Deconvolution of 1D NMR spectra: A deep learning-based approach.

The analysis of nuclear magnetic resonance (NMR) spectra to detect peaks and characterize their parameters, often referred to as deconvolution, is a crucial step in the quantification, elucidation, and verification of the structure of molecular systems. However, deconvolution of 1D NMR spectra is a challenge for both experts and machines. We propose a robust, expert-level quality deep learning-based deconvolution algorithm for 1D experimental NMR spectra. The algorithm is based on a neural network trained on synthetic spectra. Our customized pre-processing and labeling of the synthetic spectra enable the estimation of critical peak parameters. Furthermore, the neural network model transfers well to the experimental spectra and demonstrates low fitting errors and sparse peak lists in challenging scenarios such as crowded, high dynamic range, shoulder peak regions as well as broad peaks. We demonstrate in challenging spectra that the proposed algorithm is superior to expert results.

Keep breathing! Common motion helps multi-modal mapping.

We propose an unconventional approach for transferring of information between multi-modal images. It exploits the temporal commonality of multi-modal images acquired from the same organ during free-breathing. Strikingly there is no need for capturing the same region by the modalities. The method is based on extracting a low-dimensional description of the image sequences, selecting the common cause signal (breathing) for both modalities and finding the most similar sub-sequences for predicting image feature location. The approach was evaluated for 3 volunteers on sequences of 2D MRI and 2D US images of the liver acquired at different locations. Simultaneous acquisition of these images allowed for quantitative evaluation (predicted versus ground truth MRI feature locations). The best performance was achieved with signal extraction by slow feature analysis resulting in an average error of 2.6 mm (4.2 mm) for sequences acquired at the same (a different) time.

[Medical expert and consultation systems: review and examples for their use]. / Medizinische Experten- und Konsultationssysteme: Uberblick und Anwendungsbeispiele.

After a general introduction into the area of medical expert and consultation systems, a survey about different types of medical expert systems is given. The different objectives and modes of application of medical expert systems are presented and explained in detail. In the second part of this paper, the applicability of computer systems for fully automated interpretation of hepatitis serology findings in the clinical laboratory and for aiding differential diagnosis in internal medicine is described. With the examples given, it is demonstrated that expert systems for clinical decision aid can be of great benefit for the physician in the hospital or the doctor's office.

[Use of the computer in clinical medicine]. / Computereinsatz in der klinischen Medizin.

This article describes the application of computers in clinical medicine and the experience gained by the Institute of Medical Computer Science when introducing computer systems into the clinics of the University of Vienna Medical School in the last 20 years. It is shown what dramatic development has taken place in these years. The medical information system WAMIS with its central patient database is described as well as the medical record keeping documentation and retrieval system WAREL, which is destined to analyze medical natural language data. A further chapter deals with computers in clinical laboratories. At the end it is tried to point out future trends in applying computers in clinical medicine.

Approach to a hospital-based application of a medical expert system.

CADIAG-2 is a data-driven fuzzy medical expert system built for computer-based consultation in internal medicine. It has been integrated into the medical information system WAMIS of the Vienna General Hospital. Through the integration, CADIAG-2 is able to access patient data and laboratory test results already collected in the central patient database of WAMIS. CADIAG-2 operates in two subsequent phases: (1) as an automatic screening procedure for detecting pathological states in the patient, for generating diagnostic hypotheses, and for proposing further useful examinations; and (2) as an on-line consultation system for the clinician to assist him in clarifying patients' disorders completely and in great detail. At present, CADIAG-2 is subject to extended clinical trials. There are four application areas: rheumatic diseases, pancreatic diseases, gall bladder and bile duct diseases and colon diseases. First results on the performance of CADIAG-2 based on the evaluation of about 500 cases were obtained. In this paper, the principal goals, main components and concepts of CADIAG-2, and the experience gained until now are discussed.

[Diagnostic key for intensive care patients: combination of clinical parameters with laboratory findings]. / Diagnoseschlüssel für Intensivpatienten: Kombination klinischer Befunde mit Laboratoriumsbefunden.

A new diagnostic key has been established based on the reports of 3845 critically ill patients in our medical intensive care unit. The clinical diagnoses in these patients were classified in 22 different groups according to different organs or etiological entities (diseases of the liver, infectious diseases, intoxications etc.). 42 different laboratory parameters were selected for classification of metabolic or organ-related complications. Combining of clinical diagnoses with laboratory values characterizes the seriously ill patient. Our new system proved to be practicable in describing the degree, complications and prognosis of disorders in intensive care medicine. The results are demonstrated in patients with hepatic coma.

