Large Volumes Of Patient Data Research Articles

[Translated article] Introducing artificial intelligence to hospital pharmacy departments

Artificial intelligence is a broad concept that includes the study of the ability of computers to perform tasks that would normally require the intervention of human intelligence. By exploiting large volumes of healthcare data, Artificial intelligence algorithms can identify patterns and predict outcomes, which can help healthcare organizations and their professionals make better decisions and achieve better results. Machine learning, deep learning, neural networks, or natural language processing are among the most important methods, allowing systems to learn and improve from data without the need for explicit programming. Artificial intelligence has been introduced in biomedicine, accelerating processes, improving accuracy and efficiency, and improving patient care.By using Artificial intelligence algorithms and machine learning, hospital pharmacists can analyze a large volume of patient data, including medical records, laboratory results, and medication profiles, aiding them in identifying potential drug–drug interactions, assessing the safety and efficacy of medicines, and making informed recommendations. Artificial intelligence integration will improve the quality of pharmaceutical care, optimize processes, promote research, deploy open innovation, and facilitate education. Hospital pharmacists who master Artificial intelligence will play a crucial role in this transformation.

Acercando la inteligencia artificial a los servicios de farmacia hospitalaria

Artificial intelligence (AI) is a broad concept that includes the study of the ability of computers to perform tasks that would normally require the intervention of human intelligence. By exploiting large volumes of healthcare data, artificial intelligence algorithms can identify patterns and predict outcomes, which can help healthcare organizations and their professionals make better decisions and achieve better results. Machine learning, deep learning, neural networks or natural language processing are among the most important methods, allowing systems to learn and improve from data without the need for explicit programming. AI has been introduced in biomedicine, accelerating processes, improving safety and efficiency, and improving patient care.By using AI algorithms and Machine Learning, hospital pharmacists can analyze a large volume of patient data, including medical records, laboratory results, and medication profiles, aiding them in identifying potential drug-drug interactions, assessing the safety and efficacy of medicines, and making informed recommendations. AI integration will improve the quality of pharmaceutical care, optimize processes, promote research, deploy open innovation, and facilitate education. Hospital pharmacists who master AI will play a crucial role in this transformation.

Reliable and fast automatic artifact rejection of Long-Term EEG recordings based on Isolation Forest.

Long-term electroencephalogram (Long-Term EEG) has the capacity to monitor over a long period, making it a valuable tool in medical institutions. However, due to the large volume of patient data, selecting clean data segments from raw Long-Term EEG for further analysis is an extremely time-consuming and labor-intensive task. Furthermore, the various actions of patients during recording make it difficult to use algorithms to denoise part of the EEG data, and thus lead to the rejection of these data. Therefore, tools for the quick rejection of heavily corrupted epochs in Long-Term EEG records are highly beneficial. In this paper, a new reliable and fast automatic artifact rejection method for Long-Term EEG based on Isolation Forest (IF) is proposed. Specifically, the IF algorithm is repetitively applied to detect outliers in the EEG data, and the boundary of inliers is promptly adjusted by using a statistical indicator to make the algorithm proceed in an iterative manner. The iteration is terminated when the distance metric between clean epochs and artifact-corrupted epochs remains unchanged. Six statistical indicators (i.e., min, max, median, mean, kurtosis, and skewness) are evaluated by setting them as centroid to adjust the boundary during iteration, and the proposed method is compared with several state-of-the-art methods on a retrospectively collected dataset. The experimental results indicate that utilizing the min value of data as the centroid yields the most optimal performance, and the proposed method is highly efficacious and reliable in the automatic artifact rejection of Long-Term EEG, as it significantly improves the overall data quality. Furthermore, the proposed method surpasses compared methods on most data segments with poor data quality, demonstrating its superior capacity to enhance the data quality of the heavily corrupted data. Besides, owing to the linear time complexity of IF, the proposed method is much faster than other methods, thus providing an advantage when dealing with extensive datasets.

Automated Workflow for Care Plan Assignment based on Patient Data

Effective handling of large volumes of patient data in the manual system is significantly hectic and timeconsuming. It also enhances the risk of error while developing tailored care plans for individual patients in a healthcare setting.

