Product progression: a machine learning approach to forecasting industrial upgrading

Economic complexity methods, and in particular relatedness measures, lack a systematic evaluation and comparison framework. We argue that out-of-sample forecast exercises should play this role, and we compare various machine learning models to set the prediction benchmark. We find that the key object to forecast is the activation of new products, and that tree-based algorithms clearly outperform both the quite strong auto-correlation benchmark and the other supervised algorithms. Interestingly, we find that the best results are obtained in a cross-validation setting, when data about the predicted country was excluded from the training set. Our approach has direct policy implications, providing a quantitative and scientifically tested measure of the feasibility of introducing a new product in a given country.

A comparison of declarative AI techniques for computer automated design of elevator systems

Like other custom-built machinery, elevators are charecterized by a design process which includes selection, sizing and placement of components to fit a given configuration, satisfy users’ requirements and adhere to stringent normative regulations. Unlike mass-produced items, the design process needs to be repeated almost from scratch each time a new configuration is considered. Since elevators are still designed mostly manually, project engineers must engage in time-consuming and error-prone activities over and over again, leaving little to be reused from one design to the next. Computer automated design can provide a cost-effective solution as it relieves the project engineer from such burdens. However, it introduces new challenges both in terms of efficiency — the search space for solutions grows exponentially in the number of component choices — and effectiveness — the perceived quality of the final design may not be as good as in the manual process. In this paper we compare three mainstream AI techniques that can provide problem-solving capabilities inside our tool LiftCreate for automated elevator design, namely Genetic Algorithms (GAs), Constraint Programming (CP) and Satisfiability Modulo Theories (SMT). A special-purpose heuristic search technique embedded in LiftCreate provides us with a yardstick to evaluate the solutions obtained with GAs, CP and SMT and to assess their feasibility for practical applications.

The Language of Innovation

Predicting innovation is a peculiar problem in data science. Following its definition, an innovation is always a never-seen-before event, leaving no room for traditional supervised learning approaches. Here we propose a strategy to address the problem in the context of innovative patents, by defining innovations as never-seen-before associations of technologies and exploiting self-supervised learning techniques. We think of technological codes present in patents as a vocabulary and the whole technological corpus as written in a specific, evolving language. We leverage such structure with techniques borrowed from Natural Language Processing by embedding technologies in a high dimensional euclidean space where relative positions are representative of learned semantics. Proximity in this space is an effective predictor of specific innovation events, that outperforms a wide range of standard link-prediction metrics. The success of patented innovations follows a complex dynamics characterized by different patterns which we analyze in details with specific examples. The methods proposed in this paper provide a completely new way of understanding and forecasting innovation, by tackling it from a revealing perspective and opening interesting scenarios for a number of applications and further analytic approaches.

Considering patient clinical history impacts performance of machine learning models in predicting course of multiple sclerosis

Multiple Sclerosis (MS) progresses at an unpredictable rate, but predictions on the disease course in each patient would be extremely useful to tailor therapy to the individual needs. We explore different machine learning (ML) approaches to predict whether a patient will shift from the initial Relapsing-Remitting (RR) to the Secondary Progressive (SP) form of the disease, using only "real world" data available in clinical routine. The clinical records of 1624 outpatients (207 in the SP phase) attending the MS service of Sant'Andrea hospital, Rome, Italy, were used. Predictions at 180, 360 or 720 days from the last visit were obtained considering either the data of the last available visit (Visit-Oriented setting), comparing four classical ML methods (Random Forest, Support Vector Machine, K-Nearest Neighbours and AdaBoost) or the whole clinical history of each patient (History-Oriented setting), using a Recurrent Neural Network model, specifically designed for historical data. Missing values were handled by removing either all clinical records presenting at least one missing parameter (Feature-saving approach) or the 3 clinical parameters which contained missing values (Record-saving approach). The performances of the classifiers were rated using common indicators, such as Recall (or Sensitivity) and Precision (or Positive predictive value). In the visit-oriented setting, the Record-saving approach yielded Recall values from 70% to 100%, but low Precision (5% to 10%), which however increased to 50% when considering only predictions for which the model returned a probability above a given "confidence threshold". For the History-oriented setting, both indicators increased as prediction time lengthened, reaching values of 67% (Recall) and 42% (Precision) at 720 days. We show how "real world" data can be effectively used to forecast the evolution of MS, leading to high Recall values and propose innovative approaches to improve Precision towards clinically useful values.