Carcinoma of the oral cavity: on the prognostic significance of the primary tumour site (by organs) in the oral cavity.

The prognostic significance of so-called organ sites was investigated in 585 cases with carcinoma of the oral cavity and lips. For the subsamples studied the numerical distribution of TNM categories, life tables and life table comparisons were computed. This produced the following results: 1. There is no demonstrable difference in prognosis between identical T catagories in the organs of the oral cavity. 2. In some cases there is a significant difference between identical N categories in organs of the oral cavity. In the No category this is, however, attributable to the substantial differences in the numerical distribution of T categories. By contrast, a logical explanation for the computationally demonstrable significant differences in the Nx category is not available. The problem is currently being investigated. 3. An assessment of identical TN combinations in the "organs" of the oral cavity proved to be impossible on account of the inadequate number of cases available. The so-called "organ localization" of primary tumours in the oral cavity need not - at least for the time being - be accorded any prognostic relevance. The findings should, however, be re-examined on the basis of greater numbers.

[A retrospective study of carcinomas of the oral cavity: a preliminary report (author's transl)]. / Karzinome der Mundhöhle. Vorläufiger Bericht über eine retrospektive Studie.

UNLABELLED: The German-Austrian-Swiss Research Team on Maxillofacial Tumours is investigating a series of 585 carcinomas of the oral cavity, lips and oropharynx by biostatistical methods. The aim of the study is the determination of relevant prognostic symptoms of oral cavity carcinomas, classification of the series on the basis of these symptoms, the determination of therapeutic efficacy and the assessment of collective and individual prognosis. PRELIMINARY RESULTS: 1. Factors of prognostic relevance are probably only tumour size and intensity of regional metastases. 2. The classification of the series becomes problematic due to the lack of relevant prognostic factors.

Carcinoma of the oral cavity: on the prognostic significance of the primary tumour site (by levels and areas).

The prognostic significance of primary tumour site in carcinomas of the oral cavity was investigated in a series of 585 cases. For the subsamples (levels and areas of oral cavity) studied, the numerical distribution of TNM categories, life tables and life table comparisons were computed. This produced the following results: Given an identical extension and analogous metastazising rate, there is no computationally demonstrable difference in prognosis between primary tumours sited at different levels and areas of the oral cavity. The exception are the T1Nx categories, for which a difference exists between precanine and retromolar sites. These results should be re-examined on the basis of a larger series.

TNM-classification of carcinomas of the oral cavity-efficacy of clinically available data (TN).

Using adequate number of cases, the influence of the spread of primary tumour and the degree of regional metastasis on prognosis were investigated. Assuming a practicable classification as a prerequisite for clinico-therapeutic cancer research, experience has shown that the assessment of the spread of primary tumour alone does not suffice for the establishment of comparable homogenous data. The investigation on the importance of the degree of regional metastasis has shown, above all, that the percentage of N3-metastasis within the T-groups contributes essentially to the fact that these show a marked difference in their prognosis. It would therefore appear necessary also to examine the importance of other clinically accessible data in the assessment of prognosis. Only then could we be in a position to judge whether, and to what extent a clinically practicable classification and integration into special groups is possible on the basis of clinically available data. The inclusion of more clinics in the joint investigation is encouraged.

[Prophylactic effect of isosorbide dinitrate on postoperative cardiac complications (author's transl)]. / Prophylaktische Wirkung von Isosorbiddinitrat auf postoperative kardiale Komplikationen

Isosorbide dinitrate (ISD) was administered before, during and after 178 operations performed on 127 patients with arterial occlusive disease. Its influence on postoperative myocardial infarction, heart failure and mortality was tested by comparison with 188 operations performed on 140 patients with hypertension and/or old myocardial infarction receiving no ISD prophylaxis. Risk of cardiac complications was similar in both groups. Mortality in the ISD-treated group was significantly lowered as compared with the control group and was about half of the overall mortality in patients with arterial occlusive disease operated on at our hospital over the past 10 years. This difference depended partly on the influence of ISD on cardiac complications. Post-operative myocardial infarction during ISD prophylaxis occurred in 0.6% of cases as compared with 3.7% in the control group (p less than 0.05), whilst the respective values for postoperative heart failure were 5.7% and 18.2% (p less than 0.001). Both complications are related to absolute or relative hypoxia during the post-operative stress period. ISD is effective by lowering cardiac preload and afterload and thereby diminishing myocardial oxygen demand. ISD is the drug of choice for surgical patients since it provides a steady and long-lasting effect after sublingual absorption. ISD prophylaxis during the perioperative period is indicated in cases with coronary artery disease and with increased cardiac preload or afterload.