Understanding as a bottleneck for the data-driven approach to psychiatric science

The data-driven approach to psychiatric science leverages large volumes of patient data to construct machine learning models with the goal of optimizing clinical decision making. Advocates claim that this methodology is well-placed to deliver transformative improvements to psychiatric science. I argue that talk of a data-driven revolution in psychiatry is premature. Transformative improvements, cashed out in terms of better patient outcomes, cannot be achieved without addressing patient understanding. That is, how patients understand their own mental illnesses. I conceptualize understanding as the possession of adaptive mental constructs through which experience is mediated. I suggest that this notion of understanding serves as a bottleneck which any prospective approach to psychiatry must address to be efficacious. Subsequently I argue that, though the data-driven approach is undoubtedly powerful, it does not have a straightforward means of unblocking the bottleneck of understanding. I suggest that the data-driven approach must be supplemented with significant theoretical progress if it is to transform psychiatry.

IoT-Based Medical Image Monitoring System Using HL7 in a Hospital Database.

In recent years, the healthcare system, along with the technology that surrounds it, has become a sector in much need of development. It has already improved in a wide range of areas thanks to significant and continuous research into the practical implications of biomedical and telemedicine studies. To ensure the continuing technological improvement of hospitals, physicians now also must properly maintain and manage large volumes of patient data. Transferring large amounts of data such as images to IoT servers based on machine-to-machine communication is difficult and time consuming over MQTT and MLLP protocols, and since IoT brokers only handle a limited number of bytes of data, such protocols can only transfer patient information and other text data. It is more difficult to handle the monitoring of ultrasound, MRI, or CT image data via IoT. To address this problem, this study proposes a model in which the system displays images as well as patient data on an IoT dashboard. A Raspberry Pi processes HL7 messages received from medical devices like an ultrasound machine (ULSM) and extracts only the image data for transfer to an FTP server. The Raspberry Pi 3 (RSPI3) forwards the patient information along with a unique encrypted image data link from the FTP server to the IoT server. We have implemented an authentic and NS3-based simulation environment to monitor real-time ultrasound image data on the IoT server and have analyzed the system performance, which has been impressive. This method will enrich the telemedicine facilities both for patients and physicians by assisting with overall monitoring of data.

Artificial Intelligence in the American Healthcare Industry: Looking Forward to 2030

Artificial Intelligence in the American Healthcare Industry: Looking Forward to 2030

Blockchain and PUF-Based Lightweight Authentication Protocol for Wireless Medical Sensor Networks

Due to the emergence of heterogeneous Internet of Medical Things (IoMT) (e.g., wearable health devices, smartwatch monitoring, and automated insulin delivery systems), large volumes of patient data are dispatched to central cloud servers for disease analysis and diagnosis. Although this direct mode brings a lot of convenience for both patients and medical professionals (MPs), the open communication channel between them also incurs several security and privacy issues, such as man-in-the-middle attacks, eavesdropping attacks, and tracking attacks. Based on the unsolved challenges in wireless medical sensor networks (WMSNs), several researchers have proposed various authentication and key agreement (AKA) protocols for this type of healthcare system recently. However, most of these protocols do not perceive physical-layer security and over-centralized server problem in WMSN. In this article, to address these two open problems, we propose a lightweight and reliable authentication protocol for WMSN, which is composed of cutting-edge blockchain technology and physically unclonable functions (PUFs). In addition, a fuzzy extractor scheme is introduced to deal with biometric information. Subsequently, two security evaluation methods are used to prove the high reliability of our proposed scheme. Finally, performance evaluation experiments illustrate that the proposed mutual authentication protocol requires the least computation and communication cost among the compared schemes.

Healthcare Monitoring Through Fog Computing: A Survey

Healthcare is one of the prominent areas which requires a lot of improvements in terms of fast delivery of services to clients like patients, doctors, and hospitals. As the technology is growing rapidly, a number of healthcare devices and equipment are also increasing. These healthcare devices produce large volume of patient data on daily basis. The processing of the patients data is required in real time for critical cases where a quick decision can increase the lifespan of the patient. But conventional model of healthcare architecture using Cloud computing is unable to process huge health data in real time. There are a number of solutions provided by researchers to improve performance of Cloud healthcare computing, such as Edge, Fog, Mist, and Dew computing. In this survey paper, the term Fog computing, its advantages, and standard architecture are explained in detail. Various other computing terms of Internet of Things (IoT) are discussed and compared with Fog computing. The survey also presents conventional Cloud healthcare architecture, its issues, and various proposed healthcare architectures in Fog computing, and discusses new technologies that can improve healthcare system. The results shows that most of the works focus on security of hospital database and reducing the delay of providing services that are very minimal on energy consumption and mobility of patients.