A Context Similarity-Based Analysis of Countries' Technological Performance

This work contributes to the literature in the field of innovation by proposing a quantitative approach for the prediction of the timing and location of patenting activity. In a recent work, it was shown that focusing on couples of technological codes allows for the formation of testable predictions of innovation events, defined as the first time two codes appear together in a patent. In particular, the construction of the vector space of codes and the introduction of the context similarity metric allows for a quantitative analysis of technological progress. Here, we move from that result and we show that, through context similarity, it is possible to assign to countries a score which measures the probability of being the first to patent a potential innovation. In other words, we show that we can not only estimate the likelihood that a potential innovation will be patented in the imminent future, but also forecast where it will be patented.

A New and Stable Estimation Method of Country Economic Fitness and Product Complexity

We present a new metric estimating fitness of countries and complexity of products by exploiting a non-linear non-homogeneous map applied to the publicly available information on the goods exported by a country. The non homogeneous terms guarantee both convergence and stability. After a suitable rescaling of the relevant quantities, the non homogeneous terms are eventually set to zero so that this new metric is parameter free. This new map almost reproduces the results of the original homogeneous metrics already defined in literature and allows for an approximate analytic solution in case of actual binarized matrices based on the Revealed Comparative Advantage (RCA) indicator. This solution is connected with a new quantity describing the neighborhood of nodes in bipartite graphs, representing in this work the relations between countries and exported products. Moreover, we define the new indicator of country net-efficiency quantifying how a country efficiently invests in capabilities able to generate innovative complex high quality products. Eventually, we demonstrate analytically the local convergence of the algorithm involved.

Collaboration between a human group and artificial intelligence can improve prediction of multiple sclerosis course: a proof-of-principle study

Background: Multiple sclerosis has an extremely variable natural course. In most patients, disease starts with a relapsing-remitting (RR) phase, which proceeds to a secondary progressive (SP) form. The duration of the RR phase is hard to predict, and to date predictions on the rate of disease progression remain suboptimal. This limits the opportunity to tailor therapy on an individual patient's prognosis, in spite of the choice of several therapeutic options.

Approaches to improve clinical decisions, such as collective intelligence of human groups and machine learning algorithms are widely investigated.

Methods: Medical students and a machine learning algorithm predicted the course of disease on the basis of randomly chosen clinical records of patients that attended at the Multiple Sclerosis service of Sant'Andrea hospital in Rome.

Results: A significant improvement of predictive ability was obtained when predictions were combined with a weight that depends on the consistence of human (or algorithm) forecasts on a given clinical record.

Conclusions: In this work we present proof-of-principle that human-machine hybrid predictions yield better prognoses than machine learning algorithms or groups of humans alone. To strengthen and generalize this preliminary result, we propose a crowdsourcing initiative to collect prognoses by physicians on an expanded set of patients.

Collaboration between a human group and artificial intelligence can improve prediction of multiple sclerosis course: a proof-of-principle study

Background: Multiple sclerosis has an extremely variable natural course. In most patients, disease starts with a relapsing-remitting (RR) phase, which proceeds to a secondary progressive (SP) form. The duration of the RR phase is hard to predict, and to date predictions on the rate of disease progression remain suboptimal. This limits the opportunity to tailor therapy on an individual patient's prognosis, in spite of the choice of several therapeutic options. Approaches to improve clinical decisions, such as collective intelligence of human groups and machine learning algorithms are widely investigated. Methods: Medical students and a machine learning algorithm predicted the course of disease on the basis of randomly chosen clinical records of patients that attended at the Multiple Sclerosis service of Sant'Andrea hospital in Rome. Results: A significant improvement of predictive ability was obtained when predictions were combined with a weight that depends on the consistence of human (or algorithm) forecasts on a given clinical record. Conclusions: In this work we present proof-of-principle that human-machine hybrid predictions yield better prognoses than machine learning algorithms or groups of humans alone. To strengthen and generalize this preliminary result, we propose a crowdsourcing initiative to collect prognoses by physicians on an expanded set of patients.

