patient-centered technologies designed for disease prevention and management. The paper reviews current and emerging trends; highlights challenges related to design, evaluation, reimbursement, and usability; and reaches conclusions for next steps that will advance the domain. The Internet provides a platform for consumers to access health information. The number of web-based patient education sites that provide access to information related to patients' conditions has been increasing. The web enables patients communication between patients and health care providers4 or among patients and/or community members. Internet technologies have been utilized for disease management in many clinical areas, e.g., in asthma and diabetes management, where frequent monitoring can lead to early detection of potentially critical situations and timely intervention. In this context, a distinction needs to be made between applications that support pure self-care (without involvement of a health care provider) and applications that provide IT- enabled provider support of self care or disease co-management (vs. the traditional model of provider-administered and controlled care delivery). One example of IT-enabled self care is the home asthma telemonitoring5 system, which provides patients with continuous individualized help in the daily routine of asthma self-care. Extensive evaluations of the CHESS system (Comprehensive Health Enhancement Support System), an interactive computer system containing information, social support, and problem-solving tools for different patient groups (e.g., breast cancer patients, HIV patients), show the potential of web-based applications to increase disease knowledge, education, and social support.6 Most Internet-based health intervention studies have measured immediate, IT-focused nonclinical outcomes of Internet utilization for disease management, including features accessed by the patients,7 patient experience and satisfaction,8 or general health portal reliability.9 In general, it is difficult to characterize the effect of patient-centered applications compared with other interventions due to difficulty in teasing out the independent contribution of the technology. A systematic literature review focusing on the effects on health and social outcomes of computer-based peer-to-peer communities and electronic self support groups10 came to a similar conclusion, indicating that no robust evidence exists yet for the effects of such communities. Mobile health applications focus on serving the needs of the user by providing widespread access to relevant information and/or remote data capture, thus eliminating the need for the user to be physically linked to a network or restricted to a specific geographic location. The use of mobile IT devices such as personal digital assistants (PDAs) and cellular phones in health care is increasing. For health care practitioners, the use of mobile IT can bring additional resources to the point of care and can change the location of that point of care. Earlier research into using mobile IT devices, such as PDAs or cellular phones, emphasized the collection of data from the patient to facilitate clinician decision making.11 There are a few applications that provide real-time decision support to patients as well.12 Despite the movement toward patient-centric applications, most applications described in the literature follow the old model of decision-making in which the patient is a receiver of instructions rather than a participant in the management process.13 In these applications, it is assumed that patients will comply with recommended interventions and there is little follow-up to examine whether and how the patient did so.14 Patient-centered mobile health care applications have often targeted the areas of asthma,15 diabetes,16 and chronic obstructive pulmonary disease (COPD).17 Mobile health promotion or wellness applications have primarily addressed smoking cessation,18 nutritional intake,19 and vaccinations.20 In the popular media but not yet in scientific literature, there have been descriptions of how MP3 players21 and iPods22 might promote wellness activities and patient education. As noted by Moen and Brennan,23 consumers use complex strategies for managing their health information (storing information throughout multiple spaces in their household, recording with different media, and organizing data based on perceived urgency of the information), and technology designers should incorporate these strategies into their mobile IT designs for health management. Home telehealth applications (also known as telehomecare applications) utilize telecommunication and videoconferencing technologies to enable a health care provider at a clinical site to communicate with patients in their homes. Such an interaction via videoconferencing is called a virtual visit. In this context, the term actual visit is used to describe the traditional visit of the health care provider to the patient's home that includes a face-to-face interaction. In addition to the use of videoconferencing to enhance interactions, telehomecare applications utilize vital sign and other reporting devices that allow patients to become more involved and in many cases to oversee the monitoring process. Johnston et al.24 evaluated the use of remote video technology and monitoring devices in the home and determined that it achieved cost savings and improved access to home care support while producing no differences in clinical outcomes when compared with traditional care. A recent clinical trial at the Veterans Affairs Palo Alto Health Care System explored the use of a simple telephone-based device to ask patients a series of questions related to their health on a daily basis25 and demonstrated a significant decline