Real-world data-driven risk prediction of hospitalization for heart failure in non-diabetic CKD

Abstract Background Heart failure (HF) is a major cause of cardiovascular morbidity and mortality. Despite recent advances in diagnosis and management of HF, the prognosis remains poor. HF and chronic kidney disease (CKD) are interlinked chronic health conditions. The availability of large volume of patient data and modern analytic techniques opens new opportunities for identification of individuals at elevated risk of HF. Purpose Develop risk prediction model for HF hospitalizations (HHF) in patients with non-diabetic CKD by applying data-driven computational intelligence techniques to a US population-based administrative claims database. Methods Individual-level data from the US Optum Clinformatics Data Mart for years 2008–2018 were analysed. To be eligible for inclusion, adult individuals were required to have non-diabetic CKD stage 3 or 4 (index event) and one year continuous insurance coverage prior to the index date (baseline period). Selection criteria and the main clinical outcome, hospitalisation for heart failure (HHF), were identified by using laboratory tests results and/or specific codes from common clinical coding systems. Risk prediction model for HHF was built on patient data in the baseline period composed to more than 6,000 variables. Computational intelligence method based on ant colony optimization was used to develop a time-to-first-event risk prediction model for HHF. Results Of the 64 million individuals in the database, 504,924 satisfied the selection criteria. Median age was 75 years, 60% were female. Among most common baseline comorbidities were hypertension (85%) and hyperlipidaemia (68%). Coronary artery disease, HF, atrial fibrillation and peripheral artery disease were recorded in 24%, 16%, 15% and 14% of individuals. Over a median follow-up of 744 days, 53,282 (11%) patients had recorded HHF, the corresponding incidence rate was 3.95 events/100 patient-years. The developed risk prediction model for HHF in non-diabetic CKD contained 20 risk factors. The five strongest risk factors were history of HF, intake of loop diuretics, severely increased albuminuria, atrial fibrillation or flutter and CKD 4 as observed “yes/no” in the baseline period. Fig. 1 depicts the final risk prediction model. To assess model performance, all patients in the cohort were stratified into five HHF risk groups. For each group, a Kaplan-Meier curve was built based on the HHF outcome data in the database. Fig. 2 shows clear separation between the curves, demonstrating high performance of the developed risk prediction model. Conclusion Despite many existing scores to predict HHF, their use is limited. Some scores rely on availability of rarely collected information, some are applicable for specific patient populations only. Risk prediction model for HHF in non-diabetic CKD is presented, which contains risk factors routinely collected by healthcare providers. Therefore, it might be applicable for HHF risk estimation in various settings. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): Bayer AG Forest plot of HHF risk prediction modelKaplan-Meier plot of risk strata

Real-world data-driven risk prediction of hospitalization for heart failure in non-diabetic CKD

Abstract Background Heart failure (HF) is a major cause of cardiovascular morbidity and mortality. Despite recent advances in diagnosis and management of HF, the prognosis remains poor. HF and chronic kidney disease (CKD) are interlinked chronic health conditions. The availability of large volume of patient data and modern analytic techniques opens new opportunities for identification of individuals at elevated risk of HF. Purpose Develop risk prediction model for HF hospitalizations (HHF) in patients with non-diabetic CKD by applying data-driven computational intelligence techniques to a US population-based administrative claims database. Methods Individual-level data from the US Optum Clinformatics Data Mart for years 2008–2018 were analysed. To be eligible for inclusion, adult individuals were required to have non-diabetic CKD stage 3 or 4 (index event) and one year continuous insurance coverage prior to the index date (baseline period). Selection criteria and the main clinical outcome, hospitalisation for heart failure (HHF), were identified by using laboratory tests results and/or specific codes from common clinical coding systems. Risk prediction model for HHF was built on patient data in the baseline period composed to more than 6,000 variables. Computational intelligence method based on ant colony optimization was used to develop a time-to-first-event risk prediction model for HHF. Results Of the 64 million individuals in the database, 504,924 satisfied the selection criteria. Median age was 75 years, 60% were female. Among most common baseline comorbidities were hypertension (85%) and hyperlipidaemia (68%). Coronary artery disease, HF, atrial fibrillation and peripheral artery disease were recorded in 24%, 16%, 15% and 14% of individuals. Over a median follow-up of 744 days, 53,282 (11%) patients had recorded HHF, the corresponding incidence rate was 3.95 events/100 patient-years. The developed risk prediction model for HHF in non-diabetic CKD contained 20 risk factors. The five strongest risk factors were history of HF, intake of loop diuretics, severely increased albuminuria, atrial fibrillation or flutter and CKD 4 as observed “yes/no” in the baseline period. Fig. 1 depicts the final risk prediction model. To assess model performance, all patients in the cohort were stratified into five HHF risk groups. For each group, a Kaplan-Meier curve was built based on the HHF outcome data in the database. Fig. 2 shows clear separation between the curves, demonstrating high performance of the developed risk prediction model. Conclusion Despite many existing scores to predict HHF, their use is limited. Some scores rely on availability of rarely collected information, some are applicable for specific patient populations only. Risk prediction model for HHF in non-diabetic CKD is presented, which contains risk factors routinely collected by healthcare providers. Therefore, it might be applicable for HHF risk estimation in various settings. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): Bayer AG Forest plot of HHF risk prediction modelKaplan-Meier plot of risk strata