The heterogeneous dynamics of economic complexity

What will be the growth of the Gross Domestic Product (GDP) or the competitiveness of China, United States, and Vietnam in the next 3, 5 or 10 years? Despite this kind of questions has a large societal impact and an extreme value for economic policy making, providing a scientific basis for economic predictability is still a very challenging problem. Recent results of a new branch—Economic Complexity—have set the basis for a framework to approach such a challenge and to provide new perspectives to cast economic prediction into the conceptual scheme of forecasting the evolution of a dynamical system as in the case of weather dynamics. We argue that a recently introduced non-monetary metrics for country competitiveness (fitness) allows for quantifying the hidden growth potential of countries by the means of the comparison of this measure for intangible assets with monetary figures, such as GDP per capita. This comparison defines the fitness-income plane where we observe that country dynamics presents strongly heterogeneous patterns of evolution. The flow in some zones is found to be laminar while in others a chaotic behavior is instead observed. These two regimes correspond to very different predictability features for the evolution of countries: in the former regime, we find strong predictable pattern while the latter scenario exhibits a very low predictability. In such a framework, regressions, the usual tool used in economics, are no more the appropriate strategy to deal with such a heterogeneous scenario and new concepts, borrowed from dynamical systems theory, are mandatory. We therefore propose a data-driven method—the selective predictability scheme—in which we adopt a strategy similar to the methods of analogues, firstly introduced by Lorenz, to assess future evolution of countries.

How the taxonomy of products drives the economic development of countries

We introduce an algorithm able to reconstruct the relevant network structure on which the time evolution of country-product bipartite networks takes place. The significant links are obtained by selecting the largest values of the projected matrix. We first perform a number of tests of this filtering procedure on synthetic cases and a toy model. Then we analyze the bipartite network constituted by countries and exported products, using two databases for a total of almost 50 years. It is then possible to build a hierarchically directed network, in which the taxonomy of products emerges in a natural way. We study the influence of the structure of this taxonomy network on countries' development; in particular, guided by an example taken from the industrialization of South Korea, we link the structure of the taxonomy network to the empirical temporal connections between product activations, finding that the most relevant edges for countries' development are the ones suggested by our network. These results suggest paths in the product space which are easier to achieve, and so can drive countries' policies in the industrialization process.

Measuring the intangibles: a metrics for the economic complexity of countries and products

We investigate a recent methodology we have proposed to extract valuable information on the competitiveness of countries and complexity of products from trade data. Standard economic theories predict a high level of specialization of countries in specific industrial sectors. However, a direct analysis of the official databases of exported products by all countries shows that the actual situation is very different. Countries commonly considered as developed ones are extremely diversified, exporting a large variety of products from very simple to very complex. At the same time countries generally considered as less developed export only the products also exported by the majority of countries. This situation calls for the introduction of a non-monetary and non-income-based measure for country economy complexity which uncovers the hidden potential for development and growth. The statistical approach we present here consists of coupled non-linear maps relating the competitiveness/fitness of countries to the complexity of their products. The fixed point of this transformation defines a metrics for the fitness of countries and the complexity of products. We argue that the key point to properly extract the economic information is the non-linearity of the map which is necessary to bound the complexity of products by the fitness of the less competitive countries exporting them. We present a detailed comparison of the results of this approach directly with those of the Method of Reflections by Hidalgo and Hausmann, showing the better performance of our method and a more solid economic, scientific and consistent foundation.

