Automatic Priority Research Articles

Influence of pre-processing methods on the automatic priority prediction of native-language end-users’ maintenance requests through machine learning methods

Feedback and requests by occupants are relevant sources of data to improve building management, and building maintenance. Indeed, most predictable faults can be directly identified by occupants and communicated to facility managers through communications written in the end-users’ native language. In this sense, natural language processing methods can support the request identification and attribution process if they are robust enough to extract useful information from these unstructured textual sources. Machine learning (ML) can support assessing and managing these data, especially in the case of many simultaneous communications. In this field, the application of pre-processing and ML methods to English-written databases has been widely provided, while efforts in other native languages are still limited, impacting the real applicability. Moreover, the performance of combinations of methods for pre-processing, ML and classification classes attribution, has been limitedly investigated while comparing different languages. To fill this gap, this work hence explores the performance of automatic priority assignment of maintenance end-users’ requests depending on the combined influence of: (a) different natural language pre-processing methods, (b) several supervised ML algorithms, (c) two priority classification rules (2-class versus 4-class), (d) the database language (i.e. the original database written in Italian, the native end-users’ language; a translated database version in English, as standard reference). Analyses are performed on a database of about 12000 maintenance requests written in Italian concerning a stock of 23 buildings open to the public. A random sample of the sentences is supervised and labelled by 20 expert annotators following the best-worst method to attribute a priority score. Labelled sentences are then pre-processed using four different approaches to progressively reduce the number of unique words (potential predictors). Five different consolidated ML methods are applied, and comparisons involve accuracy, precision, recall and F1-score for each combination of pre-processing action, ML method and the number of priority classes. Results show that, within each ML algorithm, different pre-processing methods limitedly impact the final accuracy and average F1-score. In both Italian and English conditions, the best performance is obtained by NN, LR, SVM methods, while NB generally fails, and by considering the 2-class priority classification scale. In this sense, results confirm that facility managers can be effectively supported by ML methods for preliminary priority assessments in building maintenance processes, even when the requests database is written in end-users’ native language.

Towards a resilient health status assessment employing intelligence in cyber physical systems

Resilience is defined as the capacity of a system to cope with a hazardous event or disturbance, responding or reorganizing in ways that maintain its essential function, identity, and structure, while also maintaining the capacity for adaptation, learning and transformation. A resilient health system is one that is capable to anticipate, respond to, cope with, recover from and adapt to system-related shocks and stress, so as to bring sustained improvements in population health, despite the unstable circumstances. Nowadays, the emergency department (ED) of hospitals faces growing demands, rising acuteness and longer waiting times. An efficient, accurate and resilient triage system to improve the operation of the ED becomes crucial. In this work, a resilient system for automatic priority, sorting and monitoring of medical events -triage system- is developed, so that the patients in the ED are treated according to the severity of their condition and not by the order of attendance utilizing a Fuzzy Inference System (FIS) that aggregates, processes patients’ vital signs as well as determines their Health Status (HS), according to which the ED staff performs the appropriate classification.

A few of my favorite things: circumscribed interests in autism are not accompanied by increased attentional salience on a personalized selective attention task

BackgroundAutistic individuals commonly show circumscribed or “special” interests: areas of obsessive interest in a specific category. The present study investigated what impact these interests have on attention, an aspect of autistic cognition often reported as altered. In neurotypical individuals, interest and expertise have been shown to result in an automatic attentional priority for related items. Here, we examine whether this change in salience is also seen in autism.MethodsAdolescents and young adults with and without autism performed a personalized selective attention task assessing the level of attentional priority afforded to images related to the participant’s specific interests. In addition, participants performed a similar task with generic images in order to isolate any effects of interest and expertise. Crucially, all autistic and non-autistic individuals recruited for this study held a strong passion or interest. As such, any differences in attention could not be solely attributed to differing prevalence of interests in the two groups. In both tasks, participants were asked to perform a central target-detection task while ignoring irrelevant distractors (related or unrelated to their interests). The level of distractor interference under various task conditions was taken as an indication of attentional priority.ResultsNeurotypical individuals showed the predicted attentional priority for the circumscribed interest images but not generic items, reflecting the impact of their interest and expertise. Contrary to predictions, autistic individuals did not show this priority: processing the interest-related stimuli only when task demands were low. Attention to images unrelated to circumscribed interests was equivalent in the two groups.ConclusionsThese results suggest that despite autistic individuals holding an intense interest in a particular class of stimuli, there may be a reduced impact of this prior experience and expertise on attentional processing. The implications of this absence of automatic priority are discussed in terms of the behaviors associated with the condition.