in readmissions as a result of this simple asynchronous monitoring process.25 Health-related outcomes, including patient compliance, morbidity, and mortality, have been studied less often. Most such studies have had a maximum follow-up of one year and therefore are not able to evaluate long-term outcomes. The usability of mobile health systems is a key factor in the acceptance and diffusion of such technology in disease management and wellness promotion. In this context, four factors need to be addressed: user-friendliness, usability, user competence, and confidence.26 The first two factors deal mostly with the type of mobile technology (hardware matters such as size, noise, aesthetic presence, and obtrusiveness, and software matters such as user interfaces and device operation), whereas the last two factors relate more to users and their perceptions. The rate and impact of errors, at all steps, e.g., data acquisition, use of sensors, manual data entry, networking, and support services, must be analyzed. Furthermore, end users need to be confident in the system's performance. The latter involves challenges such as minimizing false positive alerts, protecting data security, maximizing diagnostic accuracy, etc. Special design considerations should apply when developing systems for the elderly or for other populations with functional limitations.27 Patient-centered applications often require the secure exchange of clinical data via electronic messages from different patient record systems to consolidate the disparate data required for disease management. To allow the correct interpretation of the exchanged information and adequate responses by the receiver, both a semantically sound and technically feasible set of standards are required. Goossen28 defined a framework of relevant standards for using clinical information in IT for five core areas: clinical, vocabulary, messages, work flow, and technical standards. Clinical standards, such as guidelines indicating the professional care that is appropriate for specific conditions, must be reflected in the domain knowledge included in programs for disease management and wellness. A second type of standard concerns terminologies in different formats and usually developed for specific purposes, such as clinical documentation, comparison of data, or statistical reporting. Ultimately, a broader goal of standardized vocabulary is the collection of more accurate and appropriate population and public health data to support decision making. The third type of standards focuses on the electronic exchange of information within and/or between health information systems; the classic example is Health Level Seven (HL7),29 which provides standards for the exchange, management, and integration of data that support clinical patient care and the management, delivery, and evaluation of health care services. Current HL7 v3 message models, e.g., for patient care, can represent the patient as author of health information, thus respecting self-care responsibilities. The fourth type of standard deals with work flow of health care processes. These standards describe the details of the care plan, stakeholders and timeline, required interactions, and transactions. For example, in home care, there is a detailed care plan that dictates the number of home care visits, their goals and who conducts them (registered nurse, nursing aid, social worker, etc.), and rules for specific processes (e.g., capturing of vital signs). Finally, technical standards need to be addressed. Numerous technical standards are available, including infrastructure, networking, and security issues. Particularly relevant for disease management applications are the Internet protocol (TCP/IP) for the infrastructure and Extensible Markup Language (XML) for the technical expression of messages. Investments in patient-centered IT-based applications are based in part on expectations of improving interorganizational networks, reducing costs, controlling resource allocation, and achieving a higher standard of quality of services promoting disease management and wellness.30 Innovators face major challenges in meeting increasing demands for health care services with limited resources. A major impediment for investments in IT applications, however, may be a lack of evidence of their economic impacts31 on end users, organizations, stakeholders, and society as a whole. Although pilot studies indicate clinical efficacy of patient-centered IT-based applications at the intraorganizational level,32 less is known about the cost effectiveness of such applications. Evaluation studies often are limited to hypothetical discussions, rather than actual analyses, of the potential value of patient-centered applications to consumers and methods for developing business models that transition from a payment-per-visit model (prospective payment principle) to a payment-per-episode-of-care model, or for quantifying the direct cost of the technology in use.33 Any economic evaluation will need to recognize that the system we are dealing with is not just an information system but an entire grid of interlocking actors and work processes34 whose boundaries must be determined for the sake of the evaluation. The majority of economic evaluations performed to date provide no conclusive answers about how to combine efficiency, effectiveness, and business process benefits derived from IT implementations involving patient-centered care.35 More recent intraorganizational studies have tried to evaluate savings due to productivity improvement and cost reductions. Other models of transformational benefits of clinical IT36 use frameworks such as return on investment and focus on the health care organization's perspective. However, many such models failed to represent