A network analysis of countries' export flows: firm grounds for the building blocks of the economy

In this paper we analyze the bipartite network of countries and products from UN data on country production. We define the country-country and product-product projected networks and introduce a novel method of filtering information based on elements' similarity. As a result we find that country clustering reveals unexpected socio-geographic links among the most competing countries. On the same footings the products clustering can be efficiently used for a bottom-up classification of produced goods. Furthermore we mathematically reformulate the "reflections method" introduced by Hidalgo and Hausmann as a fixpoint problem; such formulation highlights some conceptual weaknesses of the approach. To overcome such an issue, we introduce an alternative methodology (based on biased Markov chains) that allows to rank countries in a conceptually consistent way. Our analysis uncovers a strong non-linear interaction between the diversification of a country and the ubiquity of its products, thus suggesting the possible need of moving towards more efficient and direct non-linear fixpoint algorithms to rank countries and products in the global market.

Burden of rotavirus disease and cost-effectiveness of universal vaccination in the Province of Genoa (Northern Italy)

Rotavirus is acknowledged to be a major cause of acute gastroenteritis in infants and young children. As gastroenteritis due to rotavirus is a public health problem and two new vaccines are currently available, we investigated the rotavirus burden and developed a cost-effectiveness analysis, using data collected in the Province of Genoa (Italy), to evaluate the benefits of new borns vaccination. The cost-effectiveness of a rotavirus vaccination programme in the Province of Genoa was performed, in comparison with no vaccination, for both the regional healthcare system (RHS) and society (S). In 2006, admissions to the paediatric emergency department for gastroenteritis numbered 2338 (about 11% of total admissions); of these 33% were hospitalised. In 28% of cases, the children tested positive for rotavirus. During epidemics, paediatricians receive from 3 to 5 calls per day for gastroenteritis, carry out 1 or 2 ambulatory examinations and for children with a severe case history, make house visits. A rotavirus immunisation programme would have a great impact on disease burden, in that 90% coverage would reduce the number of severe cases by more than 85%. From the perspective of both the RHS and S, vaccination proved to be highly cost-effective.

Clause/Term Resolution and Learning in the Evaluation of Quantified Boolean Formulas

Resolution is the rule of inference at the basis of most procedures for automated reasoning. In these procedures, the input formula is first translated into an equisatisfiable formula in conjunctive normal form (CNF) and then represented as a set of clauses. Deduction starts by inferring new clauses by resolution, and goes on until the empty clause is generated or satisfiability of the set of clauses is proven, e.g., because no new clauses can be generated. In this paper, we restrict our attention to the problem of evaluating Quantified Boolean Formulas (QBFs). In this setting, the above outlined deduction process is known to be sound and complete if given a formula in CNF and if a form of resolution, called ``Q-resolution'', is used. We introduce Q-resolution on terms, to be used for formulas in disjunctive normal form. We show that the computation performed by most of the available procedures for QBFs --based on the Davis-Logemann-Loveland procedure (DLL) for propositional satisfiability-- corresponds to a tree in which Q-resolution on terms and clauses alternate. This poses the theoretical bases for the introduction of learning, corresponding to recording Q-resolution formulas associated with the nodes of the tree. We discuss the problems related to the introduction of learning in DLL based procedures, and present solutions extending state-of-the-art proposals coming from the literature on propositional satisfiability. Finally, we show that our DLL based solver extended with learning, performs significantly better on benchmarks used in the 2003 QBF solvers comparative evaluation.

The effect of fresh human serum on ofloxacin bactericidal activity

We have studied the possibility of an increase in ofloxacin bactericidal activity when it is combined with fresh human serum. The tested strains were 10 clinical isolates of Klebsiella pneumoniae. From among our strains 5 were susceptible to serum bactericidal activity and 5 were found to be resistant. We selected two serum concentrations (15 and 35%) to test against susceptible strains and two (55 and 75%) to test against resistant strains in combination with the minimum inhibitory concentration (MIC), 1/2MIC and 1/4MIC of ofloxacin. The results show a slight variability among the tested strains depending on microbiological characteristics of single strains, however, the serum + ofloxacin combination was advantageous. Only one exception was observed: a resistant strain that had an increased survival percentage against ofloxacin and serum in combination.