Model for end-stage liver disease (MELD) exception guidelines: Results and recommendations from the MELD exception study group and conference (MESSAGE) for the approval of patients who need liver transplantation with diseases not considered by the standard MELD formula

Richard B. Freeman Jr., Robert G. Gish, Ann Harper, Gary L. Davis, John Vierling, Leslie Lieblein, Goran Klintmalm, Jamie Blazek, Robert Hunter, and Jeffrey Punch Division of Transplantation, Department of Surgery, Tufts–New England Medical Center, Boston, MA; Departments of Medicine and Transplantation and the Division of Hepatology and Complex GI, Physicians Foundation, California Pacific Medical Center, San Francisco, CA; United Network for Organ Sharing, Richmond, VA; Baylor Regional Transplant Institute, Baylor University Medical Center, Dallas, TX; Department of Medicine, David Geffen School of Medicine at UCLA, University of California Los Angeles, Los Angeles, CA; Ochsner Multi-Organ Transplant Center, New Orleans, LA; and Department of Surgery, University of Michigan, Ann Arbor, MI

Model for end-stage liver disease (MELD) exception for polycystic liver disease

Polycystic liver disease (PLD) is commonly associated with polycystic kidney disease, but is unaccompanied by renal cysts in 10% of cases. Symptomatic PLD is mainly limited to adults and rarely, if ever, presents in childhood. There is currently no effective medical therapy for PLD. Most patients who have PLD require no medical or surgical intervention. Patients with PLD rarely, if ever, experience biochemical hepatic deterioration, and classic symptoms of hepatic failure such as ascites, variceal hemorrhage, or encephalopathy are unusual.1-3 Although there is a typical lowering of the quality of life in these patients, to date, quality of life (although not well studied) has not been associated with decreased survival. Serious, life-threatening complications related to multiple hepatic cysts may occur, including cyst infection, hepatic vein outflow obstruction, portal hypertension, refractory ascites after cyst fenestration, cyst carcinoma, cholangiocarcinoma, and most importantly, pain and/or chronic wasting with malnutrition.2-4 Symptomatic PLD only occurs in patients with massive hepatic cystic disease in which the total cyst:parenchyma ratio is >1.5 Patients with PLD on hemodialysis are at greatest risk of life-threatening complications due to hepatic cysts complicated by infection, hemorrhage, and carcinoma. In one center, 10% of the mortality in patients with PLD on hemodialysis was attributed to these complications. However, this observation has not been confirmed by other centers. Nontransplant interventions that can relieve symptoms of massive hepatic cystic disease include percutaneous cyst puncture and sclerotherapy, laparoscopic cyst decompression, open laparotomy with fenestration, and liver resection.3, 6-10 These interventions can provide temporary or prolonged relief of symptoms but may be associated with significant morbidity and even mortality. Open surgical decompression is associated with a very low mortality rate but is associated with substantial morbidity. Laparoscopic decompression reduces hospital length of stay but is also associated significant morbidity.6 Liver resection is indicated only in highly selected patients and is associated with the potential for frequent morbidity and significant mortality. Liver transplantation (LT), the ultimate treatment for PLD, eliminates the disease and its complications and provides long-lasting relief of symptoms.11-14 Approximately 40% of those undergoing LT will require simultaneous kidney transplantation. Five-year survival after LT or liver-kidney transplantation is approximately 70 to 75%, and much of the mortality is in the first year. LT with or without kidney transplantation should be avoided in severely malnourished or debilitated patients. Patients with PLD may be candidates for living-donor LT. Patients with PLD generally have preserved liver function and normal Model for End-Stage Liver Disease (MELD) scores if they do not have renal involvement. Satisfy criteria for massive PLD (total cyst:parenchyma ratio >1) and have a complication of the PLD that is likely to resolve after LT. Are not candidates for, or have disease that has failed to respond to, nontransplant interventions for relief of symptoms; malnutrition may be considered a primary contraindication to nontransplant surgery. Have clinically significant manifestations of liver disease that can be attributed to massive PLD, which may include cachexia, ascites, portal hypertension (variceal bleeding), hepatic venous outflow obstruction, biliary obstruction, cholestasis, or recurrent cyst infection. Have severe malnutrition (assessment made on the basis of hypoalbuminemia or decreased lean body mass). Have serum albumin <2.2 mg/dL. Have lean body mass reflected by decreased midarm circumference, measured in the nondominant arm midway between the acromion and the olecranon process: <23.1 cm in female patients and <23.8 cm in male patients. PLD, polycystic liver disease; LT, liver transplantation; MELD, Model for End-Stage Liver Disease. There are insufficient data to justify automatic priority for patients with PLD. Patients without renal insufficiency may receive a MELD score of 15. The score may be increased by an additional 3 points every 3 months upon reapplication with submission of current clinical data. Patients with renal insufficiency (defined as glomerular filtration rate or creatinine clearance < 30 mL/min) may receive a MELD score of 20. The score may be increased by an additional 3 points every 3 months upon reapplication. Clinical data that need to prospectively collected and be submitted to the Regional Review Boards include documentation of recurrent cyst infection by culture reports, and weight of the explant liver and the ratio of the liver weight to patient height to determine whether these parameters correlate with patient outcome. In addition, the Regional Review Boards may require vascular studies (full reports with computed tomographic scans, magnetic resonance imaging, or angiography) to document cases of vascular occlusion.