Overview of Machine Learning Part 1: Fundamentals and Classic Approaches.

The extensive body of research and advances in machine learning (ML) and the availability of a large volume of patient data make ML a powerful tool for producing models with the potential for widespread deployment in clinical settings. This article provides an overview of the classic supervised and unsupervised ML methods as well as fundamental concepts required for understanding how to develop generalizable and high-performing ML applications. It also describes the important steps for developing a ML model and how decisions made in these steps affect model performance and ability to generalize.

Adaptive Mechanism Model for the Prevention of SLA Violation in the Context of COPD Patient Monitoring

In this paper, we introduce a new kind of Service Level Agreement(SLA) Template to better control dynamically quality of medical monitoring platform service. Our approach is based on Health care system and Health Information Technology (HIT) research area, specifically the field of telemonitoring system for patients who suffer from chronic obstructive pulmonary disease (COPD). According to WHO statistics, COPD is the third leading cause of death worldwide. To this end, several solutions or platforms exist today to monitor COPD. Most of these platforms manage large volume of patient data. This can bring about quality and lost data problems. To address these issues, control mechanisms must be proposed and designed to improve the quality of service (QoS) on these platforms. A platform with continuously monitored QoS can save patients’ lives and reduce data quality risk. In this article, we propose an ontology that uses SLAs data from COPD monitoring platforms with dynamic data from a patient context. We dynamically calculate the number of patient data incidents and the number of service request incidents from two dynamic contexts: SLA and the patient context. If the number of incidents is higher than what is expected in the SLA, then alerts are sent to the interface parties in real time. Finally, the contribution of this article is the proposed virtual SLA template to better control SLA violation and improve quality of medical monitoring platforms services.

Outcomes of carotid endarterectomy in the Vascular Quality Initiative based on patch type

ObjectiveThe Vascular Quality Initiative (VQI) is the largest registry of vascular surgical procedures and as such is capable of distinguishing small but important differences in outcomes. The goal of this study was to determine the outcomes of carotid endarterectomy (CEA) based on patch type, including bovine pericardium, autogenous vein, polytetrafluoroethylene (PTFE), and Dacron. MethodsAll primary CEAs performed with primary repair and patching (n = 70,987) within the VQI were retrospectively analyzed. Reoperative CEA and combined CEA and coronary artery bypass were excluded. Rates of any postoperative neurologic event, return to the operating room (bleeding, neurologic event, or wound complication), and restenosis (>50% and >80%) at 1-year follow-up were primary outcomes. Rates were compared by patch type using χ2 and Bonferroni analysis. Multivariate hierarchical logistic regression models were used to predict end points of postoperative neurologic event, return to the operating room, and 1-year restenosis. ResultsDuring the period of study, 2003 to 2017, there were 70,987 CEAs entered into the VQI registry. Bovine pericardium was the patch material with the highest frequency of use (n = 51,480), followed by Dacron (n = 12,356), vein (n = 1460), and PTFE (n = 1638). Bovine pericardium, vein, and Dacron had lower rates of postoperative neurologic events compared with PTFE or primary repair. Bovine pericardium had the lowest rate of restenosis at 1 year. By multivariate analysis, bovine pericardium (odds ratio [OR], 0.70; 95% confidence interval [CI], 0.56-0.89) and protamine use (OR, 0.74; 95% CI, 0.60-0.91) were associated with a lower incidence of return to the operating room. The use of Dacron, vein, and PTFE patches was not significantly different from the reference of primary closure. Multivariate analysis of postoperative neurologic events revealed that bovine pericardium (OR, 0.59; CI, 0.48-0.72) and Dacron (OR, 0.56; CI, 0.43-0.72) were associated with lower incidence of stroke or transient ischemic attack, whereas vein and PTFE were no different from primary closure. Bovine pericardium (OR, 0.57; CI, 0.44-0.75), Dacron (OR, 0.70; CI, 0.50-0.98), vein (OR, 0.72; CI, 0.53-0.98), and never smoking (OR, 0.87; CI, 0.78-0.96) were associated with a lower incidence of restenosis at 1 year by multivariate analysis. ConclusionsBovine pericardium has superior outcomes both postoperatively and at 1 year compared with other patch materials. The large volume of patient data contained in the VQI makes it possible to compare outcomes that have small but meaningful differences.