IT-induced benefits apart from direct savings (such as patient empowerment, increased patient satisfaction) and do not include the efforts needed to enable the change, namely, overcoming user resistance, training and technical support, and achieving management support. Solid economic evaluations of patient-centered IT-based applications have to be performed as a comparative analysis of alternative courses of actions in terms of both their costs and their consequences. The main problem in evaluating patient-centered applications today often involves tracing and delimiting the consequences from an IT-based application. Benefits may occur only after a time lag, and sometimes they may arise as unintended consequences of the system.37 The public policy issues related to the use of IT to promote disease management and wellness are the same as those that arise for the use of IT in health care in general and involve several levels (state, federal) as well as numerous stakeholders. Specifically, these issues relate to access to care; the quality, safety, and efficacy of the delivered services; who will pay for that care and how much; and how to maintain the privacy and confidentiality of information. Introduction of IT adds a new set of cost drivers to these issues and raises questions about the benefits derived from these new technologies. Although the use of IT for patient-centered management has shown positive benefits for patients in selected experimental settings, the widespread use of IT for disease management might paradoxically reduce access to care via two mechanisms. The first of these reflects the extent to which the use of IT increases the cost of care. For example, a hypertensive patient's blood pressure can be monitored at home with a simple $50 sphygmomanometer. The same monitoring can also be performed by a home telehealth unit costing 10 to 100 times as much that automatically reminds the patient and transmits the results to a central location for evaluation. Although the latter technocentric approach may lead to higher quality of care and better patient outcomes, it also consumes considerably more financial resources. In a constrained spending environment, fewer patients will have access to this more advanced and potentially more beneficial care. The second way that access to care may be increasingly restricted results from infrastructure requirements becoming more of a technology may be restricted by the lack of access to at the point of care in the The has a number of and with for many of the in this In the of the for and has the that videoconferencing and related technologies can be used to provide appropriate care geographic but that reimbursement, from a to the site where the patient is will be to is for a face-to-face visit. There is only a for the costs of the technologies when used in a in the of home care, for virtual to the and remote monitoring at a set that no specific for the costs of the is from for services to for outcomes for and it is to that these technologies will have to to the same public policy from concerns about the and efficacy of health care devices. The and has the for the and efficacy of all such devices in the Any devices used for monitoring of disease conditions, such as are to IT is as an device may have a impact is the evolving on software that is used for purposes, but is not to a such as Medical systems, decision support systems, and disease management is a significant public policy that at the date of this major review at the as of the of who can provide such services, of services are and in many how much can be for those services. provides for the to ensure that health care in areas, the education system, and public have access to services including the One of the is to allow the of a Internet where users must pay an additional for Although this is perceived as a way to quality of services, the is that it will also increase the digital between who can better infrastructure and the applications that require them and those who that this might rather than help to health public policy to delivery of health care In many health care the site of is to be where the not the is In any in which for direct care is and IT is used to bridge geographic this distinction can become an In the it has been a significant to the diffusion of many IT-based One emerging to the may be the of of promoting of in one as in all The literature to date on the of patient-centered systems has focused on technical Although considerations related to of such systems are and more there have been fewer studies or have on patients' in knowledge of their own health (e.g., for breast cancer can lead to and/or can have a impact on quality of as well as between the patients and and between patients and researchers public health have guidelines for protecting the privacy of electronic clinical is a process that with to data when they are and for the of the protecting the data they with security, data must become increasingly about their collection and it is well known in the data security community that security security on a key of their from the are more than security to review and a by provides a patient with or other services from the of of the of the traditional is an for The of Healthcare with in and on health care information technology a of the of telehealth and mobile health More on details the in just this one of A developing of work in the mobile device issues of data but not yet of mobile technologies at to health care providers in exchange for the or to and use information white paper of the system and issues related to patient-centered disease management applications. clinical show and indicate that IT has potential to to improving patient However, more research is including experimental studies and