The Antarctic Treaty System: Environmental protection, conservation, and the question of competing use

The Antarctic Treaty System consists of the Treaty itself, over 130 recommendations made under it, the Agreed Measures for the Conservation of Antarctic Fauna and Flora, the Convention for the Conservation of Antarctic Seals, and the Convention for the Conservation of Antarctic Marine Living Resources. Consultations have been held among parties to the Antarctic Treaty to elaborate an Antarctic minerals regime. It has become clear that how to deal with issues of competing use has begun to emerge as an important political question. In such a context the development of an Antarctic conservation strategy is a potentially helpful step. Competition of use, when it occurs, will be localised and different in different areas. In only tiny parts will it be severe, but these parts may be the biologically richest coastal areas. Various activities and their possible interactions are considered. It is concluded that any arrangement of Antarctic activities which given an automatic priority of one over others is wrong. Similarly, no activity should be subservient to all others. An Antarctic conservation strategy needs to be developed and in its operation the concept of adaptive environmental assessment and management needs to be applied. Within the Antarctic Treaty System there are moves towards assessment. What is needed now is a framework within which such concepts can operate; that is, a conservation and environmental strategy.

Why Big Nations Lose Small Wars: The Politics of Asymmetric Conflict

The Vietnam and Algerian wars have demonstrated that the overwhelming conventional military superiority of major powers is no guarantee against their defeat in wars against small nations. For external powers such wars are necessarily “limited,” which constrains escalation above certain levels. With no direct survival interest at stake, fighting the war does not take automatic priority over the pursuit of other social, political, and economic objectives. Prosecuting the war consumes resources—economic, human, and political—which are thus not available for the pursuit of these other objectives. In the absence of a quick victory this creates the potential for those political divisions which historically have shifted the balance of forces in the metropolis in favor of withdrawal. For the insurgents, the fact of invasion and occupation generates cohesion, minimizes constraints on mobilization, and maximizes the willingness to incur costs. Precisely the opposite effects tend to characterize the war effort of the external power. A conceptual framework for the analysis of the evolution and outcome of such conflicts is presented and its applications and limitations discussed.

THE NEED FOR CARE IN CHOOSING LECTOTYPES

Botanists have generally appreciated the complexity resulting from the application of the type method to the older taxonomic literature. This is recognized in the International Code (1972) by the inclusion of a special section Guide for the determination of types where an attempt was made to anticipate the problems arising in connection with the selection of a type of a given taxon when none was designated in the original publication. Even recent collectors and authors present unexpected complications for the person wishing to be accurate and precise in the selection of a lectotype (Ewan, 1969). My present concern is that with the best of intentions and with the code guide to follow, mistakes in the choosing of lectotypes are still being made. My remarks are limited to species or infraspecific taxa where specimens are the primary basis for typification. The philosophy behind the intentions of the Code is relatively simple. It is that subsequent interpretations of the application of a name to a given taxon be as nearly the same as that of the original author as possible and at the same time diminish the chances for differing interpretations as nearly to zero as possible. When an original author designated a holotype and indicated its place of deposit, there is no problem. The first slippage might occur if the author failed to specify where the holotype is conserved. Unfortunately, it has sometimes been the practice of authors to merely cite a type collection without indicating precisely which particular sheet is the holotype. In such a case, and even though the code guide does not so state, the holotype is the particular specimen retained by the original author at his place of work or in his private herbarium, and the other specimens of the type collection are isotypes. It is incumbent upon subsequent authors to recognize such an automatic priority, otherwise an element of uncertainty can easily arise. The actual designation of the holotype on the sheet of the specimen should be a part of the curatorial activities of the institution where the specimen is located. If a single collection is cited by a publishing author and even though he did not specifically state that it is the type collection, it should be treated as if he had so stated. In this case, there is no need for a subsequent author to choose a lectotype. The existence of a holotype in the institution where the original author worked is assumed until proven otherwise. Such an emphasis is in accord with Article 7 of the Code. A case in point is that of the type of Montia howellii S. Watson. In his original publication, Watson (1883) cited only one collection made by Joseph and Thomas Howell on Island in the Willamette River, Oregon. Recently, Nilsson (1967) in making M. howellii the type species of his new genus Maxia, designated a specimen in the Gray Herbarium collected on Island in 1884 by J. Howell as the lectotype. Later (1971), he properly rejected this specimen as the lectotype. [It was not collected by both Howells and it bears the date i884, more than a year after the original publication of the species.] But then he proceeded to designate a specimen at Kew Sauvies