[Non-epidermidis coagulase-negative staphylococci in infectious diseases of the compromised host]

Today Staphylococcus epidermidis has been recognized as the etiological agent of infectious diseases such as endocarditis, sepsis and meningitis that mainly come out in compromised hosts because of the breaching of the mechanical barrier (cardiosurgical, neurosurgical patients and central venous catheter carriers). Other "non-epidermidis coagulase negative Staphylococci" are more and more frequently isolated from patients at high risk of infection. Faced with these isolations, it is difficult for the clinician and the microbiologist to give these microorganisms their effective pathogenic role. The Authors present a case list of seriously compromised patients in whom non-epidermidis coagulase negative Staphylococci were repeatedly isolated: hemato-oncological patients: the Authors mark out 6 cases of sepsis that is, likely, to be linked to a central venous catheter. The isolated microorganisms were: S. warneri (3 cases); S. haemolyticus (1 case); S. hominis (1 case); S. xylosus (1 case); neurosurgical patients: in whom 3 cases of cerebro-spinal fluid infection were observed; 3 patients carried a ventriculo-peritoneal derivation; 1 patient carried an Ommaya's device. The etiological agents were S. haemolyticus in 2 cases, S. capitis in 1 case. The Authors point out the multiresistance of some strains (S. haemolyticus) and the oxacillin-methicillin resistance phenomenon. They also underline the need for a specific identification of coagulase-negative Staphylococci and the importance of a strict collaboration between clinicians and microbiologists in order to get a correct interpretation of the role played by these microorganisms in infectious diseases of the compromised host.

The activity of antistaphylococcal drugs on nosocomial Staphylococcus epidermidis

In reporting on the activity of cephalothin, cefamandole, FCE 22101, gentamicin, netilmicin, amikacin, rifampicin, clindamycin, josamycin, ofloxacin, ciprofloxacin, vancomycin and teicoplanin on 72 Staphylococcus epidermidis strains clinically isolated in the hospital, the Authors observed a high percentage of methicillin-resistance (68.05%) as well as resistance to other important drugs such as gentamicin (72.22%), rifampicin (27.7%), clindamycin (36.1%), and josamycin (40.27%). They also recorded good inhibitory activity of the studied beta-lactam drugs. However, this activity was not confirmed against methicillin-resistant strains when the test was performed under particular technical conditions (hypertonic medium, incubation at 30 degrees C, inoculum = 10(6)). The Authors also emphasize the poor bactericidal activity against these strains. The activity of quinolones was good; the activity of vancomycin and teicoplanin was very good on all strains studied.

In vitro activity of sulbactam/ampicillin and ampicillin against methicillin-sensitive and methicillin-resistant Staphylococcus aureus and Staphylococcus epidermidis

Minimum inhibitory concentrations (MICs) of ampicillin and ampicillin + sulbactam (1:1) against 165 strains of Staphylococcus aureus and 72 strains of Staphylococcus epidermidis have been evaluated. The activity of the combination was very good. A concentration of 16 micrograms/ml + 16 micrograms/ml inhibited 96.9% of S. aureus and the 100% of S. epidermidis strains (at the same concentration ampicillin alone inhibited only 55.15% and 56.9% of S. aureus and S. epidermidis strains respectively). Activity against methicillin-resistant S. aureus (14.5%) was poor, whereas against methicillin-resistant S. epidermidis (67.2%) the combination maintained high efficacy.

Activity of xibornol against Staphylococcus aureus

The minimal inhibitory concentrations (MIC) and the minimal bactericidal concentrations (MBC) of xibornol against 100 strains of Staphylococcus aureus, clinically isolated, have been evaluated. Xibornol has shown very good in vitro activity and a significant uniformity of the results. In fact the inhibitory and bactericidal activity range was between 2 micrograms/ml and 8 micrograms/ml.