Systematic review of the use of big data to improve surgery in low- and middle-income countries.

BackgroundTechnological advances have led to the generation of large amounts of data, both in surgical research and practice. Despite this, it is unclear how much originates in low‐ and middle‐income countries (LMICs) and what barriers exist to the use of such data in improving surgical care. The aim of this review was to capture the extent and impact of programmes that use large volumes of patient data on surgical care in LMICs.MethodsA PRISMA‐compliant systematic literature review of PubMed, Embase and Google Scholar was performed in August 2018. Prospective studies collecting large volumes of patient‐level data within LMIC settings were included and evaluated qualitatively.ResultsA total of 68 studies were included from 71 LMICs, involving 708 032 patients. The number of patients in included studies varied widely (from 335 to 428 346), with 25 reporting data on 3000 or more LMIC patients. Patient inclusion in large‐data studies in LMICs has increased dramatically since 2015. Studies predominantly involved Brazil, China, India and Thailand, with low patient numbers from Africa and Latin America. Outcomes after surgery were commonly the focus (33 studies); very few large studies looked at access to surgical care or patient expenditure. The use of large data sets specifically to improve surgical outcomes in LMICs is currently limited.ConclusionLarge volumes of data are becoming more common and provide a strong foundation for continuing investigation. Future studies should address questions more specific to surgery.

A Qualitative Evidence Synthesis of Adverse Event Detection Methodologies.

The detection of adverse events (AE) and their relationship to data quality issues through processes or medical error is not currently understood. In order to study the relationship between adverse events and data quality it is necessary to capture as many AE as possible and computational methods will be necessary to handle the large volumes of patient data. The need for adverse event detection methodology has been repeatedly noted but standard AE detection methods are not in place in the US. At present, there are several widely enforced strategies for AE detection but none are both highly successful and computational. In order to maximize AE detection, we have conducted a qualitative evidence synthesis of these approaches. The categorization of the circumstances of the event as well as the resulting patient safety problem and the method of detection provide a means to synthesize AE detection solutions. This has resulted in a set of 130 AE detection algorithms in 9 circumstances categories and 41 patient safety problem categories. This work begins the effort of consolidation of current safety metrics in an effort to produce a common set of safety measures.

Therapeutic oncolytic viruses: clinical advances and future directions

The present review will highlight recent advances in the clinical application of oncolytic viral therapy. Until recently, oncolytic viral researchers saw the immune system as an enemy that would clear the virus from the bloodstream. However, researchers now understand that sustained responses are seen in those patients with more robust antitumor immune responses. Much of the current focus in oncolytic viral research is trained on manipulation of the immune system to affect cancer cell killing in the tumor microenvironment and to facilitate durable systemic antitumor immunity. Many investigators have demonstrated synergistic effects of checkpoint inhibition and other immune therapies with viral administration. At the same time, insertion of various markers enables noninvasive deep tissue imaging. Finally, following regulatory approval in the United States and Europe, unbridled clinical use of T-VEC for patients with metastatic melanoma is also generating large volumes of patient data that will help elucidate strengths and weaknesses of oncolytic viral therapy. Perhaps the most telling sign of the field's future is a seismic shift in clinical trials with more investigators combining virus and immunotherapies. This article reviews the current state of therapeutic oncolytic viruses in clinical use, and explores future directions of the field.

