Rapporten innehåller analysen av 26 olika situationer inom ishockey. Situationerna är hårda tacklingar från olika matchar och ligor. Analyserade tacklingar resulterade INTE i hjärnskakning, likadana situationer kan ge upphov till hjärnskakning. Målet med projektet är bland annat skapa en kontrollgrupp för studierna i hjärnskakning inom ishockey. Tidigare studier utfördes för situationer som resulterar i hjärnskakningar. Rapporten pekar kort på huvudet och nackens anatomi d.v.s. skalp, hjärnan och skallben. Begreppet hjärnskakning med dess symptom förklarades också. I valda video sekvenserna analyserades huvudets kinematik och kollisionssekvenser mellan huvud och den andra parten som kan vara en annans axel, huvud, arm eller is eller glasvägg(plexiglas). Resultatet ska komma överens med tidigare gjorda arbete. / The report includes analysis of 15 different situations in Ice-hockey. The situations are hard tackles from different matches and leagues. The analyzed tackles did Not resulted to concussion, but similar situations can be concussions. The goal of the project includes creating a control group for the studies of concussions in ice-hockey. Previous or parallel studies have been down to situations that result to concussions. The report indicates short to head and neck anatomy that is scalp, brain and skull. The concept of concussion with its symptoms explained in this report. The selected video sequences were analyzed head kinematics and collision sequences between the head and the other part that may be another person's shoulder, head, arm or ice or glass wall. When the video sequences were analyzed attempted to controll the head speed, head acceleration and the tackles angle. The results should agree with previous works.

Traumatic brain injury (TBI) is a leading cause of death in all age groups, causing society to be concerned. However, TBI diagnostics and patient outcomes prediction are still lacking in medical science. In this thesis, I used a subset of TBIcare data from Turku University Hospital in Finland to classify the severity, patient outcomes, and CT (computerized tomography) as positive/negative. The dataset was derived from the comprehensive metabolic profiling of serum samples from TBI patients. The study included 96 TBI patients who were diagnosed as 7 severe (sTBI=7), 10 moderate (moTBI=10), and 79 mild (mTBI=79). Among them, there were 85 good recoveries (Good_Recovery=85) and 11 bad recoveries (Bad_Recovery=11), as well as 49 CT positive (CT. Positive=49) and 47 CT negative (CT. Negative=47). There was a total of 455 metabolites (features), excluding three response variables. Feature selection techniques were applied to retain the most important features while discarding the rest. Subsequently, four classifications were used for classification: Ridge regression, Lasso regression, Neural network, and Deep learning. Ridge regression yielded the best results for binary classifications such as patient outcomes and CT positive/negative. The accuracy of CT positive/negative was 74% (AUC of 0.74), while the accuracy of patient outcomes was 91% (AUC of 0.91). For severity classification (multi-class classification), neural networks performed well, with a total accuracy of 90%. Despite the limited number of data points, the overall result was satisfactory.