[Documentation of obstetric case reports by means of video-terminals as a part of the Vienna General medical information system "WAMIS" (author's transl)]. / Die Dokumentation geburtshilflicher Krankengeschichten mit Hilfe von Bildschirmterminals im Rahmen des Informationssystems WAMIS

A report is given on the introduction of a complete documentation system of obstetric case reports by means of video-terminals and printer-terminals in both departments of Obstetrics and Gynaecology of the 1niversity of Vienna. The special routine for the admission of patients, which produces the heading of the case report is demonstrated, as well as the sheets of collecting the data in respect to case history, antenatal examinations, labour room reports and details of obstetric operations. The computer prints the case history using the collected data. These computer-printed case reports replace the customary handwritten reports. Laboratory data, therapeutic measures and final diagnosis are computed in the same way. The advantages of this form of organization of data collection for clinical purposes and research work are discussed.

[The implementation of a computerized documentation system for the evaluation of spa therapy in patients with rheumatoid arthritis (author's transl)]. / Der Einsatz einer EDVA in der Erfolgsbeurteilung von Kuren bei Patienten mit chronischer Polyarthritis

A previously-described documentation system for articular examination was applied to evaluate the results of spa treatment in 20 patients with rheumatoid arthritis during 3 separate treatment periods. Physical joint findings were documented and indices were compiled by means of a computer before, during and after treatment with thermal water the first year, normal water the second year (or vice versa) and without baths at all in the third year. These indices were compared statistically. Each kind of treatment produced a statistically-significant improvement in the disease, there being no significant difference in the results achieved by the 3 therapeutic regimens.

[Therapy evaluation in rheumatology with an electronic data processing system]. / Therapiebeurteilung in der Rheumatologie mit einem elektronischen Datenverarbeitungssystem

A system for the evaluation of therapeutical effects in rheumatic diseases is presented. This system permits a calculation of two indices: i.e. rheuma-number and "Masszahl" (= only measured values such as range of motion in degrees) which lend themselves to statistical treatment. The result of standardized physical joint examination of patients is recorded on two mark-pages, specially developed for documentation of joint status. The data recorded on the two-mark-pages are then entered into the computer by means of a mark-page-reader. On the basis of these data, the computer, upon the basis of a program specially developed for this purpose, automatically calculates the corresponding amount of negative-points, which parallels the severity of the joint changes, i.e. the rheuma-number ("Rheumazahl"). Separately listed at the end of the status-outprint is the "Masszahl", which is part of the rheuma-number and comprises the measured values (for example, the range of motion measured in degrees). The practicability of this system is demonstrated on the basis of the results of a double-blind-comparison of two antirheumatic-corticosteroid-combinations and an open study with immuno-suppressives in patinets with rheumatoid arthritis.

[TNM-classification of oral cavity neoplasms the value of clinically measurable factors (TN)]. / TNM-Klassifizierung der Mundhöhlenkarzinome--Wertigkeit klinisch fassbarer Sachverhalte (TN).?19H

Problems associated with the classification of cavum oris and labial carcinomata were discussed with particular reference to patients admitted to and treated in seven different clinical hospitals where identical methods of diagnosis and case history evaluation had been used. Using electronic data processing and biostatistical methods it was possible to study the effects of two clinically detectable factors (growth of primary tumor and degree of regional metastasizing) on both the prognosis and classification according to UICC rules. It was possible to show that a determination of the size of primary tumor (T) alone was not sufficient for three homogeneous, prognostically different collectives of tumors to be satisfactorily classified by the new UICC rules. It has been shown that a classification of three collectives of tumors (new classification according to UICC rules), especially as regards the proportion of N3 metastases within the collectives of tumors, was made possible. Therefore, it will be necessary to study the prognostic influences of additional clinically determinable factors with a view to arriving at a useful and practicable classification of oral cavity carcinomata.