economic studies from including design (e.g., to evidence of the effectiveness of patient-centered applications is required to the benefits of IT-enabled care can be the by of health care professionals must be addressed. work on standards and issues will facilitate health applications. Although these issues are they more critical for patient-centered which often require data and exchange among a set of and software applications and stakeholders The usability and of patient-centered applications and devices should be addressed early in the design into patient's and The of patient For researchers and system designers, the need exists for and that can patient or decision making. involves review and of many tools, for example that patient and patient in the context of a specific as well as the design of new tools. For the is to design patient education and that will take of the to a patient-centered A systematic of the issues of clinical data will help to ensure that patient data to Finally, the issues involved with the of mobile IT to health care are many and System designers should incorporate and privacy is to whether and how issues related to IT should be into the clinical for The and all of the Working Group for of this work and providing and

OBJECTIVE: To describe the configuration and use of the computerized provider order entry (CPOE) system used for inpatient and outpatient care at the authors' facility. DESIGN: Description of order configuration entities, use patterns, and configuration changes in a production CPOE system. MEASUREMENTS: The authors extracted and analyzed the content of order configuration entities (order dialogs, preconfigured [quick] orders, order sets, and order menus) and determined the number of orders entered in their production order entry system over the previous three years. The authors measured use of these order configuration entities over a six-month period. They repeated the extract two years later to measure changes in these entities. RESULTS: CPOE system configuration, conducted before and after first production use, consisted of preparing 667 order dialogs, 5,982 preconfigured (quick) orders, and 513 order sets organized in 703 order menus for particular contexts, such as admission for a particular diagnosis. Fifty percent of the order dialogs, 57% of the quick orders, and 13% of the order sets were used within a six-month period. Over the subsequent two years, the volume of order configuration entities increased by 26%. CONCLUSIONS: These order configuration steps were time-consuming, but the authors believe they were important to increase the ordering speed and acceptability of the order entry software. Lessons learned in the process of configuring the CPOE ordering system are given. Better understanding of ordering patterns may make order configuration more efficient because many of the order configuration entities that were created were not used by clinicians.

OBJECTIVE: To improve and simplify electronic order entry in an existing electronic patient record, the authors developed an alternative system for entering orders, which is based on a command- interface using robust and simple natural-language techniques. DESIGN: The authors conducted a randomized evaluation of the new entry pathway, measuring time to complete a standard set of orders, and users' satisfaction measured by questionnaire. A group of 16 physician volunteers from the staff of the Department of Veterans Affairs Puget Sound Health Care System-Seattle Division participated in the evaluation. RESULTS: Thirteen of the 16 physicians (81%) were able to enter medical orders more quickly using the natural-language-based entry system than the standard graphical user interface that uses menus and dialogs (mean time spared, 16.06 +/- 4.52 minutes; P=0.029). Compared with the graphical user interface, the command--based pathway was perceived as easier to learn (P<0.01), was considered easier to use and faster (P<0.01), and was rated better overall (P<0.05). CONCLUSION: Physicians found the command- interface easier to learn and faster to use than the usual menu-driven system. The major advantage of the system is that it combines an intuitive graphical user interface with the power and speed of a natural-language analyzer.

OBJECTIVE: The authors consider the problem of exact string pattern matching using algorithms that do not require any preprocessing. To choose the most appropriate algorithm, distinctive features of the medical language must be taken into account. The characteristics of medical language are emphasized in this regard, the best algorithm of those reviewed is proposed, and detailed evaluations of time complexity for processing medical texts are provided. DESIGN: The authors first illustrate and discuss the techniques of various string pattern-matching algorithms. Next, the source code and the behavior of representative exact string pattern-matching algorithms are presented in a comprehensive manner to promote their implementation. Detailed explanations of the use of various techniques to improve performance are given. MEASUREMENTS: Real-time measures of time complexity with English medical texts are presented. They lead to results distinct from those found in the computer science literature, which are typically computed with normally distributed texts. RESULTS: The Boyer-Moore-Horspool algorithm achieves the best overall results when used with medical texts. This algorithm usually performs at least twice as fast as the other algorithms tested. CONCLUSION: The time performance of exact string pattern matching can be greatly improved if an efficient algorithm is used. Considering the growing amount of text handled in the electronic patient record, it is worth implementing this efficient algorithm.