5-Fluorocytosine and Candida yeasts

The authors report 5-fluorocytosine's activity against 101 Candida albicans and 42 Candida non-albicans strains. They point out the drug's lower inhibitory and lethal activity against Candida non-albicans. A 1.56 microgram/ml concentration inhibits 83% of Candida albicans while only 40% of Candida non-albicans is inhibited.

Emerging microorganisms in cystic fibrosis

Pseudomonas aeruginosa is the most common bacterial isolate obtained from patients with cystic fibrosis of the lungs. Recently, however, new multiresistant organisms have emerged, whose identification may be difficult and whose pathogenic role proves hard to define. Of the 71 strains isolated from 24 patients with cystic fibrosis during acute flareups of pulmonary symptoms, 48 turned out to be Pseudomonas aeruginosa (67.6%); 11 were Pseudomonas non-aeruginosa (15.5%); and 12 were Achromobacter xylosoxidans (16.9%). Each bacterial isolate was tested for sensitivity to nine antibiotics (ceftazidime, azlocillin, piperacillin, aztreonam, cefsulodin, cefoperazone, amikacin, tobramycin, and sisomycin) in terms of minimum inhibitory concentration and minimum bactericidal concentration values. In this series, Achromobacter xylosoxidans proved the species least responsive to treatment, and ceftazidime the most active antibiotic both against Achromobacter and against strains of the genus Pseudomonas. Twenty-three different associations of ceftazidime with aminoglycosides, tested for activity on the multiresistant strains, failed to show synergism of action.

Susceptibility of enterococci. I. Inhibitory and bactericidal activity of several chemoantibiotics against Streptococcus faecalis and Streptococcus faecium

The authors present a microbiological study of 100 strains of Enterococcus (70 strains of Streptococcus faecalis and 30 strains of Streptococcus faecium) tested for susceptibility to the following antibiotics, amoxicillin, ampicillin + flucloxacillin, piperacillin, rifampicin, vancomycin, netilmicin, ofloxacin, and norfloxacin. The assessment of minimum inhibitory and minimum bactericidal concentrations of these substances indicates that all have good inhibitory activity except netilmicin, which is active at higher concentrations; with rifampicin and vancomycin showing very poor bactericidal activity. The bactericidal activity of penicillins was hard to assess because of tolerance and paradoxical effect phenomena. The quinolones showed good inhibitory and bactericidal activity.

Susceptibility of enterococci. II. Inhibitory and bactericidal activity of drugs in combination against Streptococcus faecalis and Streptococcus faecium

The microbiological utility of antibiotic combinations against Streptococcus faecalis and Streptococcus faecium strains was studied. The drugs used were netilmicin + amoxicillin (20 strains); netilmicin + piperacillin (20 strains); netilmicin- + vancomycin (20 strains); netilmicin + rifampicin (20 strains). Netilmicin used in combination with the penicillins was advantageous against Streptococcus faecalis, but not uniformly against Streptococcus faecium. The combinations of netilmicin with vancomycin or rifampicin were no more effective than the single drugs in most cases, although the response varied for the different strains of the two species.

[Occurrence of hospital infections in a department of pediatric heart surgery]

The incidence of nosocomial infections (NI) and the related risk factors in a Department of Pediatric Cardiovascular Surgery were studied, during a 6 months period. 155 successive admissions were considered. Nosocomial infections were 17 (11%), nosocomial colonizations 18 (11.6%). The most important risk factors for nosocomial infections were: age, cyanosis, duration of hospitalization, hospitalization in Intensive Care Unit and central venous catheter only as a risk factor for sepsis. The most important risk factors for nosocomial colonizations were: tracheal intubation and central venous catheter. In 4 cases the NI was related to nosocomial colonization (2 sepsis, 1 pneumonia, 1 wound infection). The most frequently isolated microorganisms were Pseudomonas aeruginosa and Staphylococcus spp. The Authors found that a longer than 5 days period of antibiotic prophylaxis did not reduce the incidence of nosocomial infections.