Use of Diagnosis-related Group-Based Days of Therapy to Evaluate Fluoroquinolone Use Optimization Across a Large Healthcare System

BackgroundOptimal use of fluoroquinolones (FQ) is a common antimicrobial stewardship program (ASP) target based on well-cited risk for Clostridium difficile colitis and has gained national attention in the setting of recent FDA warnings about serious side effects. Identifying appropriate metrics for benchmarking poses a significant challenge. Diagnosis-related group (DRG) can be leveraged to focus large volumes of patient data to derive DRG-based days of therapy (DOT). Novant Health identified an opportunity to improve FQ use among patients with COPD and pneumonia (PNA) across the health system and created a FQ use optimization initiative based on inter-facility data that would otherwise not have been possible using the standard DOT per 1000 patient-days (PD) metric.MethodsA staged approach to optimizing FQ use was developed through a multidisciplinary, system-level ASP, and system-specific benchmarks for FQ use among patients with PNA and COPD DRGs were established. 10 facilities ranging in size from 60 to 900 beds were included in the intervention. We evaluated FQ use at the system and facility level using both standard (DOT/1000 PD) and novel metrics (DRG-specific DOT/1000 PD and percentage of antibiotic use attributed to FQ within each DRG). In addition to providing feedback on performance relative to other facilities, the intervention also included provider education and targeted infectious diseases pharmacist review and feedback.ResultsPercentage of FQ use among patients with PNA DRGs decreased from 20% to 9%, while use in COPD DRGs decreased from 38% to 12% over 15 months (55% and 68% reductions in FQ use, respectively). System-wide FQ utilization decreased by 38% over the same 15 month time period, from a peak of 114 DOT/1000 PD to 71 DOT/1000 PD.ConclusionDecreases in overall FQ utilization were influenced by DRG-specific benchmarking and inter-facility comparisons. Traditional DOT/1000 PD metrics are plagued with variance in patient characteristics (e.g., disease state variations, severity of illness). While DRG-based metrics have inherent limitations, they can provide specific data on antibiotic use patterns to support health-system specific and evidence-based benchmarking and inter-facility comparisons.Disclosures All authors: No reported disclosures.

VisualDecisionLinc: A visual analytics approach for comparative effectiveness-based clinical decision support in psychiatry

Comparative Effectiveness Research (CER) is designed to provide research evidence on the effectiveness and risks of different therapeutic options on the basis of data compiled from subpopulations of patients with similar medical conditions. Electronic Health Record (EHR) system contain large volumes of patient data that could be used for CER, but the data contained in EHR system are typically accessible only in formats that are not conducive to rapid synthesis and interpretation of therapeutic outcomes. In the time-pressured clinical setting, clinicians faced with large amounts of patient data in formats that are not readily interpretable often feel ‘information overload’. Decision support tools that enable rapid access at the point of care to aggregate data on the most effective therapeutic outcomes derived from CER would greatly aid the clinical decision-making process and individualize patient care.In this manuscript, we highlight the role that visual analytics can play in CER-based clinical decision support. We developed a ‘VisualDecisionLinc’ (VDL) tool prototype that uses visual analytics to provide summarized CER-derived data views to facilitate rapid interpretation of large amounts of data. We highlight the flexibility that visual analytics offers to gain an overview of therapeutic options and outcomes and if needed, to instantly customize the evidence to the needs of the patient or clinician. The VDL tool uses visual analytics to help the clinician evaluate and understand the effectiveness and risk of different therapeutic options for different subpopulations of patients.

Monitoring service utilization of persons with mental disorders – a case for mapping pathways of care

Routinely collected and reported indicators for health service utilization have traditionally been event/episode related and hospital centered. This is also the case for service utilization by persons with mental disorders, for whom national and international databases usually report rates of hospital discharges, mean length of stay for hospital episode and the like. Such event/episode-related indicators are of limited use for planning and improving services for persons with mental disorders. It is argued that new reporting systems are needed that allow the monitoring of the pathways of persons with mental disorders through the service system. It is shown how--owing to recent developments in techniques of 'pseudonymization' and the ever-increasing computer power for dealing with large volumes of patient data--such a system can be established and how it can contribute to analyzing empirically such mental health-care issues as 'heavy utilizers', 'revolving door psychiatry', 'continuity of care', 'de-institutionalization' and the like. Results of a record linkage study for the total population of a federal state of Austria monitoring both psychiatric and non-psychiatric health service utilization are reported. Some unexpected findings include the high utilization of non-psychiatric services by patients discharged from a psychiatric hospital bed, results which could not have been found by psychiatric case registers which usually only monitor utilization of psychiatric services.